Continuous Assessment of Function and Disability via Mobile Sensing: Real-World Data-Driven Feasibility Study.

BACKGROUND: Functional limitations are associated with poor clinical outcomes, higher mortality, and disability rates, especially in older adults. Continuous assessment of patients' functionality is important for clinical practice; however, traditional questionnaire-based assessment methods are very time-consuming and infrequently used. Mobile sensing offers a great range of sources that can assess function and disability daily. OBJECTIVE: This work aims to prove the feasibility of an interpretable machine learning pipeline for predicting function and disability based on the World Health Organization Disability Assessment Schedule (WHODAS) 2.0 outcomes of clinical outpatients, using passively collected digital biomarkers. METHODS: One-month-long behavioral time-series data consisting of physical and digital activity descriptor variables were summarized using statistical measures (minimum, maximum, mean, median, SD, and IQR), creating 64 features that were used for prediction. We then applied a sequential feature selection to each WHODAS 2.0 domain (cognition, mobility, self-care, getting along, life activities, and participation) in order to find the most descriptive features for each domain. Finally, we predicted the WHODAS 2.0 functional domain scores using linear regression using the best feature subsets. We reported the mean absolute errors and the mean absolute percentage errors over 4 folds as goodness-of-fit statistics to evaluate the model and allow for between-domain performance comparison. RESULTS: Our machine learning-based models for predicting patients' WHODAS functionality scores per domain achieved an average (across the 6 domains) mean absolute percentage error of 19.5%, varying between 14.86% (self-care domain) and 27.21% (life activities domain). We found that 5-19 features were sufficient for each domain, and the most relevant being the distance traveled, time spent at home, time spent walking, exercise time, and vehicle time. CONCLUSIONS: Our findings show the feasibility of using machine learning-based methods to assess functional health solely from passively sensed mobile data. The feature selection step provides a set of interpretable features for each domain, ensuring better explainability to the models' decisions-an important aspect in clinical practice.

One-Week Suicide Risk Prediction Using Real-Time Smartphone Monitoring: Prospective Cohort Study.

BACKGROUND: Suicide is a major global public health issue that is becoming increasingly common despite preventive efforts. Though current methods for predicting suicide risk are not sufficiently accurate, technological advances provide invaluable tools with which we may evolve toward a personalized, predictive approach. OBJECTIVE: We aim to predict the short-term (1-week) risk of suicide by identifying changes in behavioral patterns characterized through real-time smartphone monitoring in a cohort of patients with suicidal ideation. METHODS: We recruited 225 patients between February 2018 and March 2020 with a history of suicidal thoughts and behavior as part of the multicenter SmartCrisis study. Throughout 6 months of follow-up, we collected information on the risk of suicide or mental health crises. All participants underwent voluntary passive monitoring using data generated by their own smartphones, including distance walked and steps taken, time spent at home, and app usage. The algorithm constructs daily activity profiles for each patient according to these data and detects changes in the distribution of these profiles over time. Such changes are considered critical periods, and their relationship with suicide-risk events was tested. RESULTS: During follow-up, 18 (8%) participants attempted suicide, and 14 (6.2%) presented to the emergency department for psychiatric care. The behavioral changes identified by the algorithm predicted suicide risk in a time frame of 1 week with an area under the curve of 0.78, indicating good accuracy. CONCLUSIONS: We describe an innovative method to identify mental health crises based on passively collected information from patients' smartphones. This technology could be applied to homogeneous groups of patients to identify different types of crises.

Smartphone-Based Ecological Momentary Assessment for the Measurement of the Performance Status and Health-Related Quality of Life in Cancer Patients Under Systemic Anticancer Therapies: Development and Acceptability of a Mobile App.

Background: We have defined a project to develop a mobile app that continually records smartphone parameters which may help define the Eastern Cooperative Oncology Group performance status (ECOG-PS) and the health-related quality of life (HRQoL), without interaction with patients or professionals. This project is divided into 3 phases. Here we describe phase 1. The objective of this phase was to develop the app and assess its usability concerning patient characteristics, acceptability, and satisfaction. Methods: The app eB2-ECOG was developed and installed in the smartphone of cancer patients who will be followed for six months. Criteria inclusion were: age over 18-year-old; diagnosed with unresectable or metastatic lung cancer, gastrointestinal stromal tumor, sarcoma, or head and neck cancer; under systemic anticancer therapies; and possession of a Smartphone. The app will collect passive and active data from the patients while healthcare professionals will evaluate the ECOG-PS and HRQoL through conventional tools. Acceptability was assessed during the follow-up. Patients answered a satisfaction survey in the app between 3-6 months from their inclusion. Results: The app developed provides a system for continuously collecting, merging, and processing data related to patient's health and physical activity. It provides a transparent capture service based on all the available data of a patient. Currently, 106 patients have been recruited. A total of 36 patients were excluded, most of them (21/36) due to technological reasons. We assessed 69 patients (53 lung cancer, 8 gastrointestinal stromal tumors, 5 sarcomas, and 3 head and neck cancer). Concerning app satisfaction, 70.4% (20/27) of patients found the app intuitive and easy to use, and 51.9% (17/27) of them said that the app helped them to improve and handle their problems better. Overall, 17 out of 27 patients [62.9%] were satisfied with the app, and 14 of them [51.8%] would recommend the app to other patients. Conclusions: We observed that the app's acceptability and satisfaction were good, which is essential for the continuity of the project. In the subsequent phases, we will develop predictive models based on the collected information during this phase. We will validate the method and analyze the sensitivity of the automated results.

Social media and smartphone app use predicts maintenance of physical activity during Covid-19 enforced isolation in psychiatric outpatients.

There is growing concern that the social and physical distancing measures implemented in response to the Covid-19 pandemic may negatively impact health in other areas, via both decreased physical activity and increased social isolation. Here, we investigated whether increased engagement with digital social tools may help mitigate effects of enforced isolation on physical activity and mood, in a naturalistic study of at-risk individuals. Passively sensed smartphone app use and actigraphy data were collected from a group of psychiatric outpatients before and during imposition of strict Covid-19 lockdown measures. Data were analysed using Gaussian graphical models: a form of network analysis which gives insight into the predictive relationships between measures across timepoints. Within-individuals, we found evidence of a positive predictive path between digital social engagement, general smartphone use, and physical activity-selectively under lockdown conditions (N = 127 individual users, M = 6201 daily observations). Further, we observed a positive relationship between social media use and total daily steps across individuals during (but not prior to) lockdown. Although there are important limitations on the validity of drawing causal conclusions from observational data, a plausible explanation for our findings is that, during lockdown, individuals use their smartphones to access social support, which may help guard against negative effects of in-person social deprivation and other pandemic-related stress. Importantly, passive monitoring of smartphone app usage is low burden and non-intrusive. Given appropriate consent, this could help identify people who are failing to engage in usual patterns of digital social interaction, providing a route to early intervention.