Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Loneliness significantly affects the quality of life and physical and mental health. In addition, recent studies have shown high levels of loneliness across various populations ranging from older adults to college students. Detection of loneliness through passive sensing on personal devices can lead to a better understanding of measurable behaviors that low and high loneliness individuals exhibit and can thus lead to explore these behaviors in interventions aimed at decreasing rates of loneliness among college students. Objective: We aimed to explore the potential of using smartphone and wearable sensors to infer the severity of loneliness and to identify its corresponding behavioral patterns. Methods: Data was collected from smartphones and Fitbits of 160 college students over a semester. Participants completed the UCLA loneliness questionnaire at the beginning and at the end of the semester. The scores were categorized to high (questionnaire score>40) and low (<=40) loneliness. Daily features were extracted from mobile phone and Fitbit sensors to capture activity and mobility, communication and phone usage, and sleep behaviors. The features were then aggregated to generate semester-level features. We used three analytic methods: 1) statistical analysis to provide an overview of loneliness in college students, 2) data mining using the Apriori algorithm to extract combined behavior patterns associated with loneliness, and 3) machine learning classification using an ensemble of Gradient Boosting and Logistic Regression algorithms with feature selection in a leave-one-student-out cross-validation manner to infer the level of loneliness. Results: The average loneliness score from both the pre-surveys and post-surveys was high, above 43, and the majority of participants fell into the high loneliness category, with 63.8% in pre-survey and 58.5% in post-survey. Severe loneliness (scores greater than one standard deviation above the mean) increased from 38.2% at the beginning of the semester to 39.4% at the end of the semester. Our machine learning pipeline achieved an accuracy of 80.2% in detecting the binary level of loneliness and an 88.4% accuracy in detecting change in loneliness level. The mining of associations between classifier-selected behavioral features and loneliness indicated that (1) spending less time outside of campus during evening hours on weekends and (2) spending less time in Greek houses for social events in the evening and night on weekdays were common behavior patterns in students with high loneliness. The analysis also indicated more activity and less sedentary behavior especially in the evening and night was associated with a decrease in loneliness. Conclusions: Passive sensing has the potential for detecting loneliness in college students and identifying the associated daily behavioral patterns, including the intensity of activity especially during night hours and the amount of time spent outside of campus. These findings highlight opportunities for interventions through mobile technology to reduce the impact of loneliness and social isolation on individuals’ health and wellbeing.

Background: Depression levels in adolescents have trended upward over the past several years. According to a 2020 survey by the National Survey on Drug Use and Health, 4.1 million US adolescents have experienced at least one major depressive episode. This number constitutes approximately 16% of adolescents aged 12 to 17 years. However, only 32.3% of adolescents received some form of specialized or nonspecialized treatment. Identifying worsening symptoms earlier using mobile and wearable sensors may lead to earlier intervention. Most studies on predicting depression using sensor-based data are geared toward the adult population. Very few studies look into predicting depression in adolescents. Objective: The aim of our work was to study passively sensed data from adolescents with depression and investigate the predictive capabilities of 2 machine learning approaches to predict depression scores and change in depression levels in adolescents. This work also provided an in-depth analysis of sensor features that serve as key indicators of change in depressive symptoms and the effect of variation of data samples on model accuracy levels. Methods: This study included 55 adolescents with symptoms of depression aged 12 to 17 years. Each participant was passively monitored through smartphone sensors and Fitbit wearable devices for 24 weeks. Passive sensors collected call, conversation, location, and heart rate information daily. Following data preprocessing, 67% (37/55) of the participants in the aggregated data set were analyzed. Weekly Patient Health Questionnaire-9 surveys answered by participants served as the ground truth. We applied regression-based approaches to predict the Patient Health Questionnaire-9 depression score and change in depression severity. These approaches were consolidated using universal and personalized modeling strategies. The universal strategies consisted of Leave One Participant Out and Leave Week X Out. The personalized strategy models were based on Accumulated Weeks and Leave One Week One User Instance Out. Linear and nonlinear machine learning algorithms were trained to model the data. Results: We observed that personalized approaches performed better on adolescent depression prediction compared with universal approaches. The best models were able to predict depression score and weekly change in depression level with root mean squared errors of 2.83 and 3.21, respectively, following the Accumulated Weeks personalized modeling strategy. Our feature importance investigation showed that the contribution of screen-, call-, and location-based features influenced optimal models and were predictive of adolescent depression. Conclusions: This study provides insight into the feasibility of using passively sensed data for predicting adolescent depression. We demonstrated prediction capabilities in terms of depression score and change in depression level. The prediction results revealed that personalized models performed better on adolescents than universal approaches. Feature importance provided a better understanding of depression and sensor data. Our findings can help in the development of advanced adolescent depression predictions.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet

