Stephen S. Intille’s research while affiliated with Northeastern University and other places

Ecological momentary assessment (EMA) is an approach to collect self-reported data repeatedly on mobile devices in natural settings. EMAs allow for temporally dense, ecologically valid data collection, but frequent interruptions with lengthy surveys on mobile devices can burden users, impacting compliance and data quality. We propose a method that reduces the length of each EMA question set measuring interrelated constructs, with only modest information loss. By estimating the potential information gain of each EMA question using question-answer prediction models, this method can prioritize the presentation of the most informative question in a question-by-question sequence and skip uninformative questions. We evaluated the proposed method by simulating question omission using four real-world datasets from three different EMA studies. When compared against the random question omission approach that skips 50% of the questions, our method reduces imputation errors by 15%-52%. In surveys with five answer options for each question, our method can reduce the mean survey length by 34%-56% with a real-time prediction accuracy of 72%-95% for the skipped questions. The proposed method may either allow more constructs to be surveyed without adding user burden or reduce response burden for more sustainable longitudinal EMA data collection.

Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered conversational interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.

BACKGROUND Missing data are inevitable in mHealth research and driven by both within- and between-person variations in compliance levels. Not distinguishing these different sources can lead to biases in health behavior inferences. However, current missing data handling techniques do not address disentangling these distinct missingness mechanisms. Compared to missingness at random (MAR), missingness not at random (MNAR) is particularly concerning—often termed non-ignorable missingness. OBJECTIVE We demonstrate the utility of a joint modeling approach that simultaneously accommodates dynamics of health behavior changes as well as within- and between-person missingness mechanisms. We also evaluate how conflating these distinct contributors of (possibly non-ignorable) missingness affects the validity of health behavior inferences. We provide practical recommendations for building such joint models with empirical data. METHODS We applied a joint model on empirical data comprising one year of daily observations of affect (i.e., feeling energetic) reported through smartphone- based ecological momentary assessment (EMA) and smartwatch-tracked physical activity (PA). We implemented a joint modeling approach combining (1) a multilevel vector autoregressive (VAR) model for examining the reciprocal influences between daily affect and PA, and (2) a multilevel probit model for missingness mechanisms. As a sensitivity analysis, we compared the results from the proposed approach against other methods that examined health behavior changes without simultaneously modeling missingness mechanisms. Additionally, we validated the joint modeling approach through simulated data mirroring missing data patterns observed in empirical data: temporally clustered (e.g., consecutive days of) missingness and across-individual heterogeneity in compliance rates. RESULTS Sensitivity analysis indicated relative robustness of the autoregressive (AR) effects across missing data handling approaches, whereas cross-regressive (CR) effects could only be detected under the joint modeling, but not with methods that did not simultaneously model the missingness mechanism. Specifically, under the joint modeling, participants had higher levels of PA on days following a previous day with higher energy levels (95% CI=[0.012, 0.049]), and a higher level of PA on one day was associated with higher energy levels the next day (95% CI=[0.006, 0.054]). Furthermore, the missing data model revealed both MAR and MNAR missing mechanisms. For example, lower PA was linked with higher missingness in PA at the within-person level (95% CI=[-1.528, -1.441]). Employment status was associated with compliance in wearables data (95% CI=[0.148, 0.574]). Finally, simulation studies demonstrated that joint modeling improves the accuracy of the substantive model’s estimate and identifies non-ignorable missing mechanisms effectively. CONCLUSIONS We recommend utilizing joint modeling, particularly with multilevel decomposition to address non-ignorable missingness in mHealth studies collecting intensive longitudinal data. Simulation study showed joint modeling yielded results as accurate as those from fully observed data and enhanced understanding of within- and between-individual sources of missingness.

μEMA is a data collection method that prompts research participants with quick, answer-at-a-glance, single-multiple-choice self-report behavioral questions, thus enabling high-temporal-density self-report of up to four times per hour when implemented on a smartwatch. However, due to the small watch screen, μEMA is better used to select among 2 to 5 multiple-choice answers versus allowing the collection of open-ended responses. We introduce an alternative and novel form of micro-interaction self-report using speech input - audio-μEMA- where a short beep or vibration cues participants to verbally report their behavioral states, allowing for open-ended, temporally dense self-reports. We conducted a one-hour usability study followed by a within-subject, 6-day to 21-day free-living feasibility study in which participants self-reported their physical activities and postures once every 2 to 5 minutes. We qualitatively explored the usability of the system and identified factors impacting the response rates of this data collection method. Despite being interrupted 12 to 20 times per hour, participants in the free-living study were highly engaged with the system, with an average response rate of 67.7% for audio-μEMA for up to 14 days. We discuss the factors that impacted feasibility; some implementation, methodological, and participant challenges we observed; and important considerations relevant to deploying audio-μEMA in real-time activity recognition systems.

