Are conversational agents used at scale by companies offering digital health services for the management and prevention of diabetes?

  • Singapore-ETH Center
To read the full-text of this research, you can request a copy directly from the authors.


Successful interventions to prevent and manage type 2 diabetes rely on long-term, day-today decisions which take place outside of clinical settings. In this context, human resources are difficult to scale up, and leveraging Conversational agents (CAs) could be one way to scale up healthcare to tackle the emerging epidemic of type 2 diabetes. The objective of this paper is to assess the degree to which CAs are employed by top-funded digital health companies that target the prevention and management of type 2 diabetes. Companies were identified via two venture capital databases, i.e. Crunchbase Pro and Pitchbook. Two independent reviewers screened results and the final list of companies was validated and revised by three independent digital health experts. The companies' digital services (usually mobile applications) were accessed and reviewed for the utilisation of CAs. To better understand the purpose of identified CAs, relevant publications were identified via PubMed, Google Scholar, ACM Digital Library and on the companies' website. Nine out of 15 companies' digital services were accessible to the authors and only in one case a CA was employed. The uptake of CAs by top-funded digital health companies targeting type-2 diabetes is still low.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Full-text available
Background Conversational agents, also known as chatbots, are computer programs designed to simulate human text or verbal conversations. They are increasingly used in a range of fields, including health care. By enabling better accessibility, personalization, and efficiency, conversational agents have the potential to improve patient care. Objective This study aimed to review the current applications, gaps, and challenges in the literature on conversational agents in health care and provide recommendations for their future research, design, and application. Methods We performed a scoping review. A broad literature search was performed in MEDLINE (Medical Literature Analysis and Retrieval System Online; Ovid), EMBASE (Excerpta Medica database; Ovid), PubMed, Scopus, and Cochrane Central with the search terms “conversational agents,” “conversational AI,” “chatbots,” and associated synonyms. We also searched the gray literature using sources such as the OCLC (Online Computer Library Center) WorldCat database and ResearchGate in April 2019. Reference lists of relevant articles were checked for further articles. Screening and data extraction were performed in parallel by 2 reviewers. The included evidence was analyzed narratively by employing the principles of thematic analysis. Results The literature search yielded 47 study reports (45 articles and 2 ongoing clinical trials) that matched the inclusion criteria. The identified conversational agents were largely delivered via smartphone apps (n=23) and used free text only as the main input (n=19) and output (n=30) modality. Case studies describing chatbot development (n=18) were the most prevalent, and only 11 randomized controlled trials were identified. The 3 most commonly reported conversational agent applications in the literature were treatment and monitoring, health care service support, and patient education. Conclusions The literature on conversational agents in health care is largely descriptive and aimed at treatment and monitoring and health service support. It mostly reports on text-based, artificial intelligence–driven, and smartphone app–delivered conversational agents. There is an urgent need for a robust evaluation of diverse health care conversational agents’ formats, focusing on their acceptability, safety, and effectiveness.
Full-text available
Background: A rising number of conversational agents or chatbots are equipped with artificial intelligence (AI) architecture. They are increasingly prevalent in health care applications such as those providing education and support to patients with chronic diseases, one of the leading causes of death in the 21st century. AI-based chatbots enable more effective and frequent interactions with such patients. Objective: The goal of this systematic literature review is to review the characteristics, health care conditions, and AI architectures of AI-based conversational agents designed specifically for chronic diseases. Methods: We conducted a systematic literature review using PubMed MEDLINE, EMBASE, PyscInfo, CINAHL, ACM Digital Library, ScienceDirect, and Web of Science. We applied a predefined search strategy using the terms "conversational agent," "healthcare," "artificial intelligence," and their synonyms. We updated the search results using Google alerts, and screened reference lists for other relevant articles. We included primary research studies that involved the prevention, treatment, or rehabilitation of chronic diseases, involved a conversational agent, and included any kind of AI architecture. Two independent reviewers conducted screening and data extraction, and Cohen kappa was used to measure interrater agreement.A narrative approach was applied for data synthesis. Results: The literature search found 2052 articles, out of which 10 papers met the inclusion criteria. The small number of identified studies together with the prevalence of quasi-experimental studies (n=7) and prevailing prototype nature of the chatbots (n=7) revealed the immaturity of the field. The reported chatbots addressed a broad variety of chronic diseases (n=6), showcasing a tendency to develop specialized conversational agents for individual chronic conditions. However, there lacks comparison of these chatbots within and between chronic diseases. In addition, the reported evaluation measures were not standardized, and the addressed health goals showed a large range. Together, these study characteristics complicated comparability and open room for future research. While natural language processing represented the most used AI technique (n=7) and the majority of conversational agents allowed for multimodal interaction (n=6), the identified studies demonstrated broad heterogeneity, lack of depth of reported AI techniques and systems, and inconsistent usage of taxonomy of the underlying AI software, further aggravating comparability and generalizability of study results. Conclusions: The literature on AI-based conversational agents for chronic conditions is scarce and mostly consists of quasi-experimental studies with chatbots in prototype stage that use natural language processing and allow for multimodal user interaction. Future research could profit from evidence-based evaluation of the AI-based conversational agents and comparison thereof within and between different chronic health conditions. Besides increased comparability, the quality of chatbots developed for specific chronic conditions and their subsequent impact on the target patients could be enhanced by more structured development and standardized evaluation processes.
