Combining anchoring with financial incentives to increase physical activity: a randomized controlled trial among college students.

The purpose of this study was to: (1) compare the relative efficacy of different combinations of three behavioral intervention strategies (i.e., personalized reminders, financial incentives, and anchoring) for establishing physical activity habits using an mHealth app and (2) to examine the effects of these different combined interventions on intrinsic motivation for physical activity and daily walking habit strength. A four-arm randomized controlled trial was conducted in a sample of college students (N = 161) who had a self-reported personal wellness goal of increasing their physical activity. Receiving cue-contingent financial incentives (i.e., incentives conditional on performing physical activity within ± one hour of a prespecified physical activity cue) combined with anchoring resulted in the highest daily step counts and greatest odds of temporally consistent walking during both the four-week intervention and the full eight-week study period. Cue-contingent financial incentives were also more successful at increasing physical activity and maintaining these effects post-intervention than traditional non-cue-contingent incentives. There were no differences in intrinsic motivation or habit strength between study groups at any time point. Financial incentives, particularly cue-contingent incentives, can be effectively used to support the anchoring intervention strategy for establishing physical activity habits. Moreover, mHealth apps are a feasible method for delivering the combined intervention technique of financial incentives with anchoring.

Patient Engagement in a Multimodal Digital Phenotyping Study of Opioid Use Disorder.

BACKGROUND: Multiple digital data sources can capture moment-to-moment information to advance a robust understanding of opioid use disorder (OUD) behavior, ultimately creating a digital phenotype for each patient. This information can lead to individualized interventions to improve treatment for OUD. OBJECTIVE: The aim is to examine patient engagement with multiple digital phenotyping methods among patients receiving buprenorphine medication for OUD. METHODS: The study enrolled 65 patients receiving buprenorphine for OUD between June 2020 and January 2021 from 4 addiction medicine programs in an integrated health care delivery system in Northern California. Ecological momentary assessment (EMA), sensor data, and social media data were collected by smartphone, smartwatch, and social media platforms over a 12-week period. Primary engagement outcomes were meeting measures of minimum phone carry (≥8 hours per day) and watch wear (≥18 hours per day) criteria, EMA response rates, social media consent rate, and data sparsity. Descriptive analyses, bivariate, and trend tests were performed. RESULTS: The participants' average age was 37 years, 47% of them were female, and 71% of them were White. On average, participants met phone carrying criteria on 94% of study days, met watch wearing criteria on 74% of days, and wore the watch to sleep on 77% of days. The mean EMA response rate was 70%, declining from 83% to 56% from week 1 to week 12. Among participants with social media accounts, 88% of them consented to providing data; of them, 55% of Facebook, 54% of Instagram, and 57% of Twitter participants provided data. The amount of social media data available varied widely across participants. No differences by age, sex, race, or ethnicity were observed for any outcomes. CONCLUSIONS: To our knowledge, this is the first study to capture these 3 digital data sources in this clinical population. Our findings demonstrate that patients receiving buprenorphine treatment for OUD had generally high engagement with multiple digital phenotyping data sources, but this was more limited for the social media data. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.3389/fpsyt.2022.871916.

Constant Optical Power Operation of an Ultraviolet LED Controlled by a Smartphone.

Constant light power operation of an ultraviolet (UV) LED based on portable low-cost instrumentation and a monolithically integrated monitoring photodiode (MPD) has been reported for the first time. UV light irradiation has become one of the essential measures for disinfection and sterilization. Monitoring and maintaining a specified light power level is important to meet the criteria of sterilization. We built a module composed of a monolithically integrated UV LED and MPD, a transimpedance amplifier, an Arduino Uno card, a digital-to-analog converter and a Bluetooth transceiver. An Android App that we wrote remotely controlled the UV LED module via Bluetooth. The Arduino Uno card was programmed to receive demands from the smartphone, sent a driving voltage to the LED and returned the present MPD voltage to the smartphone. A feedback loop was used to adjust the LED voltage for maintaining a constant light output. We successfully demonstrated the functioning of remote control of the App, and the resultant UV LED measured power remained the same as the setting power. This setup can also be applied to visible or white LEDs for controlling/maintaining mixed light's chromaticity coordinates or color temperature. With such controlling and internet capability, custom profiling and maintenance of precision lighting remotely would be possible.

Pitch perception and frequency-following responses elicited by lexical-tone chimeras.

