Project

Centre for Digital Health Interventions (CDHI), ETH Zurich & University of St.Gallen, www.c4dhi.org

Goal: see www.c4dhi.org

The Center for Digital Health Interventions has the objective to design behavior-oriented, scalable and self-learning digital health interventions that are more effective and cost-efficient than existing interventions. In the CSS Health Lab, a collaboration with CSS Insurance, we focus on interventions for the empowered asthma and diabetes patient. By contrast, projects of the Health Information Systems (IS) Lab focus on various other diseases related to mental health, obesity or drug addiction; the Health IS projects are funded by public bodies and other third-parties.

Date: 1 January 2013

Updates
0 new
0
Recommendations
0 new
0
Followers
0 new
48
Reads
0 new
502

Project log

Tobias Kowatsch
added a research item
BACKGROUND Digital innovations in the mental health care field provide an opportunity to mitigate the global burden of mental disorders such as depression by facilitating timely, accessible, scalable, and affordable interventions. However, there is little evidence on how much these interventions rely on novel automated approaches, such as conversational agents (CAS), just-in-time adaptive interventions (JITAIs), or low-burden sensing technologies. OBJECTIVE Our objectives were: (i) to identify the top-funded companies offering digital health interventions for the prevention and treatment of depression (DHID), (ii) to review DHIDs’ scientific evidence, (iii) to identify which psychotherapy approaches are being used, and (iv) to examine the degree to which these DHIDs include novel automated approaches such as CAs, JITAIs, and low-burden sensing technologies. METHODS A systematic search was conducted using two venture capital databases (Crunchbase and Pitchbook) to identify the top 30 funded companies offering DHIDs. In addition, studies related to the DHIDs were identified via scientific databases (PubMed, Cochrane Library, and APA Psych-info) and hand-searching (companies’ websites). RESULTS The top-30 funded companies offering DHIDs received total funding of 2’592 billion USD up to February 2022. A total of 83 studies were identified by fewer than half of the companies (n=14; 46.6%), of which only 8 (n= 26.6%) employed a randomized controlled trial design. Cognitive-behavioural therapy is the most commonly used psychotherapy approach (n=25, 83.3%), whereas behavioural activation and/or interpersonal therapy (the most effective interventions for depression) were used by only 8 companies (26.6%). Regarding novel technologies, only a few companies incorporated the use of CAs (n=8, 26.6%), or low-burden sensing technologies such as biofeedback-based breathing training with heart rate measurements (n=3, 10%), and only one used a biomarker for depression based on voice features (3.33%). CONCLUSIONS Findings suggest that the amount of funding is not related to the evidence. There is a strong variation in the quantity of evidence provided and an overall need for more rigorous effectiveness trials. Few DHIDs use automated approaches such as CAs and JITAIs, limiting their scalability and delivery of actionable support at the most opportune moments. CLINICALTRIAL N/A
Tobias Kowatsch
added a research item
Background: Noncommunicable diseases (NCDs) constitute a burden on public health. These are best controlled through self-management practices, such as self-information. Fostering patients’ access to health-related information through efficient and accessible channels, such as commercial voice assistants (VAs), may support the patients’ ability to make health-related decisions and manage their chronic conditions. Objective: This study aims to evaluate the reliability of the most common VAs (ie, Amazon Alexa, Apple Siri, and Google Assistant) in responding to questions about management of the main NCD. Methods: We generated health-related questions based on frequently asked questions from health organization, government, medical nonprofit, and other recognized health-related websites about conditions associated with Alzheimer’s disease (AD), lung cancer (LCA), chronic obstructive pulmonary disease, diabetes mellitus (DM), cardiovascular disease, chronic kidney disease (CKD), and cerebrovascular accident (CVA). We then validated them with practicing medical specialists, selecting the 10 most frequent ones. Given the low average frequency of the AD-related questions, we excluded such questions. This resulted in a pool of 60 questions. We submitted the selected questions to VAs in a 3×3×6 fractional factorial design experiment with 3 developers (ie, Amazon, Apple, and Google), 3 modalities (ie, voice only, voice and display, display only), and 6 diseases. We assessed the rate of error-free voice responses and classified the web sources based on previous research (ie, expert, commercial, crowdsourced, or not stated). Results: Google showed the highest total response rate, followed by Amazon and Apple. Moreover, although Amazon and Apple showed a comparable response rate in both voice-and-display and voice-only modalities, Google showed a slightly higher response rate in voice only. The same pattern was observed for the rate of expert sources. When considering the response and expert source rate across diseases, we observed that although Google remained comparable, with a slight advantage for LCA and CKD, both Amazon and Apple showed the highest response rate for LCA. However, both Google and Apple showed most often expert sources for CVA, while Amazon did so for DM. Conclusions: Google showed the highest response rate and the highest rate of expert sources, leading to the conclusion that Google Assistant would be the most reliable tool in responding to questions about NCD management. However, the rate of expert sources differed across diseases. We urge health organizations to collaborate with Google, Amazon, and Apple to allow their VAs to consistently provide reliable answers to health-related questions on NCD management across the different diseases.
Tobias Kowatsch
added a research item
Background and Objective: Researchers use wearable sensing data and machine learning (ML) models to predict various health and behavioral outcomes. However, sensor data from commercial wearables are prone to noise, missing, or artifacts. Even with the recent interest in deploying commercial wearables for long-term studies, there does not exist a standardized way to process the raw sensor data and researchers often use highly specific functions to preprocess, clean, normalize, and compute features. This leads to a lack of uniformity and reproducibility across different studies, making it difficult to compare results. To overcome these issues, we present FLIRT: A Feature Generation Toolkit for Wearable Data; it is an open-source Python package that focuses on processing physiological data specifically from commercial wearables with all its challenges from data cleaning to feature extraction. Methods: FLIRT leverages a variety of state-of-the-art algorithms (e.g., particle filters, ML-based artifact detection) to ensure a robust preprocessing of physiological data from wearables. In a subsequent step, FLIRT utilizes a sliding-window approach and calculates a feature vector of more than 100 dimensions – a basis for a wide variety of ML algorithms. Results: We evaluated FLIRT on the publicly available WESAD dataset, which focuses on stress detection with an Empatica E4 wearable. Preprocessing the data with FLIRT ensures that unintended noise and artifacts are appropriately filtered. In the classification task, FLIRT outperforms the preprocessing baseline of the original WESAD paper. Conclusion: FLIRT provides functionalities beyond existing packages that can address unmet needs in physiological data processing and feature generation: (a) integrated handling of common wearable file formats (e.g., Empatica E4 archives), (b) robust preprocessing, and (c) standardized feature generation that ensures reproducibility of results. Nevertheless, while FLIRT comes with a default configuration to accommodate most situations, it offers a highly configurable interface for all of its implemented algorithms to account for specific needs.
Tobias Kowatsch
added a research item
Background: Slow-paced breathing has been shown to be positively associated with psychological and physiological health. In practice, however, there is little long-term engagement with breathing training, as shown by the usage statistics of breathing training apps. New research suggests that gameful smartphone-delivered breathing training may address this challenge. Objective: This study assesses the impact of breathing training, guided by a gameful visualization, on perceived experiential and instrumental values and the intention to engage in such training. Methods: A between-subject online experiment with 170 participants was conducted, and one-way multiple analysis of variance and two-tailed t test analyses were used to test for any difference in intrinsic experiential value, perceived effectiveness, and the intention to engage in either a breathing training with a gameful or a nongameful guidance visualization. Moreover, prior experience in gaming and meditation practices were assessed as moderator variables for a preliminary analysis. Results: The intrinsic experiential value for the gameful visualization was found to be significantly higher compared to the nongameful visualization (P=.001), but there was no difference in either perceived effectiveness (P=.50) or the intention to engage (P=.44). The preliminary analysis of the influence of meditation and gaming experience on the outcomes indicates that people with more meditation experience yielded higher intrinsic experiential values from using the gameful visualization than people with no or little meditation experience (P=.03). This analysis did not find any additional evidence of gaming time or meditation experience impacting the outcomes. Conclusions: The gameful visualization was found to increase the intrinsic experiential value of the breathing training without decreasing the perceived effectiveness. However, there were no differences in intentions to engage in both breathing training conditions. Furthermore, gaming and meditation experiences seem to have no or only a small positive moderating effect on the relationship between the gameful visualization and the intrinsic experiential value. Future longitudinal field studies are required to assess the impact of gameful breathing training on actual behavior, that is, long-term engagement and outcomes.