Full-text available
Background: Ongoing pain is one of the most common diseases and has major physical, psychological, social, and economic impacts. A mobile health intervention utilizing a fully automated text-based health care chatbot (TBHC) may offer an innovative way not only to deliver coping strategies and psychoeducation for pain management but also to build a working alliance between a participant and the TBHC. Objective: The objectives of this study are twofold: (1) to describe the design and implementation to promote the chatbot painSELfMAnagement (SELMA), a 2-month smartphone-based cognitive behavior therapy (CBT) TBHC intervention for pain self-management in patients with ongoing or cyclic pain, and (2) to present findings from a pilot randomized controlled trial, in which effectiveness, influence of intention to change behavior, pain duration, working alliance, acceptance, and adherence were evaluated. Methods: Participants were recruited online and in collaboration with pain experts, and were randomized to interact with SELMA for 8 weeks either every day or every other day concerning CBT-based pain management (n=59), or weekly concerning content not related to pain management (n=43). Pain-related impairment (primary outcome), general well-being, pain intensity, and the bond scale of working alliance were measured at baseline and postintervention. Intention to change behavior and pain duration were measured at baseline only, and acceptance postintervention was assessed via self-reporting instruments. Adherence was assessed via usage data. Results: From May 2018 to August 2018, 311 adults downloaded the SELMA app, 102 of whom consented to participate and met the inclusion criteria. The average age of the women (88/102, 86.4%) and men (14/102, 13.6%) participating was 43.7 (SD 12.7) years. Baseline group comparison did not differ with respect to any demographic or clinical variable. The intervention group reported no significant change in pain-related impairment (P=.68) compared to the control group postintervention. The intention to change behavior was positively related to pain-related impairment (P=.01) and pain intensity (P=.01). Working alliance with the TBHC SELMA was comparable to that obtained in guided internet therapies with human coaches. Participants enjoyed using the app, perceiving it as useful and easy to use. Participants of the intervention group replied with an average answer ratio of 0.71 (SD 0.20) to 200 (SD 58.45) conversations initiated by SELMA. Participants’ comments revealed an appreciation of the empathic and responsible interaction with the TBHC SELMA. A main criticism was that there was no option to enter free text for the patients’ own comments. Conclusions: SELMA is feasible, as revealed mainly by positive feedback and valuable suggestions for future revisions. For example, the participants’ intention to change behavior or a more homogenous sample (eg, with a specific type of chronic pain) should be considered in further tailoring of SELMA. Trial Registration: German Clinical Trials Register DRKS00017147;, Swiss National Clinical Trial Portal: SNCTP000002712;
Conference Paper
Full-text available
Virtual humans are computer-generated characters designed to simulate key properties of human face-to-face conversation-verbal and nonverbal. Their human-like physical appearance and nonverbal behavior set them apart from chatbot-type embodied conversational agents, and has recently received significant interest as a potential tool for health-related interventions. As healthcare providers deliberate whether to adopt this new technology, it is crucial to examine the empirical evidence about their effectiveness. We systematically evaluated evidence from controlled studies of interventions using virtual humans on their effectiveness in health-related outcomes. Nineteen studies were included from a total of 3354 unique records. Although study objectives varied greatly, most targeted psychological conditions, such as mood, anxiety, and autism spectrum disorders (ASD). Virtual humans demonstrated effectiveness in improving health-related outcomes, more strongly when targeting clinical conditions, such as ASD or pain management, than general wellness, such as weight loss. We discuss the emerging differences when designing for clinical interventions versus wellness.