OBJECTIVE: Previous research has shown the usefulness of utilizing auditory chimeras in assessing a listener's perception of the envelope and fine structure for an acoustic stimulus. However, research comparing and contrasting behavioral and electrophysiological responses to this stimulus type is scarce. DESIGN: Two sets of chimeric stimuli were constructed by interchanging the envelopes and fine-structures of the rising/yi(2)/and falling/yi(4)/Mandarin pitch contours that were filtered through 1, 2, 4, 8, 16, 32, and 64 frequency banks. Behavioral pitch-perception tasks were administered through a two-alternative, forced-choice paradigm. Electrophysiological responses were measured through scalp-recorded frequency-following responses (FFRs) to the lexical-tone chimeras. STUDY SAMPLE: Twenty American and twenty Chinese adults were recruited. RESULTS: A two-way analysis of variance showed significance (p < 0.05) within and across the filter bank and language background factors for the behavioral measurements, while the frequency-following response demonstrated a significance only across the filter banks. CONCLUSIONS: Perceptual importance of envelope cues increases starting from 16 filter banks, while the FFR accuracy and magnitude decreases with increasing number of filter banks. These results can be useful in assessing experience-dependent neuroplasticity and in designing speech processing strategies for cochlear-implant users who speak tonal or non-tonal languages around the globe.

Semantically enabling clinical decision support recommendations.

BACKGROUND: Clinical decision support systems have been widely deployed to guide healthcare decisions on patient diagnosis, treatment choices, and patient management through evidence-based recommendations. These recommendations are typically derived from clinical practice guidelines created by clinical specialties or healthcare organizations. Although there have been many different technical approaches to encoding guideline recommendations into decision support systems, much of the previous work has not focused on enabling system generated recommendations through the formalization of changes in a guideline, the provenance of a recommendation, and applicability of the evidence. Prior work indicates that healthcare providers may not find that guideline-derived recommendations always meet their needs for reasons such as lack of relevance, transparency, time pressure, and applicability to their clinical practice. RESULTS: We introduce several semantic techniques that model diseases based on clinical practice guidelines, provenance of the guidelines, and the study cohorts they are based on to enhance the capabilities of clinical decision support systems. We have explored ways to enable clinical decision support systems with semantic technologies that can represent and link to details in related items from the scientific literature and quickly adapt to changing information from the guidelines, identifying gaps, and supporting personalized explanations. Previous semantics-driven clinical decision systems have limited support in all these aspects, and we present the ontologies and semantic web based software tools in three distinct areas that are unified using a standard set of ontologies and a custom-built knowledge graph framework: (i) guideline modeling to characterize diseases, (ii) guideline provenance to attach evidence to treatment decisions from authoritative sources, and (iii) study cohort modeling to identify relevant research publications for complicated patients. CONCLUSIONS: We have enhanced existing, evidence-based knowledge by developing ontologies and software that enables clinicians to conveniently access updates to and provenance of guidelines, as well as gather additional information from research studies applicable to their patients' unique circumstances. Our software solutions leverage many well-used existing biomedical ontologies and build upon decades of knowledge representation and reasoning work, leading to explainable results.

Identifying Game-Based Digital Biomarkers of Cognitive Risk for Adolescent Substance Misuse: Protocol for a Proof-of-Concept Study.

