Mental health disorders—including depression, anxiety, trauma-related, and psychotic conditions—are pervasive and impairing, representing considerable challenges for both individual well-being and public health. Often the first challenges to treatment include financial, geographic, and stigmatic barriers, which limit the accessibility of traditional assessment measures. Further, compounded by frequent misdiagnosis or delayed detection, there is a need for effective, accessible, and scalable approaches to identification and management. Considering advances in computing and the ubiquitous nature of personal mobile and wearable technology, this narrative review examines the utilization of passive sensor data as a screening and diagnostic tool for mental disorders. As an alternative to traditional screening measures, passive sensing offers a tool to overcome barriers that prevent many from seeking services. We critically assess the literature up to September 2023, exploring the use of passive data—such as heart rate variability, movement patterns, and geolocation—to predict mental health outcomes across a spectrum of disorders. From a translational perspective, our review explores the state of passive sensing science, with special emphasis on the capacity for the science to be implemented in real world clinical and general populations, a novelty specific to this review to the best of our knowledge. Toward this aim, we consider multiple study factors, including participant demographics, data collection methods, sensor modalities, outcome measures, and analytic modeling approaches. We find that passive sensing features, such as GPS, heart rate, and actigraphy offer promise for enhancing early detection and improving the diagnostic process for mental disorders. Despite this promise, however, our findings highlight important limitations in passive sensing research including (1) a trend toward smaller, specialized samples, (2) a predominance of data collection apps built on the Android operating system, and (3) a reliance on self-reported measures as proxies for important clinical outcomes. These limitations ultimately stymie efforts to implement and scale important research findings in larger and more heterogeneous populations. With future translational research in mind, we emphasize the importance of validating passive sensing findings with larger, more diverse samples and ensuring assessment tools can be deployed across multiple device types and operating systems. Further, where possible, we emphasize the need for robust, objectively validated outcome measures, such as by clinician assessment. We conclude that careful consideration of translational factors in the design of future research will aid in enhancing the impact of future passive sensing studies, ultimately enhancing mental health outcomes on a broad scale.

Major Depressive Disorder (MDD) is a heterogeneous disorder, resulting in challenges with early detection. However, changes in sleep and movement patterns may help improve detection. Thus, this study aimed to explore the utility of wrist-worn actigraphy data in combination with machine learning (ML) and deep learning techniques to detect MDD using a commonly used screening method: Patient Health Questionnaire-9 (PHQ-9). Participants (N = 8,378; MDD Screening = 766 participants) completed the and wore Actigraph GT3X+ for one week as part of the National Health and Nutrition Examination Survey (NHANES). Leveraging minute-level, actigraphy data, we evaluated the efficacy of two commonly used ML approaches and identified actigraphy-derived biomarkers indicative of MDD. We employed two ML modeling strategies: (1) a traditional ML approach with theory-driven feature derivation, and (2) a deep learning Convolutional Neural Network (CNN) approach, coupled with gramian angular field transformation. Findings revealed movement-related features to be the most influential in the traditional ML approach and nighttime movement to be the most influential in the CNN approach for detecting MDD. Using a large, nationally-representative sample, this study highlights the potential of using passively-collected, actigraphy data for understanding MDD to better improve diagnosing and treating MDD.

Major Depressive Disorder (MDD) presents considerable challenges to diagnosis and management due to symptom variability across time. Only recent work has highlighted the clinical implications for interrogating depression symptom variability. Thus, the present work investigates how sociodemographic, comorbidity, movement, and sleep data is associated with long-term depression symptom variability. Participant information included (N = 939) baseline sociodemographic and comorbidity data, longitudinal, passively collected wearable data, and Patient Health Questionnaire-9 (PHQ-9) scores collected over 12 months. An ensemble machine learning approach was used to detect long-term depression symptom variability via: (i) a domain-driven feature selection approach and (ii) an exhaustive feature-inclusion approach. SHapley Additive exPlanations (SHAP) were used to interrogate variable importance and directionality. The composite domain-driven and exhaustive inclusion models were both capable of moderately detecting long-term depression symptom variability (r = 0.33 and r = 0.39, respectively). Our results indicate the incremental predictive validity of sociodemographic, comorbidity, and passively collected wearable movement and sleep data in detecting long-term depression symptom variability.