Full-text available
Background: Conversational assistants, such as Siri, Alexa, and Google Assistant, are ubiquitous and are beginning to be used as portals for medical services. However, the potential safety issues of using conversational assistants for medical information by patients and consumers are not understood. Objective: To determine the prevalence and nature of the harm that could result from patients or consumers using conversational assistants for medical information. Methods: Participants were given medical problems to pose to Siri, Alexa, or Google Assistant, and asked to determine an action to take based on information from the system. Assignment of tasks and systems were randomized across participants, and participants queried the conversational assistants in their own words, making as many attempts as needed until they either reported an action to take or gave up. Participant-reported actions for each medical task were rated for patient harm using an Agency for Healthcare Research and Quality harm scale. Results: Fifty-four subjects completed the study with a mean age of 42 years (SD 18). Twenty-nine (54%) were female, 31 (57%) Caucasian, and 26 (50%) were college educated. Only 8 (15%) reported using a conversational assistant regularly, while 22 (41%) had never used one, and 24 (44%) had tried one “a few times.“ Forty-four (82%) used computers regularly. Subjects were only able to complete 168 (43%) of their 394 tasks. Of these, 49 (29%) reported actions that could have resulted in some degree of patient harm, including 27 (16%) that could have resulted in death. Conclusions: Reliance on conversational assistants for actionable medical information represents a safety risk for patients and consumers. Patients should be cautioned to not use these technologies for answers to medical questions they intend to act on without further consultation from a health care provider.
Full-text available
Objective: Our objective was to review the characteristics, current applications, and evaluation measures of conversational agents with unconstrained natural language input capabilities used for health-related purposes. Methods: We searched PubMed, Embase, CINAHL, PsycInfo, and ACM Digital using a predefined search strategy. Studies were included if they focused on consumers or healthcare professionals; involved a conversational agent using any unconstrained natural language input; and reported evaluation measures resulting from user interaction with the system. Studies were screened by independent reviewers and Cohen's kappa measured inter-coder agreement. Results: The database search retrieved 1513 citations; 17 articles (14 different conversational agents) met the inclusion criteria. Dialogue management strategies were mostly finite-state and frame-based (6 and 7 conversational agents, respectively); agent-based strategies were present in one type of system. Two studies were randomized controlled trials (RCTs), 1 was cross-sectional, and the remaining were quasi-experimental. Half of the conversational agents supported consumers with health tasks such as self-care. The only RCT evaluating the efficacy of a conversational agent found a significant effect in reducing depression symptoms (effect size d = 0.44, p = .04). Patient safety was rarely evaluated in the included studies. Conclusions: The use of conversational agents with unconstrained natural language input capabilities for health-related purposes is an emerging field of research, where the few published studies were mainly quasi-experimental, and rarely evaluated efficacy or safety. Future studies would benefit from more robust experimental designs and standardized reporting. Protocol registration: The protocol for this systematic review is registered at PROSPERO with the number CRD42017065917.
Full-text available
This research investigates the meaning of “human-computer relationship” and presents techniques for constructing, maintaining, and evaluating such relationships, based on research in social psychology, sociolinguistics, communication and other social sciences. Contexts in which relationships are particularly important are described, together with specific benefits (like trust) and task outcomes (like improved learning) known to be associated with relationship quality. We especially consider the problem of designing for long-term interaction, and define relational agents as computational artifacts designed to establish and maintain long-term social-emotional relationships with their users. We construct the first such agent, and evaluate it in a controlled experiment with 101 users who were asked to interact daily with an exercise adoption system for a month. Compared to an equivalent task-oriented agent without any deliberate social-emotional or relationship-building skills, the relational agent was respected more, liked more, and trusted more, even after four weeks of interaction. Additionally, users expressed a significantly greater desire to continue working with the relational agent after the termination of the study. We conclude by discussing future directions for this research together with ethical and other ramifications of this work for HCI designers.