BACKGROUND: Adolescents at risk for substance misuse are rarely identified early due to existing barriers to screening that include the lack of time and privacy in clinic settings. Games can be used for screening and thus mitigate these barriers. Performance in a game is influenced by cognitive processes such as working memory and inhibitory control. Deficits in these cognitive processes can increase the risk of substance use. Further, substance misuse affects these cognitive processes and may influence game performance, captured by in-game metrics such as reaction time or time for task completion. Digital biomarkers are measures generated from digital tools that explain underlying health processes and can be used to predict, identify, and monitor health outcomes. As such, in-game performance metrics may represent digital biomarkers of cognitive processes that can offer an objective method for assessing underlying risk for substance misuse. OBJECTIVE: This is a protocol for a proof-of-concept study to investigate the utility of in-game performance metrics as digital biomarkers of cognitive processes implicated in the development of substance misuse. METHODS: This study has 2 aims. In aim 1, using previously collected data from 166 adolescents aged 11-14 years, we extracted in-game performance metrics from a video game and are using machine learning methods to determine whether these metrics predict substance misuse. The extraction of in-game performance metrics was guided by literature review of in-game performance metrics and gameplay guidebooks provided by the game developers. In aim 2, using data from a new sample of 30 adolescents playing the same video game, we will test if metrics identified in aim 1 correlate with cognitive processes. Our hypothesis is that in-game performance metrics that are predictive of substance misuse in aim 1 will correlate with poor cognitive function in our second sample. RESULTS: This study was funded by National Institute on Drug Abuse through the Center for Technology and Behavioral Health Pilot Core in May 2022. To date, we have extracted 285 in-game performance metrics. We obtained institutional review board approval on October 11, 2022. Data collection for aim 2 is ongoing and projected to end in February 2024. Currently, we have enrolled 12 participants. Data analysis for aim 2 will begin once data collection is completed. The results from both aims will be reported in a subsequent publication, expected to be published in late 2024. CONCLUSIONS: Screening adolescents for substance use is not consistently done due to barriers that include the lack of time. Using games that provide an objective measure to identify adolescents at risk for substance misuse can increase screening rates, early identification, and intervention. The results will inform the utility of in-game performance metrics as digital biomarkers for identifying adolescents at high risk for substance misuse. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/46990.

Association between Self-Stigma and Suicide Risk in Individuals with Schizophrenia: Moderating Effects of Self-Esteem and Perceived Support from Friends.

This cross-sectional study assessed the moderating effects of self-esteem and perceived support from friends on the association between self-stigma and suicide risk in individuals with schizophrenia. We included 300 participants (267 with schizophrenia and 33 with schizoaffective disorder). Suicide risk was assessed using items adopted from the suicide module of the Mini-International Neuropsychiatric Interview; self-stigma was assessed using the Self-Stigma Scale-Short; perceived support from friends was assessed using the Friend Adaptation, Partnership, Growth, Affection, and Resolve Index; and self-esteem was assessed using the Rosenberg Self-Esteem Scale. A moderation analysis was performed to examine the moderating effects of self-esteem and perceived support from friends on the association between self-stigma and suicide risk. The results indicated that self-stigma was positively associated with suicide risk after the effects of other factors were controlled for. Both perceived support from friends and self-esteem significantly reduced the magnitude of suicide risk in participants with self-stigma. Our findings highlight the value of interventions geared toward ameliorating self-stigma and enhancing self-esteem in order to reduce suicide risk in individuals with schizophrenia.

The Feasibility and Utility of Harnessing Digital Health to Understand Clinical Trajectories in Medication Treatment for Opioid Use Disorder: D-TECT Study Design and Methodological Considerations.

Introduction: Across the U.S., the prevalence of opioid use disorder (OUD) and the rates of opioid overdoses have risen precipitously in recent years. Several effective medications for OUD (MOUD) exist and have been shown to be life-saving. A large volume of research has identified a confluence of factors that predict attrition and continued substance use during substance use disorder treatment. However, much of this literature has examined a small set of potential moderators or mediators of outcomes in MOUD treatment and may lead to over-simplified accounts of treatment non-adherence. Digital health methodologies offer great promise for capturing intensive, longitudinal ecologically-valid data from individuals in MOUD treatment to extend our understanding of factors that impact treatment engagement and outcomes. Methods: This paper describes the protocol (including the study design and methodological considerations) from a novel study supported by the National Drug Abuse Treatment Clinical Trials Network at the National Institute on Drug Abuse (NIDA). This study (D-TECT) primarily seeks to evaluate the feasibility of collecting ecological momentary assessment (EMA), smartphone and smartwatch sensor data, and social media data among patients in outpatient MOUD treatment. It secondarily seeks to examine the utility of EMA, digital sensing, and social media data (separately and compared to one another) in predicting MOUD treatment retention, opioid use events, and medication adherence [as captured in electronic health records (EHR) and EMA data]. To our knowledge, this is the first project to include all three sources of digitally derived data (EMA, digital sensing, and social media) in understanding the clinical trajectories of patients in MOUD treatment. These multiple data streams will allow us to understand the relative and combined utility of collecting digital data from these diverse data sources. The inclusion of EHR data allows us to focus on the utility of digital health data in predicting objectively measured clinical outcomes. Discussion: Results may be useful in elucidating novel relations between digital data sources and OUD treatment outcomes. It may also inform approaches to enhancing outcomes measurement in clinical trials by allowing for the assessment of dynamic interactions between individuals' daily lives and their MOUD treatment response. Clinical Trial Registration: Identifier: NCT04535583.

