The application of digital technology to psychiatry research is rapidly leading to new discoveries and capabilities in the field of mobile health. However, the increase in opportunities to passively collect vast amounts of detailed information on study participants coupled with advances in statistical techniques that enable machine learning models to process such information has raised novel ethical dilemmas regarding researchers' duties to: (i) monitor adverse events and intervene accordingly; (ii) obtain fully informed, voluntary consent; (iii) protect the privacy of participants; and (iv) increase the transparency of powerful, machine learning models to ensure they can be applied ethically and fairly in psychiatric care. This review highlights emerging ethical challenges and unresolved ethical questions in mobile health research and provides recommendations on how mobile health researchers can address these issues in practice. Ultimately, the hope is that this review will facilitate continued discussion on how to achieve best practice in mobile health research within psychiatry.

Generalized anxiety disorder (GAD) and major depressive disorder (MDD) are highly prevalent and impairing problems, but frequently go undetected, leading to substantial treatment delays. Electronic health records (EHRs) collect a great deal of biometric markers and patient characteristics that could foster the detection of GAD and MDD in primary care settings. We approached the problem of predicting MDD and GAD using a novel machine learning pipeline to re-analyze data from an observational study. The pipeline constitutes an ensemble of algorithmically distinct machine learning methods, including deep learning. A sample of 4,184 undergraduate students completed the study, undergoing a general health screening and completing a psychiatric assessment for MDD and GAD. After explicitly excluding all psychiatric information, 59 biomedical and demographic features from the general health survey in addition to a set of engineered features were used for model training. We assessed the model's performance on a held-out test set and found an AUC of 0.73 (sensitivity: 0.66, specificity: 0.7) and 0.67 (sensitivity: 0.55, specificity: 0.7) for GAD, and MDD, respectively. Additionally, we used advanced techniques (SHAP values) to illuminate which features had the greatest impact on prediction for each disease. The top predictive features for MDD were being satisfied with living conditions and having public health insurance. The top predictive features for GAD were vaccinations being up to date and marijuana use. Our results indicate moderate predictive performance for the application of machine learning methods in detection of GAD and MDD based on EHR data. By identifying important predictors of GAD and MDD, these results may be used in future research to aid in the early detection of MDD and GAD.

Background: COVID-19 has led to dramatic changes globally in persons' everyday lives. To combat the pandemic, many governments have implemented social distancing, quarantine, and stay-at-home orders. There is limited research on the impact of such extreme measures on mental health. Objective: The goal of the present study was to examine whether stay-at-home orders produced differential changes in mental health symptoms using internet search queries at a national scale. Methods: In the United States, individual states vary in their adoption of measures to reduce the spread of COVID-19; as of March 23, 2020, eleven of the fifty states had issued stay-at-home orders. The staggered rollout of stay-at-home measures across the U.S. allows us to investigate whether these measures impact mental health by exploring variations in mental health search queries across the states. The current manuscript examines the changes in mental health search queries on Google between March 16-23, 2020 across each state and Washington D.C. Specifically, the current manuscript examines differential change in mental health searches based on patterns of search activity following issuance of stay-at-home orders in these states compared to all other states. Participants included all persons who searched mental health terms in Google between March 16-23. Between March 16-23, eleven states underwent stay-at-home orders to prevent the transmission of COVID-19. Outcomes included search terms measuring anxiety, depression, obsessive-compulsive, negative thoughts, irritability, fatigue, anhedonia, concentration, insomnia, and suicidal ideation. Results: Analyzing over 10 million search queries using generalized additive mixed models, the results suggested that the implementation of stay-at-home orders are associated with a significant flattening of the curve for searches for suicidal ideation, anxiety, negative thoughts, and sleep disturbances with the most prominent flattening associated with suicidal ideation and anxiety. Conclusions: These MENTAL HEALTH STAY-AT-HOME ORDERS COVID-19 4results suggest that, despite decreased social contact, mental health search queries increased rapidly prior to the issuance of stay-at-home orders, and these changes dissipated following the announcement and enactment of these orders. Although more research is needed to examine sustained effects, these results suggest mental health symptoms were associated with an immediately leveling off following the issuance of stay-at-home orders.

The contrast avoidance model (CAM) suggests that worry increases and sustains negative emotion to prevent a negative emotional contrast (sharp upward shift in negative emotion) and increase the probability of a positive contrast (shift toward positive emotion). In Study 1, we experimentally validated momentary assessment items (N = 25). In Study 2, participants with generalized anxiety disorder (N = 31) and controls (N = 37) were prompted once per hour regarding their worry, thought valence, and arousal 10 times a day for 8 days. Higher worry duration, negative thought valence, and uncontrollable train of thoughts predicted feeling more keyed up concurrently and sustained anxious activation 1 hr later. More worry, feeling keyed up, and uncontrollable train of thoughts predicted lower likelihood of a negative emotional contrast in thought valence and higher likelihood of a positive emotional contrast in thought valence 1 hr later. Findings support the prospective ecological validity of CAM. Our findings suggest that naturalistic worry reduces the likelihood of a sharp increase in negative affect and does so by increasing and sustaining anxious activation.