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.
Importance: Effective and practical treatments are needed to increase physical activity among those at heightened risk from inactivity. Walking represents a popular physical activity that can produce a range of desirable health effects, particularly as people age. Objective: To test the hypothesis that counseling by a computer-based virtual advisor is no worse than (ie, noninferior to) counseling by trained human advisors for increasing 12-month walking levels among inactive adults. Design, setting, and participants: A cluster-randomized, noninferiority parallel trial enrolled 245 adults between July 21, 2014, and July 29, 2016, with follow-up through September 15, 2017. Data analysis was performed from March 15 to December 20, 2018. The evidence-derived noninferiority margin was 30 minutes of walking per week. Participants included inactive adults aged 50 years and older, primarily of Latin American descent and capable of walking without significant limitations, from 10 community centers in Santa Clara and San Mateo counties, California. Interventions: All participants received similar evidence-based, 12-month physical activity counseling at their local community center, with the 10 centers randomized to a computerized virtual advisor program (virtual) or a previously validated peer advisor program (human). Main outcomes and measures: The primary outcome was change in walking minutes per week over 12 months using validated interview assessment corroborated with accelerometry. Both per-protocol and intention-to-treat analysis was performed. Results: Among the 245 participants randomized, 193 were women (78.8%) and 241 participants (98.4%) were Latino. Mean (SD) age was 62.3 (8.4) years (range, 50-87 years), 107 individuals (43.7%) had high school or less educational level, mean BMI was 32.8 (6.8), and mean years residence in the US was 47.4 (17.0) years. A total of 231 participants (94.3%) completed the study. Mean 12-month change in walking was 153.9 min/wk (95% CI, 126.3 min/wk to infinity) for the virtual cohort (n = 123) and 131.9 min/wk (95% CI, 101.4 min/wk to infinity) for the human cohort (n = 122) (difference, 22.0, with lower limit of 1-sided 95% CI, -20.6 to infinity; P = .02); this finding supports noninferiority. Improvements emerged in both arms for relevant clinical risk factors, sedentary behavior, and well-being measures. Conclusions and relevance: The findings of this study indicate that a virtual advisor using evidence-based strategies produces significant 12-month walking increases for older, lower-income Latino adults that are no worse than the significant improvements achieved by human advisors. Changes produced by both programs are commensurate with those reported in previous investigations of these behavioral interventions and provide support for broadening the range of light-touch physical activity programs that can be offered to a diverse population. Trial registration: Identifier: NCT02111213.
Digital health technology, especially digital and health applications ("apps"), have been developing rapidly to help people manage their diabetes. Numerous health-related apps provided on smartphones and other wireless devices are available to support people with diabetes who need to adopt either lifestyle interventions or medication adjustments in response to glucose-monitoring data. However, regulations and guidelines have not caught up with the burgeoning field to standardize how mobile health apps are reviewed and monitored for patient safety and clinical validity. The available evidence on the safety and effectiveness of mobile health apps, especially for diabetes, remains limited. The European Association for the Study of Diabetes (EASD) and the American Diabetes Association (ADA) have therefore conducted a joint review of the current landscape of available diabetes digital health technology (only stand-alone diabetes apps, as opposed to those that are integral to a regulated medical device, such as insulin pumps, continuous glucose monitoring systems, and automated insulin delivery systems) and practices of regulatory authorities and organizations. We found that, across the U.S. and Europe, mobile apps intended to manage health and wellness are largely unregulated unless they meet the definition of medical devices for therapeutic and/or diagnostic purposes. International organizations, including the International Medical Device Regulators Forum and the World Health Organization, have made strides in classifying different types of digital health technology and integrating digital health technology into the field of medical devices. As the diabetes digital health field continues to develop and become more fully integrated into everyday life, we wish to ensure that it is based on the best evidence for safety and efficacy. As a result, we bring to light several issues that the diabetes community, including regulatory authorities, policy makers, professional organizations, researchers, people with diabetes, and health care professionals, needs to address to ensure that diabetes health technology can meet its full potential. These issues range from inadequate evidence on app accuracy and clinical validity to lack of training provision, poor interoperability and standardization, and insufficient data security. We conclude with a series of recommended actions to resolve some of these shortcomings.