Comparing the Psychometric Properties among Three Versions of the UCLA Loneliness Scale in Individuals with Schizophrenia or Schizoaffective Disorder.

The UCLA Loneliness Scale (Version 3; UCLA-LSV3) is widely used for assessing loneliness. Nevertheless, the validity of this scale for assessing loneliness in individuals with schizophrenia or schizoaffective disorder has not been determined. Additionally, studies validating the eight-item and three-item versions of UCLA-LSV3 have not included individuals with severe mental illness; therefore, whether the short versions are comparable to the full 20-item version of UCLA-LSV3 for this population is unclear. The present study examined the unidimensional structure, internal consistency, concurrent validity, and test-retest reliability of the Chinese versions of UCLA-LSV3 (i.e., 20-item, 8-item, and 3-item versions) to determine which version is most appropriate for assessing loneliness in individuals with schizophrenia or schizoaffective disorder in Taiwan. A total of 300 participants (267 with schizophrenia and 33 with schizoaffective disorder) completed the scales, comprising UCLA-LSV3, the Center for Epidemiological Studies Depression Scale (CES-D), the suicidality module of the Kiddie Schedule for Affective Disorders and Schizophrenia-Epidemiological Version (K-SADS-E), and the family and peer Adaptation, Partnership, Growth, Affection, and Resolve (APGAR) index. Construct validity was evaluated through confirmatory factor analysis. The three versions of UCLA-LSV3 were compared with the CES-D, the suicidality module of the K-SADS-E, and the family and peer APGAR index to establish concurrent validity. The results indicated that all three versions of UCLA-LSV3 exhibited acceptable to satisfactory psychometric properties in terms of unidimensional constructs, concurrent validity, and test-retest reliability. The full version of UCLA-LSV3 had the best performance, followed by the eight-item version and the three-item version. Moreover, the three versions had relatively strong associations with each other. Therefore, when deliberating which version of UCLA-LSV3 is the best choice for assessing loneliness in individuals with schizophrenia or schizoaffective disorder, healthcare providers and therapists should consider time availability and practicality.

Applying Contemporary Machine Learning Approaches to Nutrition Care Real-World Evidence: Findings From the National Quality Improvement Data Set.

Using real-world data from the Academy of Nutrition and Dietetics Health Informatics Infrastructure, we use state-of-the-art clustering techniques to identify 2 phenotypes characterizing the episodes of nutrition care observed in the National Quality Improvement (NQI) registry data set. The 2 phenotypes identified from recorded Nutrition Care Process data in the NQI exhibit a strong correspondence with the clinical expertise of registered dietitian nutritionists. For one of these phenotypes, it was possible to implement state-of-the-art classification techniques to predict the nutrition problem-resolution status of an episode of care. Prediction results show that the assessment of nutrition history, number of recorded visits in the episode, and use of nutrition counseling interventions were significantly and positively correlated with problem resolution. Meanwhile, evaluations of nutrition history that were not within the desired ranges were significantly and negatively correlated with problem resolution. Finally, we assess the usefulness of the current NQI data set and data model for supporting the application of contemporary machine learning methods to the data set. We also suggest ways of enhancing the NQI since registered dietitian nutritionists are encouraged to continue to contribute patient cases in this and other registry nutrition studies.

Systematic review of context-aware digital behavior change interventions to improve health.

Health risk behaviors are leading contributors to morbidity, premature mortality associated with chronic diseases, and escalating health costs. However, traditional interventions to change health behaviors often have modest effects, and limited applicability and scale. To better support health improvement goals across the care continuum, new approaches incorporating various smart technologies are being utilized to create more individualized digital behavior change interventions (DBCIs). The purpose of this study is to identify context-aware DBCIs that provide individualized interventions to improve health. A systematic review of published literature (2013-2020) was conducted from multiple databases and manual searches. All included DBCIs were context-aware, automated digital health technologies, whereby user input, activity, or location influenced the intervention. Included studies addressed explicit health behaviors and reported data of behavior change outcomes. Data extracted from studies included study design, type of intervention, including its functions and technologies used, behavior change techniques, and target health behavior and outcomes data. Thirty-three articles were included, comprising mobile health (mHealth) applications, Internet of Things wearables/sensors, and internet-based web applications. The most frequently adopted behavior change techniques were in the groupings of feedback and monitoring, shaping knowledge, associations, and goals and planning. Technologies used to apply these in a context-aware, automated fashion included analytic and artificial intelligence (e.g., machine learning and symbolic reasoning) methods requiring various degrees of access to data. Studies demonstrated improvements in physical activity, dietary behaviors, medication adherence, and sun protection practices. Context-aware DBCIs effectively supported behavior change to improve users' health behaviors.

