Search

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.

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.

BACKGROUND Feelings of loneliness are associated with poor physical and mental health. Detection of loneliness through passive sensing on personal devices can lead to the development of interventions aimed at decreasing rates of loneliness. OBJECTIVE The aim of this study was to explore the potential of using passive sensing to infer levels of loneliness and to identify the corresponding behavioral patterns. METHODS Data were collected from smartphones and Fitbits (Flex 2) of 160 college students over a semester. The participants completed the University of California, Los Angeles (UCLA) loneliness questionnaire at the beginning and end of the semester. For a classification purpose, the scores were categorized into high (questionnaire score>40) and low (≤40) levels of loneliness. Daily features were extracted from both devices to capture activity and mobility, communication and phone usage, and sleep behaviors. The features were then averaged to generate semester-level features. We used 3 analytic methods: (1) statistical analysis to provide an overview of loneliness in college students, (2) data mining using the Apriori algorithm to extract behavior patterns associated with loneliness, and (3) machine learning classification to infer the level of loneliness and the change in levels of loneliness using an ensemble of gradient boosting and logistic regression algorithms with feature selection in a leave-one-student-out cross-validation manner. RESULTS The average loneliness score from the presurveys and postsurveys was above 43 (presurvey SD 9.4 and postsurvey SD 10.4), and the majority of participants fell into the high loneliness category (scores above 40) with 63.8% (102/160) in the presurvey and 58.8% (94/160) in the postsurvey. Scores greater than 1 standard deviation above the mean were observed in 12.5% (20/160) of the participants in both pre- and postsurvey scores. The majority of scores, however, fell between 1 standard deviation below and above the mean (pre=66.9% [107/160] and post=73.1% [117/160]). 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 the loneliness level. The mining of associations between classifier-selected behavioral features and loneliness indicated that compared with students with low loneliness, students with high levels of loneliness were spending less time outside of campus during evening hours on weekends and spending less time in places for social events in the evening on weekdays (support=17% and confidence=92%). The analysis also indicated that more activity and less sedentary behavior, especially in the evening, was associated with a decrease in levels of loneliness from the beginning of the semester to the end of it (support=31% and confidence=92%). CONCLUSIONS Passive sensing has the potential for detecting loneliness in college students and identifying the associated behavioral patterns. These findings highlight intervention opportunities through mobile technology to reduce the impact of loneliness on individuals’ health and well-being.

BACKGROUND Physical and psychological symptoms are common during chemotherapy in cancer patients, and real-time monitoring of these symptoms can improve patient outcomes. Sensors embedded in mobile phones and wearable activity trackers could be potentially useful in monitoring symptoms passively, with minimal patient burden. OBJECTIVE The aim of this study was to explore whether passively sensed mobile phone and Fitbit data could be used to estimate daily symptom burden during chemotherapy. METHODS A total of 14 patients undergoing chemotherapy for gastrointestinal cancer participated in the 4-week study. Participants carried an Android phone and wore a Fitbit device for the duration of the study and also completed daily severity ratings of 12 common symptoms. Symptom severity ratings were summed to create a total symptom burden score for each day, and ratings were centered on individual patient means and categorized into low, average, and high symptom burden days. Day-level features were extracted from raw mobile phone sensor and Fitbit data and included features reflecting mobility and activity, sleep, phone usage (eg, duration of interaction with phone and apps), and communication (eg, number of incoming and outgoing calls and messages). We used a rotation random forests classifier with cross-validation and resampling with replacement to evaluate population and individual model performance and correlation-based feature subset selection to select nonredundant features with the best predictive ability. RESULTS Across 295 days of data with both symptom and sensor data, a number of mobile phone and Fitbit features were correlated with patient-reported symptom burden scores. We achieved an accuracy of 88.1% for our population model. The subset of features with the best accuracy included sedentary behavior as the most frequent activity, fewer minutes in light physical activity, less variable and average acceleration of the phone, and longer screen-on time and interactions with apps on the phone. Mobile phone features had better predictive ability than Fitbit features. Accuracy of individual models ranged from 78.1% to 100% (mean 88.4%), and subsets of relevant features varied across participants. CONCLUSIONS Passive sensor data, including mobile phone accelerometer and usage and Fitbit-assessed activity and sleep, were related to daily symptom burden during chemotherapy. These findings highlight opportunities for long-term monitoring of cancer patients during chemotherapy with minimal patient burden as well as real-time adaptive interventions aimed at early management of worsening or severe symptoms.

Background: Physical and psychological symptoms are common during chemotherapy in cancer patients, and real-time monitoring of these symptoms can improve patient outcomes. Sensors embedded in mobile phones and wearable activity trackers could be potentially useful in monitoring symptoms passively, with minimal patient burden. Objective: The aim of this study was to explore whether passively sensed mobile phone and Fitbit data could be used to estimate daily symptom burden during chemotherapy. Methods: A total of 14 patients undergoing chemotherapy for gastrointestinal cancer participated in the 4-week study. Participants carried an Android phone and wore a Fitbit device for the duration of the study and also completed daily severity ratings of 12 common symptoms. Symptom severity ratings were summed to create a total symptom burden score for each day, and ratings were centered on individual patient means and categorized into low, average, and high symptom burden days. Day-level features were extracted from raw mobile phone sensor and Fitbit data and included features reflecting mobility and activity, sleep, phone usage (eg, duration of interaction with phone and apps), and communication (eg, number of incoming and outgoing calls and messages). We used a rotation random forests classifier with cross-validation and resampling with replacement to evaluate population and individual model performance and correlation-based feature subset selection to select nonredundant features with the best predictive ability. Results: Across 295 days of data with both symptom and sensor data, a number of mobile phone and Fitbit features were correlated with patient-reported symptom burden scores. We achieved an accuracy of 88.1% for our population model. The subset of features with the best accuracy included sedentary behavior as the most frequent activity, fewer minutes in light physical activity, less variable and average acceleration of the phone, and longer screen-on time and interactions with apps on the phone. Mobile phone features had better predictive ability than Fitbit features. Accuracy of individual models ranged from 78.1% to 100% (mean 88.4%), and subsets of relevant features varied across participants. Conclusions: Passive sensor data, including mobile phone accelerometer and usage and Fitbit-assessed activity and sleep, were related to daily symptom burden during chemotherapy. These findings highlight opportunities for long-term monitoring of cancer patients during chemotherapy with minimal patient burden as well as real-time adaptive interventions aimed at early management of worsening or severe symptoms. [J Med Internet Res 2017;19(12):e420]