Artificial intelligence (AI) has transformed the world and the relationships among humans as the learning capabilities of machines have allowed for a new means of communication between humans and machines. In the field of health, there is much interest in new technologies that help to improve and automate services in hospitals. This article aims to explore the literature related to conversational agents applied to health care, searching for definitions, patterns, methods, architectures, and data types. Furthermore, this work identifies an agent application taxonomy, current challenges, and research gaps. In this work, we use a systematic literature review approach. We guide and refine this study and the research questions by applying Population, Intervention, Comparison, Outcome, and Context (PICOC) criteria. The present study investigated approximately 4145 articles involving conversational agents in health published over the last ten years. In this context, we finally selected 40 articles based on their approaches and objectives as related to our main subject. As a result, we developed a taxonomy, identified the main challenges in the field, and defined the main types of dialog and contexts related to conversational agents in health. These results contributed to discussions regarding conversational health agents, and highlighted some research gaps for future study.
Background: Diabetes and related complications are estimated to cost US $727 billion worldwide annually. Type 1 diabetes, type 2 diabetes, and gestational diabetes are three subtypes of diabetes that share the same behavioral risk factors. Efforts in lifestyle modification, such as daily physical activity and healthy diets, can reduce the risk of prediabetes, improve the health levels of people with diabetes, and prevent complications. Lifestyle modification is commonly performed in a face-to-face interaction, which can prove costly. Mobile phone apps provide a more accessible platform for lifestyle modification in diabetes. Objective: This review aimed to summarize and synthesize the clinical evidence of the efficacy of mobile phone apps for lifestyle modification in different subtypes of diabetes. Methods: In June 2018, we conducted a literature search in 5 databases (Cochrane Central Register of Controlled Trials, MEDLINE, Embase, CINAHL, and PsycINFO). We evaluated the studies that passed screening using The Cochrane Collaboration's risk of bias tool. We conducted a meta-analysis for each subtype on the mean difference (between intervention and control groups) at the posttreatment glycated hemoglobin (HbA1c) level. Where possible, we analyzed subgroups for short-term (3-6 months) and long-term (9-12 months) studies. Heterogeneity was assessed using the I2 statistic. Results: We identified total of 2669 articles through database searching. After the screening, we included 26 articles (23 studies) in the systematic review, of which 18 studies (5 type 1 diabetes, 11 type 2 diabetes, and 2 prediabetes studies) were eligible for meta-analysis. For type 1 diabetes, the overall effect on HbA1c was statistically insignificant (P=.46) with acceptable heterogeneity (I2=39%) in the short-term subgroup (4 studies) and significant heterogeneity between the short-term and long-term subgroups (I2=64%). Regarding type 2 diabetes, the overall effect on HbA1c was statistically significant (P<.01) in both subgroups, and when the 2 subgroups were combined, there was virtually no heterogeneity within and between the subgroups (I2 range 0%-2%). The effect remained statistically significant (P<.01) after adjusting for publication bias using the trim and fill method. For the prediabetes condition, the overall effect on HbA1c was statistically insignificant (P=.67) with a large heterogeneity (I2=65%) between the 2 studies. Conclusions: There is strong evidence for the efficacy of mobile phone apps for lifestyle modification in type 2 diabetes. The evidence is inconclusive for the other diabetes subtypes.
Digital medicine offers the possibility of continuous monitoring, behavior modification and personalized interventions at low cost, potentially easing the burden of chronic disease in cost-constrained healthcare systems.