Identifying Ingredient Substitutions Using a Knowledge Graph of Food.

People can affect change in their eating patterns by substituting ingredients in recipes. Such substitutions may be motivated by specific goals, like modifying the intake of a specific nutrient or avoiding a particular category of ingredients. Determining how to modify a recipe can be difficult because people need to 1) identify which ingredients can act as valid replacements for the original and 2) figure out whether the substitution is "good" for their particular context, which may consider factors such as allergies, nutritional contents of individual ingredients, and other dietary restrictions. We propose an approach to leverage both explicit semantic information about ingredients, encapsulated in a knowledge graph of food, and implicit semantics, captured through word embeddings, to develop a substitutability heuristic to rank plausible substitute options automatically. Our proposed system also helps determine which ingredient substitution options are "healthy" using nutritional information and food classification constraints. We evaluate our substitutability heuristic, diet-improvement ingredient substitutability heuristic (DIISH), using a dataset of ground-truth substitutions scraped from ingredient substitution guides and user reviews of recipes, demonstrating that our approach can help reduce the human effort required to make recipes more suitable for specific dietary needs.

Efficient goal attainment and engagement in a care manager system using unstructured notes.

OBJECTIVE: To improve efficient goal attainment of patients by analyzing the unstructured text in care manager (CM) notes (CMNs). Our task is to determine whether the goal assigned by the CM can be achieved in a timely manner. MATERIALS AND METHODS: Our data consists of CM structured and unstructured records from a private firm in Orlando, FL. The CM data is based on phone interactions between the CM and the patient. A portion of the data has been manually annotated to indicate engagement. We present 2 machine learning classifiers: an engagement model and a goal attainment model. RESULTS: We can successfully distinguish automatically between engagement and lack of engagement. Subsequently, incorporating engagement and features from textual information from the unstructured notes significantly improves goal attainment classification. DISCUSSION: Two key challenges in this task were the time-consuming annotation effort for engagement classification and the limited amount of data for the more difficult goal attainment class (specifically, for people who take a long time to achieve their goals). We successfully explore domain adaptation and transfer learning techniques to improve performance on the under-represented classes. We also explore the value of using features from unstructured notes to improve the model and interpretability. CONCLUSIONS: Unstructured CMNs can be used to improve accuracy of our classification models for predicting patient self-management goal attainment. This work can be used to help identify patients who may require special attention from CMs to improve engagement in self-management.

Learning Interpretable Behavioral Engagement for Care Management.

The health outcomes of high-need patients can be substantially influenced by the degree of patient engagement in their own care. The role of care managers (CMs) includes enrolling patients and keeping them sufficiently engaged in care programs, so that patients complete assigned goals leading to improvement in their health outcomes. Here, we present a data-driven behavioral engagement scoring (BES) pipeline that can compute the patients' engagement level with regards to their interest in: (1) enrolling into a relevant care program, and (2) completing program goals. This score is leveraged to predict a patient's propensity to respond to CMs' actions. Using real-world care management data, we show that the BES pipeline successfully predicts patient engagement and provides interpretable insights to CMs, using prototypical patient cases as a point of reference, without sacrificing prediction performance.

Evaluating the Reproducibility of Physiological Stress Detection Models.