Tobias Kowatsch
added a research item
Background: Electronic Health (eHealth) interventions have a potential to increase physical activity of their users. However, their effectiveness varies and they often have only short-lasting effects. One possible way to enhance their effectiveness, is increasing positive outcome expectations of the users by giving them positive suggestions regarding the effectiveness of the intervention. It has been shown that when individuals have positive expectations regarding various types of interventions, they tend to benefit from these interventions more. Objective: The main objective of this web-based study was to investigate whether positive suggestions can change the expectations of the participants regarding the effectiveness of a smartphone physical activity intervention and subsequently enhance the number of steps participants take during the intervention. Additionally, we studied if suggestions affect perceived app effectiveness, engagement with the app, self-reported vitality and fatigue of the participants. Methods: A 21-day physical fully automated activity intervention aimed at helping participants to walk more steps. The intervention was delivered via a smartphone-based application (app), that deliver specific tasks to participants (e.g., setting activity goals or looking for social support) and recorded daily step count of the participants. Participants were randomized to either a positive suggestions group (n = 69) or a control group (n = 64). Positive suggestions emphasizing the effectiveness of the intervention were implemented in an online flyer sent to the participants before the intervention. Suggestions were repeated on day 8 and 15 of the intervention via the app. Results: Participants significantly increased their daily step count from baseline compared to 21 days of the intervention (t (107) = -8.62, p < .001) regardless of the suggestions. Participants in the positive suggestions group had more positive expectations regarding the app (B= -1.61, SE= 0.47, p < 0.001) and higher expected engagement with the app (B= 3.80, SE= 0.63, p < .001) compared to the participants in the control group. No effect of suggestions on the step count (B = -22.05, SE = 334.90, p = .95), perceived effectiveness of the app (B= 0.78, SE= 0.69, p= 0.26), engagement with the app (B= 0.78, SE= 0.75, p= 0.29), and vitality (B= 0.01, SE= 0.11, p= 0.95) were found. Positive suggestions decreased the fatigue of participants during the three weeks of the intervention (B= 0.11, SE= 0.02, p< 0.001). Conclusions: Even though the suggestions did not affect the number of daily steps, they increased the positive expectations of the participants and decreased their fatigue. These results indicate that adding positive suggestions to eHealth physical activity interventions might be a promising way to influence subjective, but not objective, outcomes of interventions. Future research should focus on finding ways to strengthen the suggestions as they have a potential to boost effectiveness of eHealth interventions. Clinical Trial: osf.io/cwjes
Tobias Kowatsch
added a research item
Background: Less than 2% of overweight children and adolescents in Switzerland can participate in multi-component behaviour changing interventions (BCI), due to costs and lack of time. Stress often hinders positive health outcomes in youth with obesity. Digital health interventions, with fewer on-site visits, promise health care access in remote regions; however, evidence for their effectiveness is scarce. Methods: This randomized controlled not blinded trial (1:1) was conducted in a specialized childhood obesity center in Switzerland. Forty-one youth aged 10-18 years old with body mass index (BMI) >P.90 with risk factors or co-morbidities or BMI>P.97 were recruited. During 5.5 months, the PathMate2 group (PM) received daily conversational agent counselling via mobile app, combined with standardized counselling (4 on-site visits). Controls (CON) participated in a BCI (7 on-site visits). We compared the outcomes of both groups after 5.5 (T1) and 12 (T2) months. Primary outcome was reduction in BMI-SDS (BMI standard deviation score). Secondary outcomes were changes in body composition and further physical parameters. Additionally, we hypothesized that less stressed children would lose more weight. Thus, children performed biofeedback relaxation exercises while cortisol and other stress parameters were evaluated. Results: After randomization and dropouts before intervention start (n=10), the median BMI-SDS of all patients (18 PM, 13 CON) at T0 was 2.61 (range 1.7 to 3.5). BMI-SDS decreased significantly at T1 in CON (median change -0.35, -1.6 to 0.1, p=0.002) compared to PM ( 0.08, -0.4 to 0.3, p=0.15), but not at T2. Muscle mass, strength and agility improved significantly in both groups at T2; only PM reduced significantly their body fat at T1 and T2. Average daily PM app usage rate was 71.5%. Cortisol serum levels reduced significantly after biofeedback but with no association between stress parameters and BMI-SDS. No side effects were observed. Conclusions: Equally to BCI, PathMate2 intervention resulted in significant and lasting improvements of physical capacities and body composition, but not in sustained BMI-SDS decrease. This youth-appealing mobile health intervention provides an interesting approach for youth with obesity who have limited access to health care. Biofeedback reduces acute stress and could be an innovative adjunct to usual care.
Tobias Kowatsch
added a research item
Background: Conversational agents (CAs) for chronic disease management are receiving increasing attention in academia and the industry. However, long-term adherence to CAs is still a challenge and needs to be explored. Personalization of CAs has the potential to improve long-term adherence and, with it, user satisfaction, task efficiency, perceived benefits, and intended behavior change. Research on personalized CAs has already addressed different aspects, such as personalized recommendations and anthropomorphic cues. However, detailed information on interaction styles between patients and CAs in the role of medical health care professionals is scant. Such interaction styles play essential roles for patient satisfaction, treatment adherence, and outcome, as has been shown for physician-patient interactions. Currently, it is not clear (1) whether chronically ill patients prefer a CA with a paternalistic, informative, interpretive, or deliberative interaction style, and (2) which factors influence these preferences. Objective: We aimed to investigate the preferences of chronically ill patients for CA-delivered interaction styles. Methods: We conducted two studies. The first study included a paper-based approach and explored the preferences of chronic obstructive pulmonary disease (COPD) patients for paternalistic, informative, interpretive, and deliberative CA-delivered interaction styles. Based on these results, a second study assessed the effects of the paternalistic and deliberative interaction styles on the relationship quality between the CA and patients via hierarchical multiple linear regression analyses in an online experiment with COPD patients. Patients’ sociodemographic and disease-specific characteristics served as moderator variables. Results: Study 1 with 117 COPD patients revealed a preference for the deliberative (50/117) and informative (34/117) interaction styles across demographic characteristics. All patients who preferred the paternalistic style over the other interaction styles had more severe COPD (three patients, Global Initiative for Chronic Obstructive Lung Disease class 3 or 4). In Study 2 with 123 newly recruited COPD patients, younger participants and participants with a less recent COPD diagnosis scored higher on interaction-related outcomes when interacting with a CA that delivered the deliberative interaction style (interaction between age and CA type: relationship quality: b=−0.77, 95% CI −1.37 to −0.18; intention to continue interaction: b=−0.49, 95% CI −0.97 to −0.01; working alliance attachment bond: b=−0.65, 95% CI −1.26 to −0.04; working alliance goal agreement: b=−0.59, 95% CI −1.18 to −0.01; interaction between recency of COPD diagnosis and CA type: working alliance goal agreement: b=0.57, 95% CI 0.01 to 1.13). Conclusions: Our results indicate that age and a patient’s personal disease experience inform which CA interaction style the patient should be paired with to achieve increased interaction-related outcomes with the CA. These results allow the design of personalized health care CAs with the goal to increase long-term adherence to health-promoting behavior.
Tobias Kowatsch
added a research item
Just-In-Time Adaptive Intervention (JITAI) is an emerging technique with great potential to support health behavior by providing the right type and amount of support at the right time. A crucial aspect of JITAIs is properly timing the delivery of interventions, to ensure that a user is receptive and ready to process and use the support provided. Some prior works have explored the association of context and some user-specific traits on receptivity, and have built post-study machine-learning models to detect receptivity. For effective intervention delivery, however, a JITAI system needs to make in-the-moment decisions about a user’s receptivity. To this end, we conducted a study in which we deployed machine-learning models to detect receptivity in the natural environment, i.e., in free-living conditions. We leveraged prior work regarding receptivity to JITAIs and deployed a chatbot-based digital coach – Ally – that provided physical-activity interventions and motivated participants to achieve their step goals. We extended the original Ally app to include two types of machine-learning model that used contextual information about a person to predict when a person is receptive: a static model that was built before the study started and remained constant for all participants and an adaptive model that continuously learned the receptivity of individual participants and updated itself as the study progressed. For comparison, we included a control model that sent intervention messages at random times. The app randomly selected a delivery model for each intervention message. We observed that the machine-learning models led up to a 40% improvement in receptivity as compared to the control model. Further, we evaluated the temporal dynamics of the different models and observed that receptivity to messages from the adaptive model increased over the course of the study.
Tobias Kowatsch
added a research item
Background Mobile health (mHealth) interventions can increase physical activity (PA); however, their long-term impact is not well understood. Objective The primary aim of this study is to understand the immediate and long-term effects of mHealth interventions on PA. The secondary aim is to explore potential effect moderators. Methods We performed this study according to the Cochrane and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We searched PubMed, the Cochrane Library, SCOPUS, and PsycINFO in July 2020. Eligible studies included randomized controlled trials of mHealth interventions targeting PA as a primary outcome in adults. Eligible outcome measures were walking, moderate-to-vigorous physical activity (MVPA), total physical activity (TPA), and energy expenditure. Where reported, we extracted data for 3 time points (ie, end of intervention, follow-up ≤6 months, and follow-up >6 months). To explore effect moderators, we performed subgroup analyses by population, intervention design, and control group type. Results were summarized using random effects meta-analysis. Risk of bias was assessed using the Cochrane Collaboration tool. ResultsOf the 2828 identified studies, 117 were included. These studies reported on 21,118 participants with a mean age of 52.03 (SD 14.14) years, of whom 58.99% (n=12,459) were female. mHealth interventions significantly increased PA across all the 4 outcome measures at the end of intervention (walking standardized mean difference [SMD] 0.46, 95% CI 0.36-0.55; P
Tobias Kowatsch
added a research item
Background Many young adults with type 1 diabetes (T1D) struggle with the complex daily demands of adherence to their medical regimen and fail to achieve target range glycemic control. Few interventions, however, have been developed specifically for this age group. Objective In this randomized trial, we will provide a mobile app (SweetGoals) to all participants as a “core” intervention. The app prompts participants to upload data from their diabetes devices weekly to a device-agnostic uploader (Glooko), automatically retrieves uploaded data, assesses daily and weekly self-management goals, and generates feedback messages about goal attainment. Further, the trial will test two unique intervention components: (1) incentives to promote consistent daily adherence to goals, and (2) web health coaching to teach effective problem solving focused on personalized barriers to self-management. We will use a novel digital direct-to-patient recruitment method and intervention delivery model that transcends the clinic. Methods A 2x2 factorial randomized trial will be conducted with 300 young adults ages 19-25 with type 1 diabetes and (Hb)A1c ≥ 8.0%. All participants will receive the SweetGoals app that tracks and provides feedback about two adherence targets: (a) daily glucose monitoring; and (b) mealtime behaviors. Participants will be randomized to the factorial combination of incentives and health coaching. The intervention will last 6 months. The primary outcome will be reduction in A1c. Secondary outcomes include self-regulation mechanisms in longitudinal mediation models and engagement metrics as a predictor of outcomes. Participants will complete 6- and 12-month follow-up assessments. We hypothesize greater sustained A1c improvements in participants who receive coaching and who receive incentives compared to those who do not receive those components. Results Data collection is expected to be complete by February 2025. Analyses of primary and secondary outcomes are expected by December 2025. Conclusions Successful completion of these aims will support dissemination and effectiveness studies of this intervention that seeks to improve glycemic control in this high-risk and understudied population of young adults with T1D. Trial Registration ClinicalTrials.gov NCT04646473; https://clinicaltrials.gov/ct2/show/NCT04646473 International Registered Report Identifier (IRRID) PRR1-10.2196/27109
Tobias Kowatsch
added a research item
Background: This systematic literature review aims to provide a better understanding of the current methods on VCAs delivering interventions for the prevention and management of chronic and mental conditions. Objective: This systematic literature review aims to provide a better understanding of the current methods on VCAs delivering interventions for the prevention and management of chronic and mental conditions. Methods: We conducted a systematic literature review using PubMed Medline, EMBASE, PsycINFO, Scopus, and Web of Science databases. We included primary research involving the prevention and/or management of chronic or mental conditions through a VCA and reporting an empirical evaluation of the system in terms of system accuracy and/or in terms of technology acceptance. Two independent reviewers conducted screening and data extraction and measured their agreement with Cohen’s kappa. A narrative approach was applied to synthesize the selected records. Results: Twelve out of 7’170 articles met the inclusion criteria. All studies were non-experimental. The VCAs provided behavioral support (N=5), health monitoring services (N=3), or both (N=4). The interventions were delivered via smartphone (N=5), tablet (N=2), or smart speakers (N=3). In two cases, no device was specified. Three VCAs targeted cancer, while two VCAs each targeted diabetes and heart failure. The other VCAs targeted hearing-impairment, asthma, Parkinson's disease, dementia and autism, “intellectual disability”, and depression. The majority of the studies (N=7) assessed technology acceptance but only a minority (N=3) used validated instruments. Half of the studies (N=6) reported either performance measures on speech recognition or on the ability of VCA’s to respond to health-related queries. Only a minority of the studies (N=2) reported behavioral measure or a measure of attitudes towards intervention-related health behavior. Moreover, only a minority of studies (N=4) reported controlling for participant’s previous experience with technology. Finally, risk bias varied markedly. Conclusions: The heterogeneity in the methods, the limited number of studies identified, and the high risk of bias, show that research on VCAs for chronic and mental conditions is still in its infancy. Although results in system accuracy and technology acceptance are encouraging, there still is a need to establish more conclusive evidence on the efficacy of VCAs for the prevention and management of chronic and mental conditions, both in absolute terms and in comparison to standard healthcare.