Background Intensive longitudinal data (ILD) collection methods have gained popularity in social and behavioral research as a tool to better understand behavior and experiences over time with reduced recall bias. Engaging participants in these studies over multiple months and ensuring high data quality are crucial but challenging due to the potential burden of repeated measurements. It is suspected that participants may engage in inattentive responding (IR) behavior to combat burden, but the processes underlying this behavior are unclear as previous studies have focused on the barriers to compliance rather than the barriers to providing high-quality data. Objective This study aims to broaden researchers’ knowledge about IR during ILD studies using qualitative analysis and uncover the underlying IR processes to aid future hypothesis generation. Methods We explored the process of IR by conducting semistructured qualitative exit interviews with 31 young adult participants (aged 18-29 years) who completed a 12-month ILD health behavior study with daily evening smartphone-based ecological momentary assessment (EMA) surveys and 4-day waves of hourly EMA surveys. The interviews assessed participants’ motivations, the impact of time-varying contexts, changes in motivation and response patterns over time, and perceptions of attention check questions (ACQs) to understand participants’ response patterns and potential factors leading to IR. Results Thematic analysis revealed 5 overarching themes on factors that influence participant engagement: (1) friends and family also had to tolerate the frequent surveys, (2) participants tried to respond to surveys quickly, (3) the repetitive nature of surveys led to neutral responses, (4) ACQs within the surveys helped to combat overly consistent response patterns, and (5) different motivations for answering the surveys may have led to different levels of data quality. Conclusions This study aimed to examine participants’ perceptions of the quality of data provided in an ILD study to contribute to the field’s understanding of engagement. These findings provide insights into the complex process of IR and participant engagement in ILD studies with EMA. The study identified 5 factors influencing IR that could guide future research to improve EMA survey design. The identified themes offer practical implications for researchers and study designers, including the importance of considering social context, the consideration of dynamic motivations, and the potential benefit of including ACQs as a technique to reduce IR and leveraging the intrinsic motivators of participants. By incorporating these insights, researchers might maximize the scientific value of their multimonth ILD studies through better data collection protocols. International Registered Report Identifier (IRRID) RR2-10.2196/36666

Despite the plethora of telehealth applications to assist home-based older adults and healthcare providers, basic messaging and phone calls are still the most common communication methods, which suffer from limited availability, information loss, and process inefficiencies. One promising solution to facilitate patient-provider communication is to leverage large language models (LLMs) with their powerful natural conversation and summarization capability. However, there is a limited understanding of LLMs' role during the communication. We first conducted two interview studies with both older adults (N=10) and healthcare providers (N=9) to understand their needs and opportunities for LLMs in patient-provider asynchronous communication. Based on the insights, we built an LLM-powered communication system, Talk2Care, and designed interactive components for both groups: (1) For older adults, we leveraged the convenience and accessibility of voice assistants (VAs) and built an LLM-powered conversational interface for effective information collection. (2) For health providers, we built an LLM-based dashboard to summarize and present important health information based on older adults' conversations with the VA. We further conducted two user studies with older adults and providers to evaluate the usability of the system. The results showed that Talk2Care could facilitate the communication process, enrich the health information collected from older adults, and considerably save providers' efforts and time. We envision our work as an initial exploration of LLMs' capability in the intersection of healthcare and interpersonal communication.

BACKGROUND The lack of regular physical activity (PA) in individuals with spinal cord injury (SCI) in the United States is an ongoing health crisis. Regular PA and exercise-based interventions have been linked with improved outcomes and healthier lifestyles among those with SCI. Providing people with an accurate estimate of their everyday PA level can promote PA. Furthermore, PA tracking can be combined with mobile health technology such as smartphones and smartwatches to provide a just-in-time adaptive intervention (JITAI) for individuals with SCI as they go about everyday life. A JITAI can prompt an individual to set a PA goal or provide feedback about their PA levels. OBJECTIVE The primary aim of this study is to investigate whether minutes of moderate-intensity PA among individuals with SCI can be increased by integrating a JITAI with a web-based PA intervention (WI) program. The WI program is a 14-week web-based PA program widely recommended for individuals with disabilities. A secondary aim is to investigate the benefit of a JITAI on proximal PA, defined as minutes of moderate-intensity PA within 120 minutes of a PA feedback prompt. METHODS Individuals with SCI (N=196) will be randomized to a WI arm or a WI+JITAI arm. Within the WI+JITAI arm, a microrandomized trial will be used to randomize participants several times a day to different tailored feedback and PA recommendations. Participants will take part in the 24-week study from their home environment in the community. The study has three phases: (1) baseline, (2) WI program with or without JITAI, and (3) PA sustainability. Participants will provide survey-based information at the initial meeting and at the end of weeks 2, 8, 16, and 24. Participants will be asked to wear a smartwatch every day for ≥12 hours for the duration of the study. RESULTS Recruitment and enrollment began in May 2023. Data analysis is expected to be completed within 6 months of finishing participant data collection. CONCLUSIONS The JITAI has the potential to achieve long-term PA performance by delivering tailored, just-in-time feedback based on the person’s actual PA behavior rather than a generic PA recommendation. New insights from this study may guide intervention designers to develop engaging PA interventions for individuals with disability. CLINICALTRIAL ClinicalTrials.gov NCT05317832; https://clinicaltrials.gov/study/NCT05317832 INTERNATIONAL REGISTERED REPORT DERR1-10.2196/57699