Depression affects approximately 15% of the US population, and is recognized as an important risk factor for poor outcomes among patients with various illnesses. Automated health education and behavior change programs have the potential to help address many of the shortcomings in health care. However, the role of these systems in the care of patients with depression has been insufficiently examined. In the current study, we sought to evaluate how hospitalized medical patients would respond to a computer animated conversational agent that has been developed to provide information in an empathic fashion about a patient's hospital discharge plan. In particular, we sought to examine how patients who have a high level of depressive symptoms respond to this system. Therapeutic alliance-the trust and belief that a patient and provider have in working together to achieve a desired therapeutic outcome- was used as the primary outcome measure, since it has been shown to be important in predicting outcomes across a wide range of health problems, including depression. In an evaluation of 139 hospital patients who interacted with the agent at the time of discharge, all patients, regardless of depressive symptoms, rated the agent very high on measures of satisfaction and ease of use, and most preferred receiving their discharge information from the agent compared to their doctors or nurses in the hospital. In addition, we found that patients with symptoms indicative of major depression rated the agent significantly higher on therapeutic alliance compared to patients who did not have major depressive symptoms. We conclude that empathic agents represent a promising technology for patient assessment, education and counseling for those most in need of comfort and caring in the inpatient setting.
Current user interfaces for automated patient and consumer health care systems can be improved by leveraging the results of several decades of research into effective patient-provider communication skills. A research project is presented in which several such "relational" skills - including empathy, social dialogue, nonverbal immediacy behaviors, and other behaviors to build and maintain good working relationships over multiple interactions - are explicitly designed into a computer interface within the context of a longitudinal health behavior change intervention for physical activity adoption. Results of a comparison among 33 subjects interacting near-daily with the relational system and 27 interacting near-daily with an identical system with the relational behaviors ablated, each for 30 days indicate, that the use of relational behaviors by the system significantly increases working alliance and desire to continue working with the system. Comparison of the above groups to another group of 31 subjects interacting with a control system near-daily for 30 days also indicated a significant increase in proactive viewing of health information.
  • Alexander Fleming
  • G Petrie
  • J R Bergenstal
  • R M Holl
  • R W Peters
  • A L Heinemann
Alexander Fleming, G., Petrie, J. R., Bergenstal, R. M., Holl, R. W., Peters, A. L., & Heinemann, L. (2020). Diabetes digital app technology: Benefits, challenges, and recommendations. A consensus report by the European Association for the Study of Diabetes (EASD) and the American Diabetes Association (ADA) Diabetes Technology Working Group. Diabetes Care, 43(1), 250-260.
Introduction -WHO guideline Recommendations on Digital Interventions for Health System Strengthening -NCBI Bookshelf
  • Idc
IDC. (2020). Introduction -WHO guideline Recommendations on Digital Interventions for Health System Strengthening -NCBI Bookshelf. International Diabetes Federation. (2019). IDF Diabetes Atlas 9th edition.
Chatbots for Diabetes Self-Management: Diabetes coaching at scale
  • J D O'brien
O'brien, J. D. (2017). Chatbots for Diabetes Self-Management: Diabetes coaching at scale.
Virtual Coaching to Enhance Diabetes Care
PitchBook. (n.d.). PitchBook [home page on the Internet]. Retrieved November 29, 2020, from Ramchandani, N. (2019). Virtual Coaching to Enhance Diabetes Care. Diabetes Technology and Therapeutics, 21(S2), S2-48-S2-51.
Benchmarking Venture Capital Databases
  • A Retterath
  • R Braun
Retterath, A., & Braun, R. (2020). Benchmarking Venture Capital Databases.
National Ambulatory Medical Care Survey: 2014 State and National Summary Tables
  • P Rui
  • E Hing
  • T Okeyode
Rui, P., Hing, E., & Okeyode, T. (2014). National Ambulatory Medical Care Survey: 2014 State and National Summary Tables.
One-Year Clinical Outcomes of an Artificial Intelligence-Based Digital Diabetes Prevention Program
  • N Stein
  • K Delury
  • J Paruthi
Stein, N., Delury, K., & Paruthi, J. (2020). One-Year Clinical Outcomes of an Artificial Intelligence-Based Digital Diabetes Prevention Program.
Clinical outcomes from older adults in a digital diabetes pre-vention program
  • N Stein
  • R Ku
  • T Mao
Stein, N., Ku, R., & Mao, T. (2019). Clinical outcomes from older adults in a digital diabetes pre-vention program.
Classification of Digital Health Interventions v 1.0: a shared language to describe the uses of digital technology for health
World Health Organization. (2018). Classification of Digital Health Interventions v 1.0: a shared language to describe the uses of digital technology for health. /10665/260480/WHO-RHR-18.06-eng.pdf