David Cleres
added a research item
Chronic obstructive pulmonary disease (COPD) is one of the leading causes of death worldwide. To manage the increasing number of COPD patients and reduce the social and economic burden of treatment, healthcare providers have sought to implement remote patient monitoring (RPM). Screen-based RPM applications, such as filling self-reports on the smartphone or computer, have been shown to increase the quality of life, reduce the frequency and severity of exacerbations, and increase physical activity in patients with COPD. These applications, however, are not without challenges for the elderly target population. They are often used on devices designed by and for a different age group, which makes filling out self-reports prone to error and induces fears of technology malfunctions. Voice-based conversational agents (VCAs) are available on more than 2.5 billion devices and are increasingly present in homes worldwide. Aside from their commercial success, VCAs are also credited with several functionalities, such as hands-free use, that make their adoption in healthcare attractive, especially for the elderly. In this work, we investigate the potential of VCAs for RPM of COPD. Specifically, we designed and evaluated Lena, a single-board computer-based VCA framed as a digital member of the medical team. Lena acts as RPM for the early prediction of COPD exacerbations by asking ten symptom-related questions to determine the patient's daily health status. This paper presents the patients' feedback after their interaction with Lena. Patients evaluated the acceptability of the system. Notably, all patients could imagine using the system once a day in the context of a larger study and wished to integrate Lena into their daily routine.
Yanick Xavier Lukic
added a research item
Background Slow-paced breathing training (6 breaths per minute [BPM]) improves physiological and psychological well-being by inducing relaxation characterized by increased heart rate variability (HRV). However, classic breathing training has a limited target group, and retention rates are very low. Although a gameful approach may help overcome these challenges, it is crucial to enable breathing training in a scalable context (eg, smartphone only) and ensure that they remain effective. However, despite the health benefits, no validated mobile gameful breathing training featuring a biofeedback component based on breathing seems to exist. Objective This study aims to describe the design choices and their implementation in a concrete mobile gameful breathing training app. Furthermore, it aims to deliver an initial validation of the efficacy of the resulting app. Methods Previous work was used to derive informed design choices, which, in turn, were applied to build the gameful breathing training app Breeze. In a pretest (n=3), design weaknesses in Breeze were identified, and Breeze was adjusted accordingly. The app was then evaluated in a pilot study (n=16). To ascertain that the effectiveness was maintained, recordings of breathing rates and HRV-derived measures (eg, root mean square of the successive differences [RMSSDs]) were collected. We compared 3 stages: baseline, standard breathing training deployed on a smartphone, and Breeze. ResultsOverall, 5 design choices were made: use of cool colors, natural settings, tightly incorporated game elements, game mechanics reflecting physiological measures, and a light narrative and progression model. Breeze was effective, as it resulted in a slow-paced breathing rate of 6 BPM, which, in turn, resulted in significantly increased HRV measures compared with baseline (P
Tobias Kowatsch
added a research item
Effective interventions for the prevention and treatment of child and adolescent obesity play an important role in reducing the global health and economic burden of non-communicable diseases. Although multi-component interventions targeting various health behaviors are deemed promising, evidence for their effectiveness is still limited. Self-regulation seems to be a relevant working mechanism in this regard. Therefore, we propose a playful, smartphone-based self-regulation training that also utilizes the health benefits of a slow-paced breathing exercise. The mobile app uses the microphone of the smartphone to detect breathing sounds (e.g. inhalation, exhalation) and translates these sounds into a visual biofeedback on the smartphone screen. The design and evaluation of a very first prototype is described in this interdisciplinary work of obesity experts, clinical psychologists, young patients, and computer scientists. The apps' breathing detection module uses a random forest tree for quasi real-time classification of the incoming audio samples and biofeedback generation. A study with 11 obese children and adolescents was conducted to assess the prototype. Results indicate overall positive evaluations and suggestions for improvement. Implications and limitations are discussed, and an outlook on future work is provided.
Tobias Kowatsch
added a research item
Background: Work stress afflicts individual health and well-being. These negative effects could be mitigated through regular monitoring of employees’ stress. Such monitoring becomes even more important as the digital transformation of the economy implies profound changes of working conditions. Objective: To investigate whether the computer mouse can be used for continuous monitoring and early detection of work stress in the field. Methods: We hypothesized that stress is associated with a speed-accuracy tradeoff in computer mouse movements (CMMs). To test this hypothesis, we conducted a longitudinal field study at a large business organization, where CMMs from regular work activities were monitored over seven weeks (70 subjects, n=1,829 observations). A Bayesian regression model was used to estimate whether self-reported acute work stress was associated with a speed-accuracy tradeoff in CMMs. Results: There was a negative association between stress and the two-way interaction term of mouse speed and accuracy (mean = −0.36, lower = −0.66, upper = −0.08), which means that stress was associated with a speed-accuracy tradeoff. The estimated effect was not sensitive to different processing of the data and remained negative after controlling for the demographics, health, and personality traits of subjects. Conclusions: Self-reported acute stress can be inferred from CMMs, specifically in the form of a speed-accuracy tradeoff. This finding suggests to use regular analysis of CMMs for the early and scalable detection of work stress on the job and thus promises more timely and effective stress management.
Tobias Kowatsch
added 7 research items
Thema: Husten ist das häufigste Symptom, bei dem Personen ärztlichen Rat suchen. Die gewöhnliche Erkältung stellt die bekannteste Ursache dar. Darüber hinaus sind steigende Hustenraten mit einer Verschlechterung des Gesundheitszustands bei Krankheiten wie Asthma und COPD assoziiert. Infolgedessen wurden viele Anstrengungen unternommen, um ein objektives Mass für Husten zu schaffen. Bis heute gibt es jedoch keine standardisierte Methode, und es gibt keinen ausreichend validierten generischen Hustenmonitor, der im Handel erhältlich und klinisch akzeptabel ist. Zielsetzung: Ziel dieses Projekts ist es, die Smartphone-basierte Hustenerkennung über 24 Stunden bei 22 COPD-Patienten zu validieren und die erkannten Hustenzahlen mit menschlichen Annotatoren zu vergleichen. Methode: Für das Android-Betriebssystem wurde eine App zur Hustenerkennung entwickelt. Die Detektion des Hustens basiert auf einen Ensemble-Klassifikator von fünf Convolutional Neural Networks. Die App fungiert auch als Audiorecorder, sodass die Erkennung anschliessend verifiziert werden kann. Zusätzlich werden Hustendetektionen an einen Studienserver gesendet und können in Echtzeit über einen Web-Client verfolgt werden. Ergebnisse: Für das Trainieren von Hustenklassifikationsmodellen wurden Audiodaten von 94 Erwachsenen mit Asthma (57% Frauen, Durchschnittsalter 43 Jahre) verwendet, die über 29 Nächte aufgezeichnet wurden. Insgesamt wurden 704.697 Geräusche benutzt, von denen 30.304 als Husten identifiziert wurden. Der Ensemble-Klassifikator wurde vor der Studie auf dem PC evaluiert und schnitt mit einem Matthews-Korrelationskoeffizienten von 94.4% ab. Ob diese Ergebnisse auf dem Smartphone mit COPD Patienten im Krankenhauszimmer oder zu Hause reproduzierbar sind, wird in diesem Projekt erforscht. Fazit: Smartphone-basierte Hustenerkennung kann einen skalierbaren, kostengünstigen Marker für chronische Atemwegserkrankungen liefern.
