Identifying a stable and generalizable factor structure of major depressive disorder across three large longitudinal cohorts.

The Patient Health Questionnaire 9 (PHQ-9) is the current standard outpatient screening tool for measuring and tracking the nine symptoms of major depressive disorder (MDD). While the PHQ-9 was originally conceptualized as a unidimensional measure, it has become clear that MDD is not a monolithic construct, as evidenced by high comorbidities with other theoretically distinct diagnoses and common symptom overlap between depression and other diagnoses. Therefore, identifying reliable and temporally stable subfactors of depressive symptoms could allow research and care to be tailored to different depression phenotypes. This study improved on previous factor analysis studies of the PHQ-9 by leveraging samples that were clinical (participants with depression only), large (N = 1483 depressed individuals in total), longitudinal (up to 5 years), and from three diverse (matching racial distribution of the United States) datasets. By refraining from assuming the number of factors or item loadings a priori, and thus utilizing a solely data-driven approach, we identified a ranked list of best-fitting models, with the parsimonious one achieving good model fit across studies at most timepoints (average TLI >= 0.90). This model categorizes the PHQ-9 items into four factors: (1) Affective (Anhedonia + Depressed Mood), (2) Somatic (Sleep + Fatigue + Appetite), (3) Internalizing (Worth/Guilt + Suicidality), (4) Sensorimotor (Concentration + Psychomotor), which may be used to further precision psychiatry by testing factor-specific interventions in research and clinical settings.

Identifying Mobile Sensing Indicators of Stress-Resilience.

Resident physicians (residents) experiencing prolonged workplace stress are at risk of developing mental health symptoms. Creating novel, unobtrusive measures of resilience would provide an accessible approach to evaluate symptom susceptibility without the perceived stigma of formal mental health assessments. In this work, we created a system to find indicators of resilience using passive wearable sensors and smartphone-delivered ecological momentary assessment (EMA). This system identified indicators of resilience during a medical internship, the high stress first-year of a residency program. We then created density estimation approaches to predict these indicators before mental health changes occurred, and validated whether the predicted indicators were also associated with resilience. Our system identified resilience indicators associated with physical activity (step count), sleeping behavior, reduced heart rate, increased mood, and reduced mood variability. Density estimation models were able to replicate a subset of the associations between sleeping behavior, heart rate, and resilience. To the best of our knowledge, this work provides the first methodology to identify and predict indicators of resilience using passive sensing and EMA. Researchers studying resident mental health can apply this approach to design resilience-building interventions and prevent mental health symptom development.

Using behavioral rhythms and multi-task learning to predict fine-grained symptoms of schizophrenia.

Schizophrenia is a severe and complex psychiatric disorder with heterogeneous and dynamic multi-dimensional symptoms. Behavioral rhythms, such as sleep rhythm, are usually disrupted in people with schizophrenia. As such, behavioral rhythm sensing with smartphones and machine learning can help better understand and predict their symptoms. Our goal is to predict fine-grained symptom changes with interpretable models. We computed rhythm-based features from 61 participants with 6,132 days of data and used multi-task learning to predict their ecological momentary assessment scores for 10 different symptom items. By taking into account both the similarities and differences between different participants and symptoms, our multi-task learning models perform statistically significantly better than the models trained with single-task learning for predicting patients' individual symptom trajectories, such as feeling depressed, social, and calm and hearing voices. We also found different subtypes for each of the symptoms by applying unsupervised clustering to the feature weights in the models. Taken together, compared to the features used in the previous studies, our rhythm features not only improved models' prediction accuracy but also provided better interpretability for how patients' behavioral rhythms and the rhythms of their environments influence their symptom conditions. This will enable both the patients and clinicians to monitor how these factors affect a patient's condition and how to mitigate the influence of these factors. As such, we envision that our solution allows early detection and early intervention before a patient's condition starts deteriorating without requiring extra effort from patients and clinicians.