Recent advances in wearable sensor technologies have led to a variety of approaches for detecting physiological stress. Even with over a decade of research in the domain, there still exist many significant challenges, including a near-total lack of reproducibility across studies. Researchers often use some physiological sensors (custom-made or off-the-shelf), conduct a study to collect data, and build machine-learning models to detect stress. There is little effort to test the applicability of the model with similar physiological data collected from different devices, or the efficacy of the model on data collected from different studies, populations, or demographics. This paper takes the first step towards testing reproducibility and validity of methods and machine-learning models for stress detection. To this end, we analyzed data from 90 participants, from four independent controlled studies, using two different types of sensors, with different study protocols and research goals. We started by evaluating the performance of models built using data from one study and tested on data from other studies. Next, we evaluated new methods to improve the performance of stress-detection models and found that our methods led to a consistent increase in performance across all studies, irrespective of the device type, sensor type, or the type of stressor. Finally, we developed and evaluated a clustering approach to determine the stressed/not-stressed classification when applying models on data from different studies, and found that our approach performed better than selecting a threshold based on training data. This paper's thorough exploration of reproducibility in a controlled environment provides a critical foundation for deeper study of such methods, and is a prerequisite for tackling reproducibility in free-living conditions.

The application of digital health to the assessment and treatment of substance use disorders: The past, current, and future role of the National Drug Abuse Treatment Clinical Trials Network.

The application of digital technologies to better assess, understand, and treat substance use disorders (SUDs) is a particularly promising and vibrant area of scientific research. The National Drug Abuse Treatment Clinical Trials Network (CTN), launched in 1999 by the U.S. National Institute on Drug Abuse, has supported a growing line of research that leverages digital technologies to glean new insights into SUDs and provide science-based therapeutic tools to a diverse array of persons with SUDs. This manuscript provides an overview of the breadth and impact of research conducted in the realm of digital health within the CTN. This work has included the CTN's efforts to systematically embed digital screeners for SUDs into general medical settings to impact care models across the nation. This work has also included a pivotal multi-site clinical trial conducted on the CTN platform, whose data led to the very first "prescription digital therapeutic" authorized by the U.S. Food and Drug Administration (FDA) for the treatment of SUDs. Further CTN research includes the study of telehealth to increase capacity for science-based SUD treatment in rural and under-resourced communities. In addition, the CTN has supported an assessment of the feasibility of detecting cocaine-taking behavior via smartwatch sensing. And, the CTN has supported the conduct of clinical trials entirely online (including the recruitment of national and hard-to-reach/under-served participant samples online, with remote intervention delivery and data collection). Further, the CTN is supporting innovative work focused on the use of digital health technologies and data analytics to identify digital biomarkers and understand the clinical trajectories of individuals receiving medications for opioid use disorder (OUD). This manuscript concludes by outlining the many potential future opportunities to leverage the unique national CTN research network to scale-up the science on digital health to examine optimal strategies to increase the reach of science-based SUD service delivery models both within and outside of healthcare.

An Adaptive, Data-Driven Personalized Advisor for Increasing Physical Activity.

In recent years, there has been growing interest in the use of fitness trackers and smartphone applications for promoting physical activity. Many of these applications use accelerometers to estimate the level of activity that users engage in and provide visual reports of a user's step counts. When provided, most recommendations are limited to popular general health advice. In our study, we develop an approach for providing data-driven and personalized recommendations for intraday activity planning. We generate an hour-by-hour activity plan that is based on the user's probability of adhering to the plan. The user's probability of adherence to the plan is personalized, based on his/her past activity patterns and current activity target. Using this approach, we can tailor notifications (e.g., reminders, encouragement) to each user. We can also dynamically update the user's activity plan at mid-day, if his/her actual activity deviates sufficiently from the original plan. In this paper, we describe an implementation of our approach and report our technical findings with respect to identifying typical activity patterns from historical data, predicting whether an activity target will be achieved, and adapting an activity plan based on a user's actual performance throughout the day.

A First Step Towards Behavioral Coaching for Managing Stress: A Case Study on Optimal Policy Estimation with Multi-stage Threshold Q-learning.

Psychological stress is a major contributor to the adoption of unhealthy behaviors, which in turn accounts for 41% of global cardiovascular disease burden. While the proliferation of mobile health apps has offered promise to stress management, these apps do not provide micro-level feedback with regard to how to adjust one's behaviors to achieve a desired health outcome. In this paper, we formulate the task of multi-stage stress management as a sequential decision-making problem and explore the application of reinforcement learning to provide micro-level feedback for stress reduction. Specifically, we incorporate a multi-stage threshold selection into Q-learning to derive an interpretable form of a recommendation policy for behavioral coaching. We apply this method on an observational dataset that contains Fitbit ActiGraph measurements and self-reported stress levels. The estimated policy is then used to understand how exercise patterns may affect users' psychological stress levels and to perform coaching more effectively.