Hintergrund: Langsames Atmen hat eine positive Wirkung auf die Herzfunktion und auf das psychische Wohlbefinden. Daher werden entsprechende Atemübungen oft bei chronischen Krankheiten empfohlen; sie werden allerdings aus verschiedenen Gründen nur von bestimmten Personengruppen ausgeübt und haben somit eine eingeschränkte Reichweite und Wirkung. Ziel: Die Breeze App verfolgt das Ziel, die Reichweite von Atemübungen mit einem spielerischen und skalierbaren Biofeedback-Ansatz zu erhöhen. Methode: Grundlage der Atemübung Breeze ist die Erkennung der Atmung mit dem Mikrofon des Smartphones, um damit beim Ausatmen «Rückenwind» für ein virtuelles Segelboot zu erzeugen und es somit zu beschleunigen. Entspricht der Atmungs-Zyklus einem validierten Muster (z.B. 4s Einatmung, 2s Ausatmung und 4s Pause), kann mit dem Segelboot, welches in Echtzeit auf dem Bildschirm des Smartphones dargestellt wird, die grösste Reisedistanz zurückgelegt werden. Es wurden Labor-und Online-Experimente durchgeführt, um Breeze hinsichtlich physiologischer Effekte und subjektiver Einschätzungen bei erwachsenen Personen zu evaluieren. Ergebnisse: Im Labor (N=16) konnte gezeigt werden, dass Breeze nicht nur zu einer Steigerung der Herzfrequenzvariabilität geführt hat (p<.001), sondern auch gegenüber einer validierten Atemübung ohne spielerischen Ansatz von 14 (87.5%) Personen präferiert wurde. Ein Online-Experiment mit Teilnehmenden, welche im Schnitt nur wenig bis gar keine Erfahrung mit Atemübungen hatten, zeigte darüber hinaus, dass die wahrgenommene Entspannung durch Breeze (N=88) mit der einer validierten Atemübung (N=82) vergleichbar ist und 51 (58.0%) Personen Breeze im Alltag nutzen würden. Zusammenfassung: Breeze hat mit seinem spielerischen Ansatz das Potential, die Reichweite von Atemübungen zu erhöhen, was insbesondere für das Selbstmanagement bei chronischen Krankheiten relevant sein kann.
Tobias Kowatsch
added a research item
Introduction: Objective markers for asthma, that can be measured without extra patient effort, could mitigate current shortcomings in asthma monitoring. We investigated whether smartphone-recorded nocturnal cough and sleep quality can be utilized for the detection of periods with uncontrolled asthma or meaningful changes in asthma control and for the prediction of asthma attacks. Methods: We analyzed questionnaire and sensor data of 79 adults with asthma. Data were collected in situ for 29 days by means of a smartphone. Sleep quality and nocturnal cough frequencies were measured every night with the Pittsburgh Sleep Quality Index and by manually annotating coughs from smartphone audio recordings. Primary endpoint was asthma control assessed with a weekly version of the Asthma Control Test. Secondary endpoint was self-reported asthma attacks. Results: Mixed-effects regression analyses showed that nocturnal cough and sleep quality were statistically significantly associated with asthma control on a between- and within-patient level (p < 0.05). Decision trees indicated that sleep quality was more useful for detecting weeks with uncontrolled asthma (balanced accuracy (BAC) 68% vs 61%; Δ sensitivity -12%; Δ specificity -2%), while nocturnal cough better detected weeks with asthma control deteriorations (BAC 71% vs 56%; Δ sensitivity 3%; Δ specificity -34%). Cut-offs using both markers predicted asthma attacks up to five days ahead with BACs between 70% and 75% (sensitivities 75 - 88% and specificities 57 - 72%). Conclusion: Nocturnal cough and sleep quality have useful properties as markers for asthma control and seem to have prognostic value for the early detection of asthma attacks. Due to the limited study duration per patient and the pragmatic nature of the study, future research is needed to comprehensively evaluate and externally validate the performance of both biomarkers and their utility for asthma self-management.
Tobias Kowatsch
added a research item
Background: Recent years have witnessed a constant increase in the number of people with chronic conditions requiring ongoing medical support in their everyday lives. However, global health systems are not adequately equipped for this extraordinarily time-consuming and cost-intensive development. Here, conversational agents (CAs) can offer easily scalable and ubiquitous support. Moreover, different aspects of CAs have not yet been sufficiently investigated to fully exploit their potential. One such trait is the interaction style between patients and CAs. In human-to-human settings, the interaction style is an imperative part of the interaction between patients and physicians. Patient-physician interaction is recognized as a critical success factor for patient satisfaction, treatment adherence, and subsequent treatment outcomes. However, so far, it remains effectively unknown how different interaction styles can be implemented into CA interactions and whether these styles are recognizable by users. Objective: The objective of this study was to develop an approach to reproducibly induce 2 specific interaction styles into CA-patient dialogs and subsequently test and validate them in a chronic health care context. Methods: On the basis of the Roter Interaction Analysis System and iterative evaluations by scientific experts and medical health care professionals, we identified 10 communication components that characterize the 2 developed interaction styles: deliberative and paternalistic interaction styles. These communication components were used to develop 2 CA variations, each representing one of the 2 interaction styles. We assessed them in a web-based between-subject experiment. The participants were asked to put themselves in the position of a patient with chronic obstructive pulmonary disease. These participants were randomly assigned to interact with one of the 2 CAs and subsequently asked to identify the respective interaction style. Chi-square test was used to assess the correct identification of the CA-patient interaction style. Results: A total of 88 individuals (42/88, 48% female; mean age 31.5 years, SD 10.1 years) fulfilled the inclusion criteria and participated in the web-based experiment. The participants in both the paternalistic and deliberative conditions correctly identified the underlying interaction styles of the CAs in more than 80% of the assessments (X2=38.2; P<.001; phi coefficient r=0.68). The validation of the procedure was hence successful. Conclusions: We developed an approach that is tailored for a medical context to induce a paternalistic and deliberative interaction style into a written interaction between a patient and a CA. We successfully tested and validated the procedure in a web-based experiment involving 88 participants. Future research should implement and test this approach among actual patients with chronic diseases and compare the results in different medical conditions. This approach can further be used as a starting point to develop dynamic CAs that adapt their interaction styles to their users.
Tobias Kowatsch
added 2 research items
Introduction: The nature of nocturnal cough is largely unknown. It might be a valid marker for asthma control but very few studies characterized it as a basis for better defining its role and its use as clinical marker. This study investigated prevalence and characteristics of nocturnal cough in asthmatics over the course of four weeks. Methods: In two centers, 94 adult patients with physician-diagnosed asthma were recruited. Patient-reported outcomes and nocturnal sensor data were collected by a smartphone with a chat-based study app. Results: Patients coughed in 53% of 2212 nights (range: 0-345 coughs/night). Median coughs per hour were 0 (IQR 0-1). Nocturnal cough rates showed considerable inter-individual variance. The highest counts were measured in the first 30 min in bed (4.5-fold higher than rest of night). Eighty-six percent of coughs were part of a cough cluster. Clusters consisted of a median of two coughs (IQR 2-4). Nocturnal cough was persistent within patient. Conclusion: To the best of the authors' knowledge, this study is the first to describe prevalence and characteristics of nocturnal cough in asthma over a period of one month, demonstrating that it was a prevalent symptom with large variance between patients and high persistence within patients. Cough events in asthmatics were 4.5 times more frequent within the first 30 min in bed indicating a potential role of positional change, and not more frequent during the early morning hours. An important next step will investigate the association between nocturnal cough and asthma control.
Background: Chronic and mental conditions are increasingly prevalent worldwide. As devices in our everyday lives offer more and more voice-based self-service, voice-based conversational agents (VCAs) have the potential to support the prevention and management of these conditions in a scalable way. VCAs allow for a more natural interaction compared to text-based conversational agents, facilitate input for users who cannot type, allow for routine monitoring and support when in-person healthcare is not possible, and open the doors to voice and speech analysis. The state of the art of VCAs for chronic and mental conditions is, however, unclear. Objective: This systematic literature review aims to provide a better understanding of state-of-the-art research on VCAs delivering interventions for the prevention and management of chronic and mental conditions. Methods: We conducted a systematic literature review using PubMed Medline, EMBASE, PsycINFO, Scopus, and Web of Science databases. We included primary research that involved the prevention or management of chronic or mental conditions, where the voice was the primary interaction modality of the conversational agent, and where an empirical evaluation of the system in terms of system accuracy and/or in terms of technology acceptance was included. Two independent reviewers conducted screening and data extraction and measured their agreement with Cohen’s kappa. A narrative approach was applied to synthesize the selected records. Results: Twelve out of 7’170 articles met the inclusion criteria. The majority of the studies (N=10) were non-experimental, while the remainder (N=2) were quasi-experimental. The VCAs provided behavioral support (N=5), a health monitoring service (N=3), or both (N=4). The VCA services were delivered via smartphone (N=5), tablet (N=2), or smart speakers (N=3). In two cases, no device was specified. Three VCAs targeted cancer, while two VCAs each targeted diabetes and heart failure. The other VCAs targeted hearing-impairment, asthma, Parkinson's disease, dementia and autism, “intellectual disability”, and depression. The majority of the studies (N=7) assessed technology acceptance but only a minority (N=3) used validated instruments. Half of the studies (N=6) reported either performance measures on speech recognition or on the ability of VCA’s to respond to health-related queries. Only a minority of the studies (N=2) reported behavioral measure or a measure of attitudes towards intervention-related health behavior. Moreover, only a minority of studies (N=4) reported controlling for participant’s previous experience with technology. Conclusions: Considering the heterogeneity of the methods and the limited number of studies identified, it seems that research on VCAs for chronic and mental conditions is still in its infancy. Although results in system accuracy and technology acceptance are encouraging, there still is a need to establish evidence on the efficacy of VCAs for the prevention and management of chronic and mental conditions, both in absolute terms and in comparison to standard healthcare.
Tobias Kowatsch
added a research item
Smartphones promise great potential for personality science to study people's everyday life behaviours. Even though personality psychologists have become increasingly interested in the study of personality states, associations between smartphone data and personality states have not yet been investigated. This study provides a first step towards understanding how smartphones may be used for behavioural assessment of personality states. We explored the relationships between Big Five personality states and data from smartphone sensors and usage logs. On the basis of the existing literature, we first compiled a set of behavioural and situational indicators, which are potentially related to personality states. We then applied them on an experience sampling data set containing 5748 personality state responses that are self-assessments of 30 minutes timeframes and corresponding smartphone data. We used machine learning analyses to investigate the predictability of personality states from the set of indicators. The results showed that only for extraversion, smartphone data (specifically, ambient noise level) were informative beyond what could be predicted based on time and day of the week alone. The results point to continuing challenges in realizing the potential of smartphone data for psychological research.