Background The lack of regular physical activity (PA) in individuals with spinal cord injury (SCI) in the United States is an ongoing health crisis. Regular PA and exercise-based interventions have been linked with improved outcomes and healthier lifestyles among those with SCI. Providing people with an accurate estimate of their everyday PA level can promote PA. Furthermore, PA tracking can be combined with mobile health technology such as smartphones and smartwatches to provide a just-in-time adaptive intervention (JITAI) for individuals with SCI as they go about everyday life. A JITAI can prompt an individual to set a PA goal or provide feedback about their PA levels. Objective The primary aim of this study is to investigate whether minutes of moderate-intensity PA among individuals with SCI can be increased by integrating a JITAI with a web-based PA intervention (WI) program. The WI program is a 14-week web-based PA program widely recommended for individuals with disabilities. A secondary aim is to investigate the benefit of a JITAI on proximal PA, defined as minutes of moderate-intensity PA within 120 minutes of a PA feedback prompt. Methods Individuals with SCI (N=196) will be randomized to a WI arm or a WI+JITAI arm. Within the WI+JITAI arm, a microrandomized trial will be used to randomize participants several times a day to different tailored feedback and PA recommendations. Participants will take part in the 24-week study from their home environment in the community. The study has three phases: (1) baseline, (2) WI program with or without JITAI, and (3) PA sustainability. Participants will provide survey-based information at the initial meeting and at the end of weeks 2, 8, 16, and 24. Participants will be asked to wear a smartwatch every day for ≥12 hours for the duration of the study. Results Recruitment and enrollment began in May 2023. Data analysis is expected to be completed within 6 months of finishing participant data collection. Conclusions The JITAI has the potential to achieve long-term PA performance by delivering tailored, just-in-time feedback based on the person’s actual PA behavior rather than a generic PA recommendation. New insights from this study may guide intervention designers to develop engaging PA interventions for individuals with disability. Trial Registration ClinicalTrials.gov NCT05317832; https://clinicaltrials.gov/study/NCT05317832 International Registered Report Identifier (IRRID) DERR1-10.2196/57699

BACKGROUND Engaging participants in intensive longitudinal data (ILD) collection studies over multiple months and ensuring high data quality is crucial but challenging due to the potential burden of repeated measurements. Participants may engage in inattentive responding behavior (IR) to combat burden, but the processes underlying this behavior are unclear. OBJECTIVE This study was designed to broaden researchers’ knowledge about IR during ILD studies using qualitative analysis and to uncover the underlying IR processes to aid with future hypothesis generation. METHODS We explored the process of IR by conducting qualitative exit interviews with 31 young adult participants (ages 18-29) who completed a 12-month ILD study with smartphone-based ecological momentary assessment (EMA). The interviews assessed participants' motivations, the impact of time-varying contexts, changes in motivation and response patterns over time, and perceptions of attention check questions. RESULTS Thematic analysis revealed five overarching themes on factors that influence participant engagement: 1) friends and family also had to tolerate the frequent surveys, 2) participants tried to respond to surveys quickly, 3) the repetitive nature of surveys led to neutral responses, 4) attention check questions helped to combat overly consistent response patterns, and 5) different motivations may have led to different levels of data quality. CONCLUSIONS These findings provide insights into the complex process of IR and participant engagement in ILD studies with EMA. The study identified factors influencing IR that could guide future research to improve EMA survey design. The identified themes offer practical implications for researchers and study designers, including the importance of considering social context, dynamic motivation, attention check questions, and intrinsic motivators of participants. By incorporating these insights, researchers might maximize the scientific value of their multi-month intensive longitudinal data studies through better data collection protocols. INTERNATIONAL REGISTERED REPORT RR2-10.2196/36666