Predicting Early Warning Signs of Psychotic Relapse From Passive Sensing Data: An Approach Using Encoder-Decoder Neural Networks.

BACKGROUND: Schizophrenia spectrum disorders (SSDs) are chronic conditions, but the severity of symptomatic experiences and functional impairments vacillate over the course of illness. Developing unobtrusive remote monitoring systems to detect early warning signs of impending symptomatic relapses would allow clinicians to intervene before the patient's condition worsens. OBJECTIVE: In this study, we aim to create the first models, exclusively using passive sensing data from a smartphone, to predict behavioral anomalies that could indicate early warning signs of a psychotic relapse. METHODS: Data used to train and test the models were collected during the CrossCheck study. Hourly features derived from smartphone passive sensing data were extracted from 60 patients with SSDs (42 nonrelapse and 18 relapse >1 time throughout the study) and used to train models and test performance. We trained 2 types of encoder-decoder neural network models and a clustering-based local outlier factor model to predict behavioral anomalies that occurred within the 30-day period before a participant's date of relapse (the near relapse period). Models were trained to recreate participant behavior on days of relative health (DRH, outside of the near relapse period), following which a threshold to the recreation error was applied to predict anomalies. The neural network model architecture and the percentage of relapse participant data used to train all models were varied. RESULTS: A total of 20,137 days of collected data were analyzed, with 726 days of data (0.037%) within any 30-day near relapse period. The best performing model used a fully connected neural network autoencoder architecture and achieved a median sensitivity of 0.25 (IQR 0.15-1.00) and specificity of 0.88 (IQR 0.14-0.96; a median 108% increase in behavioral anomalies near relapse). We conducted a post hoc analysis using the best performing model to identify behavioral features that had a medium-to-large effect (Cohen d>0.5) in distinguishing anomalies near relapse from DRH among 4 participants who relapsed multiple times throughout the study. Qualitative validation using clinical notes collected during the original CrossCheck study showed that the identified features from our analysis were presented to clinicians during relapse events. CONCLUSIONS: Our proposed method predicted a higher rate of anomalies in patients with SSDs within the 30-day near relapse period and can be used to uncover individual-level behaviors that change before relapse. This approach will enable technologists and clinicians to build unobtrusive digital mental health tools that can predict incipient relapse in SSDs.

CrossCheck: Integrating self-report, behavioral sensing, and smartphone use to identify digital indicators of psychotic relapse.

OBJECTIVE: This purpose of this study was to describe and demonstrate CrossCheck, a multimodal data collection system designed to aid in continuous remote monitoring and identification of subjective and objective indicators of psychotic relapse. METHOD: Individuals with schizophrenia-spectrum disorders received a smartphone with the monitoring system installed along with unlimited data plan for 12 months. Participants were instructed to carry the device with them and to complete brief self-reports multiple times a week. Multimodal behavioral sensing (i.e., physical activity, geospatials activity, speech frequency, and duration) and device use data (i.e., call and text activity, app use) were captured automatically. Five individuals who experienced psychiatric hospitalization were selected and described for instructive purposes. RESULTS: Participants had unique digital indicators of their psychotic relapse. For some, self-reports provided clear and potentially actionable description of symptom exacerbation prior to hospitalization. Others had behavioral sensing data trends (e.g., shifts in geolocation patterns, declines in physical activity) or device use patterns (e.g., increased nighttime app use, discontinuation of all smartphone use) that reflected the changes they experienced more effectively. CONCLUSION: Advancements in mobile technology are enabling collection of an abundance of information that until recently was largely inaccessible to clinical research and practice. However, remote monitoring and relapse detection is in its nascence. Development and evaluation of innovative data management, modeling, and signal-detection techniques that can identify changes within an individual over time (i.e., unique relapse signatures) will be essential if we are to capitalize on these data to improve treatment and prevention. (PsycINFO Database Record