Tobias Kowatsch
added a research item
Background The Assistant to Lift your Level of activitY (Ally) app is a smartphone application that combines financial incentives with chatbot-guided interventions to encourage users to reach personalized daily step goals. Purpose To evaluate the effects of incentives, weekly planning, and daily self-monitoring prompts that were used as intervention components as part of the Ally app. Methods We conducted an 8 week optimization trial with n = 274 insurees of a health insurance company in Switzerland. At baseline, participants were randomized to different incentive conditions (cash incentives vs. charity incentives vs. no incentives). Over the course of the study, participants were randomized weekly to different planning conditions (action planning vs. coping planning vs. no planning) and daily to receiving or not receiving a self-monitoring prompt. Primary outcome was the achievement of personalized daily step goals. Results Study participants were more active and healthier than the general Swiss population. Daily cash incentives increased step-goal achievement by 8.1%, 95% confidence interval (CI): [2.1, 14.1] and, only in the no-incentive control group, action planning increased step-goal achievement by 5.8%, 95% CI: [1.2, 10.4]. Charity incentives, self-monitoring prompts, and coping planning did not affect physical activity. Engagement with planning interventions and self-monitoring prompts was low and 30% of participants stopped using the app over the course of the study. Conclusions Daily cash incentives increased physical activity in the short term. Planning interventions and self-monitoring prompts require revision before they can be included in future versions of the app. Selection effects and engagement can be important challenges for physical-activity apps. Clinical Trial Information This study was registered on ClinicalTrials.gov, NCT03384550.
Tobias Kowatsch
added 2 research items
Illness management among married adults is mainly shared with their spouses and it involves social support. Social support among couples has been shown to affect emotional well-being positively or negatively and result in healthier habits among diabetes patients. Hence, through automatic emotion recognition, we could have an assessment of the emotional well-being of couples which could inform the development and triggering of interventions to help couples better manage chronic diseases. We are developing an emotion recognition system to recognize the emotions of real couples in everyday life and in this paper, we describe our approach to collecting sensor and self-report emotion data among Swiss-based German-speaking couples in everyday life. We also discuss various aspects of the study such as our novel approach of triggering data collection based on detecting that the partners are close and speaking, the self-reports and multimodal data as well as privacy concerns with our method.
Couples’ relationships affect partners’ mental and physical well-being. Automatic recognition of couples’ emotions will not only help to better understand the interplay of emotions, intimate relationships, and health and well-being, but also provide crucial clinical insights into protective and risk factors of relationships, and can ultimately guide interventions. However, several works developing emotion recognition algorithms use data from actors in artificial dyadic interactions and the algorithms are likely not to perform well on real couples. We are developing emotion recognition methods using data from real couples and, in this paper, we describe two studies we ran in which we collected emotion data from real couples — Dutch-speaking couples in Belgium and German-speaking couples in Switzerland. We discuss our approach to eliciting and capturing emotions and make five recommendations based on their relevance for developing well-performing emotion recognition systems for couples.
Tobias Kowatsch
added 4 research items
Despite the widely known necessity to counteract the increase in physical inactivity, only small strides have been achieved so far. Digital health interventions (DHIs) are proposed to reach both healthy and at-risk populations on a large scale. However, designing scalable DHIs that are engaging in the long term remains a challenge. Small financial incentives may help to achieve such long-lasting behaviour changes. This work thusly investigates the effects of daily or monthly paid small financial incentives on step counts and goal achievements in physical activity. Six-month observational field data of a physical activity DHI (PADHI), offered by a Swiss health insurer, was used for this investigation. From 1623 contacted customers, 742 (45.7%) joined the PADHI. Step counts and times the challenging goal was reached were significantly higher in the condition of daily paid incentives. The findings from objectively measure daily step counts and goal achievements indicate better outcomes when incentives are paid daily. Further findings indicate the importance of recording various physical activities and not only step counts.
Leveraging new technological tools in medical service delivery has been shown as important factor adding scalability and/or value to patient care. However, as of yet, relatively little research has focused on the implementation of mass-market digital health products to address population needs. The current paper examines one such tool; a browser-optimized smartphone app developed by a major Swiss health insurance, offering validated medical information for patients to identify the optimal care path of action (i.e. self-care, pharmacy visit, general practitioner visit, hospital visit). Summary statistics of usage data from 149 922 users over 6 months are outlined, overviewing; (i) key usage cases for the service over time, (ii) for whom the app was used, (iii) dropout rates and potential design pitfalls. Possible themes are identified such as the importance of additional information regarding privacy or service/usage experience information, and some considerations for both the research, design and implementation communities.
In recent years, mobile health (mHealth) technologies have received increasing attention from industry and researchers. Such technologies have been the focus of both criticism and high expectations. In this paper, we analyze the integration of mHealth tools in everyday life. Insights into the actual use of such tools have empirical importance and could contribute to our theoretical understanding of mHealth technologies. Our research is based on 23 interviews with the participants of a smartphone-based mobile health intervention aimed at increasing physical activity. We followed the principles of grounded theory during data collection and our analysis is framed by the domestication approach. Our results reveal that the intervention design can result in the participants feeling ill-represented by the reductive nature of the data they generate. The results also reveal the inadequacy between biomedical standards and the social contexts of use. In addition, we describe how middle-class users perceive step-counting through the prism of a moralizing ethos of self-responsibility. Our research has practical implications for the developers and participants of mHealth interventions and theoretical implications regarding mHealth as a societal practice. We also suggest that mHealth-related public policies may fail to reach certain population groups, namely those who do not share the values that surround those technologies and their uses.
Tobias Kowatsch
added 2 research items
Slow-paced biofeedback-guided breathing training has been shown to improve cardiac functioning and psychological well-being. Current training options, however, attract only a fraction of individuals and are limited in their scalability as they require dedicated biofeedback hardware. In this work, we present Breeze, a mobile application that uses a smartphone's microphone to continuously detect breathing phases, which then trigger a gamified biofeedback-guided breathing training. Circa 2.76 million breathing sounds from 43 subjects and control sounds were collected and labeled to train and test our breathing detection algorithm. We model breathing as inhalation-pause-exhalation-pause sequences and implement a phase-detection system with an attention-based LSTM model in conjunction with a CNN-based breath extraction module. A biofeedback-guided breathing training with Breeze takes place in real-time and achieves 75.5% accuracy in breathing phases detection. Breeze was also evaluated in a pilot study with 16 new subjects, which demonstrated that the majority of subjects prefer Breeze over a validated active control condition in its usefulness, enjoyment, control, and usage intentions. Breeze is also effective for strengthening users' cardiac functioning by increasing high-frequency heart rate variability. The results of our study suggest that Breeze could potentially be utilized in clinical and self-care activities.
Recent advancements in sensing techniques for mHealth applications have led to successful development and deployments of several mHealth intervention designs, including Just-In-Time Adaptive Interventions (JITAI). JITAIs show great potential because they aim to provide the right type and amount of support, at the right time. Timing the delivery of a JITAI such as the user is receptive and available to engage with the intervention is crucial for a JITAI to succeed. Although previous research has extensively explored the role of context in users’ responsiveness towards generic phone notifications, it has not been thoroughly explored for actual mHealth interventions. In this work, we explore the factors affecting users’ receptivity towards JITAIs. To this end, we conducted a study with 189 participants, over a period of 6 weeks, where participants received interventions to improve their physical activity levels. The interventions were delivered by a chatbot-based digital coach ś Ally ś which was available on Android and iOS platforms. We define several metrics to gauge receptivity towards the interventions, and found that (1) several participant-specific characteristics (age, personality, and device type) show significant associations with the overall participant receptivity over the course of the study, and that (2) several contextual factors (day/time, phone battery, phone interaction, physical activity, and location), show significant associations with the participant receptivity, in-the-moment. Further, we explore the relationship between the effectiveness of the intervention and receptivity towards those interventions; based on our analyses, we speculate that being receptive to interventions helped participants achieve physical activity goals, which in turn motivated participants to be more receptive to future interventions. Finally, we build machine-learning models to detect receptivity, with up to a 77% increase in F1 score over a biased random classifier.
Tobias Kowatsch
added 8 research items
Background: Type II diabetes mellitus (T2DM) is a common chronic disease. To manage blood glucose levels, patients need to follow medical recommendations for healthy eating, physical activity, and medication adherence in their everyday life. Illness management is mainly shared with partners and involves social support and common dyadic coping (CDC). Social support and CDC have been identified as having implications for people’s health behavior and well-being. Visible support, however, may also be negatively related to people’s well-being. Thus, the concept of invisible support was introduced. It is unknown which of these concepts (ie, visible support, invisible support, and CDC) displays the most beneficial associations with health behavior and well-being when considered together in the context of illness management in couple’s everyday life. Therefore, a novel ambulatory assessment application for the open-source behavioral intervention platform MobileCoach (AAMC) was developed. It uses objective sensor data in combination with self-reports in couple’s everyday life. Objective: The aim of this paper is to describe the design of the Dyadic Management of Diabetes (DyMand) study, funded by the Swiss National Science Foundation (CR12I1_166348/1). The study was approved by the cantonal ethics committee of the Canton of Zurich, Switzerland (Req-2017_00430). Methods: This study follows an intensive longitudinal design with 2 phases of data collection. The first phase is a naturalistic observation phase of couples’ conversations in combination with experience sampling in their daily lives, with plans to follow 180 T2DM patients and their partners using sensor data from smartwatches, mobile phones, and accelerometers for 7 consecutive days. The second phase is an observational study in the laboratory, where couples discuss topics related to their diabetes management. The second phase complements the first phase by focusing on the assessment of a full discussion about diabetes-related concerns. Participants are heterosexual couples with 1 partner having a diagnosis of T2DM. Results: The AAMC was designed and built until the end of 2018 and internally tested in March 2019. In May 2019, the enrollment of the pilot phase began. The data collection of the DyMand study will begin in September 2019, and analysis and presentation of results will be available in 2021. Conclusions: For further research and practice, it is crucial to identify the impact of social support and CDC on couples’ dyadic management of T2DM and their well-being in daily life. Using AAMC will make a key contribution with regard to objective operationalizations of visible and invisible support, CDC, physical activity, and well-being. Findings will provide a sound basis for theory- and evidence-based development of dyadic interventions to change health behavior in the context of couple’s dyadic illness management. Challenges to this multimodal sensor approach and its feasibility aspects are discussed. International Registered Report Identifier (IRRID): PRR1-10.2196/13685
Smartwatches provide a unique opportunity to collect more speech data because they are always with the user and also have a more exposed microphone compared to smartphones. Speech data could be used to infer various indicators of mental well being such as emotions, stress and social activity. Hence, real-time voice activity detection (VAD) on smartwatches could enable the development of applications for mental health monitoring. In this work, we present VADLite, an open-source, lightweight, system that performs real-time VAD on smartwatches. It extracts mel-frequency cepstral coefficients and classifies speech versus non-speech audio samples using a linear Support Vector Machine. The real-time implementation is done on the Wear OS Polar M600 smartwatch. An offline and online evaluation of VADLite using real-world data showed better performance than WebRTC's open-source VAD system. VADLite can be easily integrated into Wear OS projects that need a lightweight VAD module running on a smartwatch.