Background Since late 2019, the lives of people across the globe have been disrupted by COVID-19. Millions of people have become infected with the disease, while billions of people have been continually asked or required by local and national governments to change their behavioral patterns. Previous research on the COVID-19 pandemic suggests that it is associated with large-scale behavioral and mental health changes; however, few studies have been able to track these changes with frequent, near real-time sampling or compare these changes to previous years of data for the same individuals. Objective By combining mobile phone sensing and self-reported mental health data in a cohort of college-aged students enrolled in a longitudinal study, we seek to understand the behavioral and mental health impacts associated with the COVID-19 pandemic, measured by interest across the United States in the search terms coronavirus and COVID fatigue. Methods Behaviors such as the number of locations visited, distance traveled, duration of phone use, number of phone unlocks, sleep duration, and sedentary time were measured using the StudentLife mobile smartphone sensing app. Depression and anxiety were assessed using weekly self-reported ecological momentary assessments, including the Patient Health Questionnaire-4. The participants were 217 undergraduate students. Differences in behaviors and self-reported mental health collected during the Spring 2020 term, as compared to previous terms in the same cohort, were modeled using mixed linear models. Results Linear mixed models demonstrated differences in phone use, sleep, sedentary time and number of locations visited associated with the COVID-19 pandemic. In further models, these behaviors were strongly associated with increased interest in COVID fatigue. When mental health metrics (eg, depression and anxiety) were added to the previous measures (week of term, number of locations visited, phone use, sedentary time), both anxiety and depression (P<.001) were significantly associated with interest in COVID fatigue. Notably, these behavioral and mental health changes are consistent with those observed around the initial implementation of COVID-19 lockdowns in the spring of 2020. Conclusions In the initial lockdown phase of the COVID-19 pandemic, people spent more time on their phones, were more sedentary, visited fewer locations, and exhibited increased symptoms of anxiety and depression. As the pandemic persisted through the spring, people continued to exhibit very similar changes in both mental health and behaviors. Although these large-scale shifts in mental health and behaviors are unsurprising, understanding them is critical in disrupting the negative consequences to mental health during the ongoing pandemic.

Objective Prevention of eating disorders (EDs) is of high importance. However, digital programs with human moderation are unlikely to be disseminated widely. The aim of this study was to test whether a chatbot (i.e., computer program simulating human conversation) would significantly reduce ED risk factors (i.e., weight/shape concerns, thin‐ideal internalization) in women at high risk for an ED, compared to waitlist control, as well as whether it would significantly reduce overall ED psychopathology, depression, and anxiety and prevent ED onset. Method Women who screened as high risk for an ED were randomized (N = 700) to (1) chatbot based on the StudentBodies© program; or (2) waitlist control. Participants were followed for 6 months. Results For weight/shape concerns, there was a significantly greater reduction in intervention versus control at 3‐ (d = −0.20; p = .03) and 6‐m‐follow‐up (d = −0.19; p = .04). There were no differences in change in thin‐ideal internalization. The intervention was associated with significantly greater reductions than control in overall ED psychopathology at 3‐ (d = −0.29; p = .003) but not 6‐month follow‐up. There were no differences in change in depression or anxiety. The odds of remaining nonclinical for EDs were significantly higher in intervention versus control at both 3‐ (OR = 2.37, 95% CI [1.37, 4.11]) and 6‐month follow‐ups (OR = 2.13, 95% CI [1.26, 3.59]). Discussion Findings provide support for the use of a chatbot‐based EDs prevention program in reducing weight/shape concerns through 6‐month follow‐up, as well as in reducing overall ED psychopathology, at least in the shorter‐term. Results also suggest the intervention may reduce ED onset. Public Significance We found that a chatbot, or a computer program simulating human conversation, based on an established, cognitive‐behavioral therapy‐based eating disorders prevention program, was successful in reducing women's concerns about weight and shape through 6‐month follow‐up and that it may actually reduce eating disorder onset. These findings are important because this intervention, which uses a rather simple text‐based approach, can easily be disseminated in order to prevent these deadly illnesses. Trial registration: OSF Registries; https://osf.io/7zmbv

No abstract

Background This PRISMA systematic literature review examined the use of digital data collection methods (including ecological momentary assessment [EMA], experience sampling method [ESM], digital biomarkers, passive sensing, mobile sensing, ambulatory assessment, and time-series analysis), emphasizing on digital phenotyping (DP) to study depression. DP is defined as the use of digital data to profile health information objectively. Aims Four distinct yet interrelated goals underpin this study: (a) to identify empirical research examining the use of DP to study depression; (b) to describe the different methods and technology employed; (c) to integrate the evidence regarding the efficacy of digital data in the examination, diagnosis, and monitoring of depression and (d) to clarify DP definitions and digital mental health records terminology. Results Overall, 118 studies were assessed as eligible. Considering the terms employed, “EMA”, “ESM”, and “DP” were the most predominant. A variety of DP data sources were reported, including voice, language, keyboard typing kinematics, mobile phone calls and texts, geocoded activity, actigraphy sensor-related recordings (i.e., steps, sleep, circadian rhythm), and self-reported apps’ information. Reviewed studies employed subjectively and objectively recorded digital data in combination with interviews and psychometric scales. Conclusions Findings suggest links between a person’s digital records and depression. Future research recommendations include (a) deriving consensus regarding the DP definition and (b) expanding the literature to consider a person’s broader contextual and developmental circumstances in relation to their digital data/records.