Deep reinforcement learning (DRL) has proven capable of superhuman performance on many complex tasks. To achieve this success, DRL algorithms train a decision-making agent to select the actions that maximize some long-term performance measure. In many consequential real-world domains, however, optimal performance is not enough to justify an algorithm’s use—for example, sometimes a system’s robustness, stability, or safety must be rigorously ensured. Thus, methods for verifying DRL systems have emerged. These algorithms can guarantee a system’s properties over an infinite set of inputs, but the task is not trivial. DRL relies on deep neural networks (DNNs). DNNs are often referred to as “black boxes” because examining their respective structures does not elucidate their decision-making processes. Moreover, the sequential nature of the problems DRL is used to solve promotes significant scalability challenges. Finally, because DRL environments are often stochastic, verification methods must account for probabilistic behavior. To address these complications, a new subfield has emerged. In this survey, we establish the foundations of DRL and DRL verification, define a taxonomy for DRL verification methods, describe approaches for dealing with stochasticity, characterize considerations related to writing specifications, enumerate common testing tasks/environments, and detail opportunities for future research.

Background: Cancer treatments can cause a variety of symptoms that impair quality of life and functioning but are frequently missed by clinicians. Smartphone and wearable sensors may capture behavioral and physiological changes indicative of symptom burden, enabling passive and remote real-time monitoring of fluctuating symptoms Objective: The aim of this study was to examine whether smartphone and Fitbit data could be used to estimate daily symptom burden before and after pancreatic surgery. Methods: A total of 44 patients scheduled for pancreatic surgery participated in this prospective longitudinal study and provided sufficient sensor and self-reported symptom data for analyses. Participants collected smartphone sensor and Fitbit data and completed daily symptom ratings starting at least two weeks before surgery, throughout their inpatient recovery, and for up to 60 days after postoperative discharge. Day-level behavioral features reflecting mobility and activity patterns, sleep, screen time, heart rate, and communication were extracted from raw smartphone and Fitbit data and used to classify the next day as high or low symptom burden, adjusted for each individual’s typical level of reported symptoms. In addition to the overall symptom burden, we examined pain, fatigue, and diarrhea specifically. Results: Models using light gradient boosting machine (LightGBM) were able to correctly predict whether the next day would be a high symptom day with 73.5% accuracy, surpassing baseline models. The most important sensor features for discriminating high symptom days were related to physical activity bouts, sleep, heart rate, and location. LightGBM models predicting next-day diarrhea (79.0% accuracy), fatigue (75.8% accuracy), and pain (79.6% accuracy) performed similarly. Conclusions: Results suggest that digital biomarkers may be useful in predicting patient-reported symptom burden before and after cancer surgery. Although model performance in this small sample may not be adequate for clinical implementation, findings support the feasibility of collecting mobile sensor data from older patients who are acutely ill as well as the potential clinical value of mobile sensing for passive monitoring of patients with cancer and suggest that data from devices that many patients already own and use may be useful in detecting worsening perioperative symptoms and triggering just-in-time symptom management interventions.