Laut WHO sind chronische Krankheiten wie Herz-Kreislauf-Erkrankungen, Krebs, Diabetes oder Asthma weltweit für circa 70 % aller Todesfälle verantwortlich. Leistungserbringer haben allerdings nur beschränkte Ressourcen und können den Gesundheitszustand im Alltag von Patienten nicht kontinuierlich erheben und daher auch nicht immer rechtzeitig intervenieren, bevor es zu einer allfälligen Hospitalisierung kommt. Vor diesem Hintergrund diskutiert dieser interdisziplinäre Beitrag das Potenzial digitaler Pillen. Das Ziel digitaler Pillen besteht darin, Gesundheitszustände mithilfe von Informations- und Kommunikationstechnologie möglichst kontinuierlich, zweckdienlich und bequem zu erheben und nur dann zu intervenieren, wenn es unbedingt sein muss, kurzum Patienten den Umgang mit ihrer chronischen Krankheit im Alltag zu erleichtern. Nach einer Einleitung wird das Konzept digitaler Pillen näher erläutert. Danach werden fünf digitale Pillen aus den Bereichen Gesundheitskompetenz, Prävention und Therapie näher vorgestellt. Abschließend wird das Konzept der digitalen Pille kritisch reflektiert und Potenziale sowie Herausforderungen werden diskutiert.
Filipe Barata
added a research item
MobileCoach, an open source behavioral intervention platform, has been developed to provide health professionals with an authoring tool to design evidence-based, scalable and low-cost digital health interventions (DHI). Its potential meets the lack in resources and capacity of health care systems to provide DHI for the treatment of noncommunicable diseases. In the current work, we introduce the first personalization approach for MobileCoach with the purpose of identifying the needs of participants, tailoring the treatment and, as a consequence, enhancing the capability of MobileCoach-based DHIs. The personalization approach is then exemplified by a very first prototype of a DHI for people with asthma that is able to detect coughing by just using a smartphone's microphone. First empirical results with five healthy subjects and 80 coughs indicate its technical feasibility as the detection accuracy yielded 83.3%. Future work will focus on the integration of personalized sensing and supporting applications for MobileCoach.
Filipe Barata
added a research item
Ubiquitous mobile devices have the potential to reduce the financial burden of healthcare systems by providing scalable and cost-efficient health monitoring applications. Coughing is a symptom associated with prevalent pulmonary diseases, and bears great potential for being exploited by monitoring applications. Prior research has shown the feasibility of cough detection by smartphone-based audio recordings, but it is still open as to whether current detection models generalize well to a variety of mobile devices to ensure scalability. We first conducted a lab study with 43 subjects and recorded 6737 cough samples and 8854 control sounds by 5 different recording devices. We then reimplemented two approaches from prior work and investigated their performance in two different scenarios across devices. We propose an efficient convolutional neural network architecture and an ensemble based classifier to reduce the cross-device discrepancy. Our approach produced mean accuracies in the range [85.9%, 90.9%], showing consistency across devices (SD = [1.5%, 2.7%]) and outperforming prior learning algorithms. Thus, our proposal is a step towards cost-efficient, ubiquitous, scalable and device-agnostic cough detection.
Jan-Niklas Kramer
added a research item
Introduction: There has been limited research investigating whether small financial incentives can promote participation, behavior change, and engagement in physical activity promotion programs. This study evaluates the effects of two types of small financial incentives within a physical activity promotion program of a Swiss health insurance company. Study design: Three-arm cluster-randomized trial comparing small personal financial incentives and charity financial incentives (10 Swiss Francs, equal to US$10.40) for each month with an average step count of >10,000 steps per day to control. Insureds' federal state of residence was the unit of randomization. Data were collected in 2015 and analyses were completed in 2018. Setting/participants: German-speaking insureds of a large health insurer in Switzerland were invited. Invited insureds were aged ≥18 years, enrolled in complementary insurance plans and registered on the insurer's online platform. Main outcome measures: Primary outcome was the participation rate. Secondary outcomes were steps per day, the proportion of participant days in which >10,000 steps were achieved and non-usage attrition over the first 3 months of the program. Results: Participation rate was 5.94% in the personal financial incentive group (OR=1.96, 95% CI=1.55, 2.49) and 4.98% in the charity financial incentive group (OR=1.59, 95% CI=1.25, 2.01) compared with 3.23% in the control group. At the start of the program, the charity financial group had a 12% higher chance of walking 10,000 steps per day than the control group (OR=1.68, 95% CI=1.23, 2.30), but this effect dissipated after 3 months. Steps per day and non-usage attrition did not differ significantly between the groups. Conclusions: Small personal and charity financial incentives can increase participation in physical activity promotion programs. Incentives may need to be modified in order to prevent attrition and promote behavior change over a longer period of time. Trial registration: This study is registered at www.isrctn.com ISRCTN24436134.
Peter Tinschert
added 3 research items
Introduction: Nocturnal cough is a burdensome asthma symptom. However, knowledge about the prevalence of nocturnal cough in asthma is limited. Furthermore, prior research has shown that nocturnal cough and impaired sleep quality are associated with asthma control, but the association between these two symptoms remains unclear. This study further investigates the potential of these symptoms as markers for asthma control and the accuracy of automated, smartphone-based passive monitoring for nocturnal cough detection and sleep quality assessment. Methods and analysis: The study is a multicentre, longitudinal observational study with two stages. Sensor and questionnaire data of 94 individuals with asthma will be recorded for 28 nights by means of a smartphone. On the first and the last study day, a participant’s asthma will be clinically assessed, including spirometry and fractionated exhaled nitric oxide levels. Asthma control will be assessed by the Asthma Control Test and sleep quality by means of the Pittsburgh Sleep Quality Index. In addition, nocturnal coughs from smartphone microphone recordings will be labelled and counted by human annotators. Relatively unrestrictive eligibility criteria for study participation are set to support external validity of study results. Analysis of the first stage is concerned with the prevalence and trends of nocturnal cough and the accuracies of smartphone-based automated detection of nocturnal cough and sleep quality. In the second stage, patient-reported asthma control will be predicted in a mixed effects regression model with nocturnal cough frequencies and sleep quality of past nights as the main predictors. Ethics and dissemination: The study was reviewed and approved by the ethics commission responsible for research involving humans in eastern Switzerland (BASEC ID: 2017–01872). All study data will be anonymised on study termination. Results will be published in medical and technical peer-reviewed journals.
Tobias Kowatsch
added a research item
Diabetes mellitus Type II (T2DM) is a common chronic disease of the endocrine system in which the pancreas no longer produces enough insulin to metabolize blood glucose or the body becomes less sensitive to insulin. To manage blood glucose levels and to reduce the risk of diabetes-related complications (e.g., cardiovascular diseases, vision loss, amputations), patients need to follow medical recommendations for healthy eating, physical activity, and medication adherence in their everyday life. Evidence suggests that for married adults, illness management is mainly shared with their spouses. Spousal support is associated with healthier habits among diabetes patients. Additionally, spousal support has been shown to have beneficial effects on well-being or affect (feelings). Given that there is some relationship between spousal support and affect, through affect detection, we may have a proxy for received spousal support. Considering the health benefits of spousal support especially for chronic disease management, affect detection could be used to inform just-in-time adaptive interventions. In this ongoing work to develop an affect detection system for couples’ chronic illness management, we describe the specific research questions we want answer, our potential technical contributions, our data collection plan and finally our data analysis plan.
Jan-Niklas Kramer
added a research item
Background: Smartphones enable the implementation of just-in-time adaptive interventions (JITAIs) that tailor the delivery of health interventions over time to user- and time-varying context characteristics. Ideally, JITAIs include effective intervention components, and delivery tailoring is based on effective moderators of intervention effects. Using machine learning techniques to infer each user's context from smartphone sensor data is a promising approach to further enhance tailoring. Objective: The primary objective of this study is to quantify main effects, interactions, and moderators of 3 intervention components of a smartphone-based intervention for physical activity. The secondary objective is the exploration of participants' states of receptivity, that is, situations in which participants are more likely to react to intervention notifications through collection of smartphone sensor data. Methods: In 2017, we developed the Assistant to Lift your Level of activitY (Ally), a chatbot-based mobile health intervention for increasing physical activity that utilizes incentives, planning, and self-monitoring prompts to help participants meet personalized step goals. We used a microrandomized trial design to meet the study objectives. Insurees of a large Swiss insurance company were invited to use the Ally app over a 12-day baseline and a 6-week intervention period. Upon enrollment, participants were randomly allocated to either a financial incentive, a charity incentive, or a no incentive condition. Over the course of the intervention period, participants were repeatedly randomized on a daily basis to either receive prompts that support self-monitoring or not and on a weekly basis to receive 1 of 2 planning interventions or no planning. Participants completed a Web-based questionnaire at baseline and postintervention follow-up. Results: Data collection was completed in January 2018. In total, 274 insurees (mean age 41.73 years; 57.7% [158/274] female) enrolled in the study and installed the Ally app on their smartphones. Main reasons for declining participation were having an incompatible smartphone (37/191, 19.4%) and collection of sensor data (35/191, 18.3%). Step data are available for 227 (82.8%, 227/274) participants, and smartphone sensor data are available for 247 (90.1%, 247/274) participants. Conclusions: This study describes the evidence-based development of a JITAI for increasing physical activity. If components prove to be efficacious, they will be included in a revised version of the app that offers scalable promotion of physical activity at low cost. Trial registration: ClinicalTrials.gov NCT03384550; https://clinicaltrials.gov/ct2/show/NCT03384550 (Archived by WebCite at http://www.webcitation.org/74IgCiK3d). International registered report identifier (irrid): DERR1-10.2196/11540.
Tobias Kowatsch
added 2 research items
Context: Intervention components of a MobileCoach based smartphone app to promote walking were assessed in a seven-week micro-randomized trial (N = 274). In order to make a significant contribution to public health, the app must also engage those at higher risk for adverse health outcomes, i.e. elderly, less active or less healthy participants. Methods: In a secondary analysis, longitudinal trajectories of participants’ number of daily app sessions were clustered using the k-means algorithm with an alternating number of clusters. An app session was defined as any interaction between a participant and the app separated by at least five minutes between interactions. The final number of clusters was determined based on five different clustering quality criteria. Results: Two different clusters emerged: stable high engagement (31.3% of participants, 7.6 (SD = 2.9) mean daily app sessions) and stable low engagement (68.7% of participants, 1.5 (SD = 1.4) mean daily app sessions). Highly engaged participants were older (45.8 vs. 40.1 years, p < .001, d = 0.43) and accumulated more steps per day during the study (7373 vs. 5828 steps per day, p < .001, d = 0.57). Clusters did not differ with regard to participants’ baseline physical activity, gender, body mass index, self-reported health status or education. Conclusions: A chatbot-based walking app engaged participants of a micro-randomized trial over a period of seven weeks independent of their risk for adverse health outcomes. Thus, participants with low risk for adverse health outcomes at baseline do not drive high engagement with the app.
Context: In situ patient data over multiple weeks are needed to explore the potential of nocturnal cough and sleep quality as digital biomarkers for asthma. Methods: Ninety-four asthmatics need to complete a 29-day EMA study in which nocturnal smartphone sensor data is recorded and daily questionnaires of 13 to 45 items are delivered by an adapted version of the MobileCoach app. Patients are withdrawn from the study in case of non-adherence on more than five days. Adherence is not financially incentivized. Appointments with health professionals take place on the first and last day. Intervention: Engagement, operationalized as response rates to the questionnaires, is promoted using the following strategies: first, patients discuss with health professionals how they will integrate the study app tasks in their daily routine. Second, working alliance is established through the chat-based interaction with the app’s virtual study nurse. Third, non-adherence is illustrated as lost hearts to elicit loss aversion. Finally, in case of non-adherence (on consecutive days) a notification system sends out reminder SMS to patients (prompts calls from health professionals). Results: The first 29 patients successfully completed 791 of the 810 daily questionnaires (97.65%). 58 reminder SMS were sent to patients and 13 calls by health professionals were triggered. One patient lost all hearts and was withdrawn from the study. The remaining patients completed the study with an average of 4.61/5 hearts (SD = 0.83). Conclusion: The preliminary results suggest that the employed strategies successfully promoted engagement in a population known for non-adherence in clinical practice.
Tobias Kowatsch
added a research item
Die «Digitalisierung der Medizin» weckt grosse Hoffnungen auf eine effizientere und zunehmend bessere Medizin. Begriffe wie «Digitalisierung» und «künstliche Intelligenz» erzeugen zugleich aber auch Ängste. Dabei ist die Digitalisierung, die Erfassung und Speicherung von Daten in digitaler Form, nichts grundlegend Neues; neu hingegen sind die algorithmischen Fortschritte, kombiniert mit der enormen Leistungsfähigkeit moderner Computersysteme, aber auch die kostengünstige Speicherung und Übertragung grosser Datenmengen. Diese Errungenschaften haben das Potential, die Patientenversorgung merklich zu verbessern.
Tobias Kowatsch
added a research item
Childhood obesity is an increasingly pervasive problem. Traditional therapy programs are time-and cost-intensive. Furthermore, success of therapy is often not guaranteed. Typically, success of therapies is determined by comparison of body mass index (BMI) before and after a therapy. In this paper, we present a Data-analytical Information Systems (DAIS) that provides predictions of future BMI changes before conducting a therapy. The DAIS considers current parameters like age as well as heart rate during a standardized exercise. By predicting outcomes of a therapy, healthcare practitioners could personalize standard therapies and improve the outcome. We collected data from randomized clinical trial and trained Machine Learning models to estimate whether BMI will decrease after therapy with 85% accuracy. Accuracy of predictions is compared with domain experts' predictions. Further, we present empirical results of the domain experts' perception regarding the proposed DAIS. Our DAIS provides positive evidence as a tool for personalized medicine.
Jan-Niklas Kramer
added a research item
BACKGROUND Smartphones enable the implementation of just-in-time adaptive interventions (JITAIs) that tailor the delivery of health interventions over time to user- and time-varying context characteristics. Ideally, JITAIs include effective intervention components, and delivery tailoring is based on effective moderators of intervention effects. Using machine learning techniques to infer each user’s context from smartphone sensor data is a promising approach to further enhance tailoring. OBJECTIVE The primary objective of this study is to quantify main effects, interactions, and moderators of 3 intervention components of a smartphone-based intervention for physical activity. The secondary objective is the exploration of participants’ states of receptivity, that is, situations in which participants are more likely to react to intervention notifications through collection of smartphone sensor data. METHODS In 2017, we developed the Assistant to Lift your Level of activitY (Ally), a chatbot-based mobile health intervention for increasing physical activity that utilizes incentives, planning, and self-monitoring prompts to help participants meet personalized step goals. We used a microrandomized trial design to meet the study objectives. Insurees of a large Swiss insurance company were invited to use the Ally app over a 12-day baseline and a 6-week intervention period. Upon enrollment, participants were randomly allocated to either a financial incentive, a charity incentive, or a no incentive condition. Over the course of the intervention period, participants were repeatedly randomized on a daily basis to either receive prompts that support self-monitoring or not and on a weekly basis to receive 1 of 2 planning interventions or no planning. Participants completed a Web-based questionnaire at baseline and postintervention follow-up. RESULTS Data collection was completed in January 2018. In total, 274 insurees (mean age 41.73 years; 57.7% [158/274] female) enrolled in the study and installed the Ally app on their smartphones. Main reasons for declining participation were having an incompatible smartphone (37/191, 19.4%) and collection of sensor data (35/191, 18.3%). Step data are available for 227 (82.8%, 227/274) participants, and smartphone sensor data are available for 247 (90.1%, 247/274) participants. CONCLUSIONS This study describes the evidence-based development of a JITAI for increasing physical activity. If components prove to be efficacious, they will be included in a revised version of the app that offers scalable promotion of physical activity at low cost. CLINICALTRIAL ClinicalTrials.gov NCT03384550; https://clinicaltrials.gov/ct2/show/NCT03384550 (Archived by WebCite at http://www.webcitation.org/74IgCiK3d) INTERNATIONAL REGISTERED REPOR DERR1-10.2196/11540
Tobias Kowatsch
added a research item
Working alliance describes an important relationship quality between health professionals and patients and is robustly linked to treatment success. However, due to limited resources of health professionals, working alliance cannot always be promoted just-in-time in a ubiquitous fashion. To address this scalability problem, we investigate the direct effect of interpersonal closeness cues of text-based healthcare chatbots (THCBs) on attachment bond from the working alliance con-struct and the indirect effect on the desire to continue interacting with THCBs. The underlying research model and hypotheses are informed by counselling psychology and research on conver-sational agents. In order to investigate the hypothesized effects, we first develop a THCB codebook with 12 design dimensions on interpersonal closeness cues that are categorized into visual cues (i.e. avatar), verbal cues (i.e. greetings, address, jargon, T-V-distinction), quasi-nonverbal cues (i.e. emoticons) and relational cues (i.e. small talk, self-disclosure, empathy, humor, meta-relational talk and continuity). In a second step, four distinct THCB designs are developed along the continuum of interpersonal closeness (i.e. institutional-like, expert-like, peer-like and myself-like THCBs) and a corresponding study design for an interactive THCB-based online experiment is presented to test our hypotheses. We conclude this work-in-progress by outlining our future work.
Tobias Kowatsch
added 6 research items
Health literacy is a crucial ingredient of successful asthma self-management. Studies have shown that a paucity of asthma health literacy leads to lower levels of asthma control and thus more severe asthma symptoms, which, in turn, results in a suboptimal course of disease. In this research focus on two research questions: (1) To which degree does an interactive health literacy coaching with parental support improve the health literacy in children with asthma? and (2) How must the intervention be implemented in the healthcare system to increase its efficacy?
The poster gives an overview of health literacy video clips for children with Asthma which have been produced in 2017 (German version only, French and Italian versions will follow in 2018). The video clips are available here: https://www.lungenliga.ch/de/krankheiten-ihre-folgen/asthma-bei-kindern/asthma-lern-videoclips.html
Opportunities and Limitations of Digital Health Interventions are discussed based on research projects at the Center for Digital Health Interventions (Invited Talk).
Tobias Kowatsch
added 3 research items
No behavior has an impact on human health as great as physical activity (PA). We therefore developed Ally, a smartphone-based 6-week PA intervention. Ally seeks to exploit the ubiquity and sensing capabilities of mobile phones to adapt the provision of PA interventions to the context of the user. In this research we investigate the following research questions: (1) What are effective components of Ally, a mHealth physical activity intervention? and (2) Can mobile sensor data predict opportune moments for interventions?
Non communicable diseases (NCDs) the greatest global burden. Health personnel is strongly limited to address NCDs satisfactory and thus, scalable, cost- efficient and evidence-based digital health interventions are required. This research investigates how to increase therapy adherence with a digital coach in the everyday life of patients.
We are investigating to which degree of accuracy can a mobile application detect asthmatic nocturnal cough and sleep quality with the smartphone’s built-in microphone?
Chen-Hsuan Iris Shih
added a research item
Biofeedback-based Breathing Trainings (BBTs) shows significant effect on health (WAN10, DIL16). State-of-the-art BBTs require dedicated (high cost) hardware and health professionals which represent a significant barrier to their widespread adoption. While It has been shown that a smartphone microphone has the ability to record audio signals from exhalation in a quality of professional respiratory devices (LAR12), the ultimate goal of this project is to answer the research question: To which degree of accuracy can a mobile application detect respiratory acoustic patterns in quasi-real-time with a smartphone’s microphone, thus capable of triggering adequate biofeedback?
Elgar Fleisch
added a research item
The sheer amount of available apps allows users to customize smartphones to match their personality and interests. As one of the first large-scale studies, the impact of personality traits on mobile app adoption was examined through an empirical study involving 2043 Android users. A mobile app was developed to assess each smartphone user's personality traits based on a state-of-the-art Big Five questionnaire and to collect information about her installed apps. The contributions of this work are two-fold. First, it confirms that personality traits have significant impact on the adoption of different types of mobile apps. Second, a machine-learning model is developed to automatically determine a user's personality based on her installed apps. The predictive model is implemented in a prototype app and shows a 65% higher precision than a random guess. Additionally, the model can be deployed in a non-intrusive, low privacy-concern, and highly scalable manner as part of any mobile app.
Tobias Kowatsch
added 6 research items
Background: Substance use and misuse often first emerge during adolescence. Generic life skills training that is typically conducted within the school curriculum is effective at preventing the onset and escalation of substance use among adolescents. However, the dissemination of such programs is impeded by their large resource requirements in terms of personnel, money, and time. Life skills training provided via mobile phones might be a more economic and scalable approach, which additionally matches the lifestyle and communication habits of adolescents. Objective: The aim of this study was to test the acceptance and initial effectiveness of an individually tailored mobile phone–based life skills training program in vocational school students. Methods: Thefullyautomatedprogram,namedready4life,isbasedonsocialcognitivetheoryandaddressesself-management skills, social skills, and substance use resistance skills. Program participants received up to 3 weekly text messages (short message service, SMS) over 6 months. Active program engagement was stimulated by interactive features such as quiz questions, message- and picture-contests, and integration of a friendly competition with prizes in which program users collected credits with each interaction. Generalized estimating equation (GEE) analyses were used to investigate for changes between baseline and 6-month follow-up in the following outcomes: perceived stress, self-management skills, social skills, at-risk alcohol use, tobacco smoking, and cannabis use. Results: The program was tested in 118 school classes at 13 vocational schools in Switzerland. A total of 1067 students who owned a mobile phone and were not regular cigarette smokers were invited to participate in the life skills program. Of these, 877 (82.19%, 877/1067; mean age=17.4 years, standard deviation [SD]=2.7; 58.3% females) participated in the program and the associated study. A total of 43 students (4.9%, 43/877) withdrew their program participation during the intervention period. The mean number of interactive program activities that participants engaged in was 15.5 (SD 13.3) out of a total of 39 possible activities. Follow-up assessments were completed by 436 of the 877 (49.7%) participants. GEE analyses revealed decreased perceived stress (odds ratio, OR=0.93; 95% CI 0.87-0.99; P=.03) and increases in several life skills addressed between baseline and the follow-up assessment. The proportion of adolescents with at-risk alcohol use declined from 20.2% at baseline to 15.5% at follow-up (OR 0.70, 95% CI 0.53-0.93; P=.01), whereas no significant changes were obtained for tobacco (OR 0.94, 95% CI 0.65-1.36; P=.76) or cannabis use (OR 0.91, 95% CI 0.67-1.24; P=.54). Conclusions: These results reveal high-level acceptance and promising effectiveness of this interventional approach, which could be easily and economically implemented. A reasonable next step would be to test the efficacy of this program within a controlled trial.
Notifications can be relevant but they can also decrease productivity when delivered at the wrong point in time. Smartphones are increasingly capable of detecting relevant context information with the goal to decrease the number of these badly timed interruptions. Accordingly, research on context- aware notification management systems (CNMSs) on mobile devices has received increasing attention recently, prototypes have been built and empirically evaluated. However, there exists no systematic overview of mobile CNMSs evaluating their efficacy. The objectives of the current work are therefore to identify relevant empirical studies that have assessed the efficacy of mobile CNMSs and to discuss the findings with respect to future work. A systematic literature review and meta-analysis was conducted to address these objectives. Consistent with prior work, two efficacy metrics were applied: response rate and response delay. A keyword-based search strategy was used and resulted in 1’634 studies, out of which 8 were relevant for the topic. Findings indicate that mobile CNMSs increase the response rate, while there was only little evidence that they reduce response time, too. Implications for researchers and practitioners are discussed and future research is outlined that aims at further increasing the efficacy of mobile CNMSs.
Health professionals have limited resources and are not able to personally monitor and support patients in their everyday life. Against this background and due to the increasing number of self-service channels and digital health interventions, we investigate how text-based healthcare chatbots (THCB) can be designed to effectively support patients and health professionals in therapeutic settings beyond on-site consultations. We present an open source THCB system and how the THCP was designed for a childhood obesity intervention. Preliminary results with 15 patients indicate promising results with respect to intervention adherence (ca. 13.000 conversational turns over the course of 4 months or ca. 8 per day and patient), scalability of the THCB approach (ca. 99.5% of all conversational turns were THCB-driven) and over-average scores on perceived enjoyment and attachment bond between patient and THCB. Future work is discussed.
Elgar Fleisch
added 2 research items
Giving people ownership of the data they produce becomes more and more important in times of ever-growing capabilities to collect and analyze data of individuals. In light of this challenge, we show how blockchain technology can enable privacy by presenting an odometer fraud prevention system. It records mileage and GPS data of cars and secures that on the blockchain, which strongly hinders odometer fraud. Our users own and control their data while at the same time data integrity is ensured. This facilitates the certification of that data. We discuss the advantages of this approach compared to current systems and also highlight limitations of our architecture and the use of blockchain technology.
Elgar Fleisch
added a research item
Introduction We sought to identify whether an intensive 10-week mobile health (mHealth) Mnemonic Strategy Training (MST) could shift the resting-state brain network more toward cortical level integration, which has recently been proven to reflect the reorganization of the brain networks, compensating for cognitive decline. Methods A total of 158 patients with MCI were selected and participated in a 10-week training consisting of 90 minutes of memory training per day. They benefited from an initial and follow-up neuropsychological evaluation and resting state electroencephalography (EEG). Results At follow-up, Mnemonic Strategy Training revealed an extensive significant training effect that changed the network with an increase of synchronization between parietal-temporal, frontal areas, frontalθ -parietalα2 causal strengthening as part of top-down inhibitory control, enhancement of sensorimotor connections in the β band and a general increase of cortical level integration. More precisely, Mnemonic Strategy Training induced a gain as an increase of the global cost efficiency (GCE) of the whole cortical network and a neuropsychological performance improvement, which was correlated (r=0.32, p=0.0001). The present study unfolded intervention changes based on EEG-source activity via novel neuroinformatic tools for revealing intrinsic coupling modes in both amplitude-phase representations and in the mixed spectro-spatio-temporal domain. Discussion Further work should identify whether the GCE enhancement of the functional cortical brain networks is a compensation mechanism for brain network dysfunction or a more permanent neuroplasticity effect.
Peter Tinschert
added a research item
Background: Effective disease self-management lowers asthma’s burden of disease for both individual patients and health care systems. In principle, mobile health (mHealth) apps could enable effective asthma self-management interventions that improve a patient’s quality of life while simultaneously reducing the overall treatment costs for health care systems. However, prior reviews in this field have found that mHealth apps for asthma lack clinical evaluation and are often not based on medical guidelines. Yet, beyond the missing evidence for clinical efficacy, little is known about the potential apps might have for improving asthma self-management. Objective: The aim of this study was to assess the potential of publicly available and well-adopted mHealth apps for improving asthma self-management. Methods: The Apple App store and Google Play store were systematically searched for asthma apps. In total, 523 apps were identified, of which 38 apps matched the selection criteria to be included in the review. Four requirements of app potential were investigated: app functions, potential to change behavior (by means of a behavior change technique taxonomy), potential to promote app use (by means of a gamification components taxonomy), and app quality (by means of the Mobile Application Rating Scale [MARS]). Results: The most commonly implemented functions in the 38 reviewed asthma apps were tracking (30/38, 79%) and information (26/38, 68%) functions, followed by assessment (20/38, 53%) and notification (18/38, 47%) functions. On average, the reviewed apps applied 7.12 of 26 available behavior change techniques (standard deviation [SD]=4.46) and 4.89 of 31 available gamification components (SD=4.21). Average app quality was acceptable (mean=3.17/5, SD=0.58), whereas subjective app quality lied between poor and acceptable (mean=2.65/5, SD=0.87). Additionally, the sum scores of all review frameworks were significantly correlated (lowest correlation: r36=.33, P=.04 between number of functions and gamification components; highest correlation: r36=.80, P<.001 between number of behavior change techniques and gamification components), which suggests that an app’s potential tends to be consistent across review frameworks. Conclusions: Several apps were identified that performed consistently well across all applied review frameworks, thus indicating the potential mHealth apps offer for improving asthma self-management. However, many apps suffer from low quality. Therefore, app reviews should be considered as a decision support tool before deciding which app to integrate into a patient’s asthma self-management. Furthermore, several research-practice gaps were identified that app developers should consider addressing in future asthma apps.
Peter Tinschert
added a research item
The personal and financial burden of asthma highly depends on a patient's disease self-management skill. Scalable mHealth apps, designed to empower patients, have the potential to play a crucial role in asthma disease management. However, the actual clinical efficacy of mHealth asthma apps is poorly understood due to the lack of both methodologically sound research and accessible evidence-based apps. We therefore apply design science with the goal to design, implement and evaluate a mHealth app for people with asthma, the Mobile Asthma Companion (MAC). The current prototype of MAC delivers health literacy knowledge triggered by nocturnal cough rates. We conclude by proposing a randomized controlled trial to test the efficacy of our prototype.