OBJECTIVE: Pediatric Autoimmune Neuropsychiatric Disorder Associated with Streptococcal infection (PANDAS) and Pediatric Acute-Onset Neuropsychiatric syndrome (PANS) are presumed autoimmune complications of infection or other instigating events. To determine the incidence of these disorders, we performed a retrospective review for the years 2017-2019 at three academic medical centers. METHODS: We identified the population of children receiving well-child care at each institution. Potential cases of PANS and PANDAS were identified by including children age 3-12 years at the time they received one of five new diagnoses: avoidant/restrictive food intake disorder, other specified eating disorder, separation anxiety disorder of childhood, obsessive-compulsive disorder, or other specified disorders involving an immune mechanism, not elsewhere classified. Tic disorders was not used as a diagnostic code to identify cases. Data were abstracted; cases were classified as PANDAS or PANS if standard definitions were met. RESULTS: The combined study population consisted of 95,498 individuals. The majority were non-Hispanic Caucasian (85%), 48% were female and the mean age was 7.1 (SD 3.1) years. Of 357 potential cases, there were 13 actual cases [mean age was 6.0 (SD 1.8) years, 46% female and 100% non-Hispanic Caucasian]. The estimated annual incidence of PANDAS/PANS was 1/11,765 for children between 3 and 12 years with some variation between different geographic areas. CONCLUSION: Our results indicate that PANDAS/PANS is a rare disorder with substantial heterogeneity across geography and time. A prospective investigation of the same question is warranted.

IMPORTANCE: Selective serotonin reuptake inhibitors (SSRIs) are a common first-line treatment for some psychiatric disorders, including depression and anxiety; although they are generally well tolerated, SSRIs have known adverse effects, including movement problems, sleep disruption, and gastrointestinal problems (eg, nausea and upset stomach). No large-scale studies using naturalistic, longitudinal, objective data have validated physical activity findings, and actigraphy data are well suited to address this task. OBJECTIVES: To evaluate whether differences in physical movement exist among individuals treated with SSRIs compared with control participants and to identify the unique features of the movement of patients treated with SSRIs. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study examines longitudinally collected wearable movement data within a cross-sectional sample of 7162 participants from the 2005-2006 National Health and Nutrition Examination Survey (NHANES), a nationally representative population-based sample of noninstitutionalized persons in the US having both medication information and passive movement data. Statistical analysis was performed from April 1, 2021, to February 1, 2022. EXPOSURES: The use of SSRIs (sertraline hydrochloride, escitalopram oxalate, fluoxetine hydrochloride, paroxetine hydrochloride, and citalopram hydrobromide), as reported by participants interviewed by NNHANES personnel, was the primary exposure, measured as a binary variable (taking an SSRI vs not taking an SSRI). MAIN OUTCOMES AND MEASURES: The primary outcome was the intensity of body movement as recorded by a piezoelectric accelerometer worn on the right hip for more than 1 week. RESULTS: Of the 7162 participants included in the study, the mean (SD) age was 33.7 (22.6) years, 266 (3.7%) were taking an SSRI, 3706 (51.7%) were female, 1934 (27.0%) were Black, 1823 (25.5%) were Mexican American, 210 (2.9%) were other Hispanic, 336 (4.7%) were other or multiracial, and 2859 (39.9%) were White (per the NHANES data collection protocol). A cross-validated, deep learning classifier was constructed that achieved fair performance predicting SSRI use (area under the curve, 0.67 [95% CI, 0.64-0.71] for the validation set and 0.66 [95% CI, 0.64-0.68] for the test set). To account for possible confounding by indication, we constructed a parallel model incorporating depression severity, finding only marginal performance improvement. When averaged across individuals and across 7 days, the results show less overall movement in the SSRI group (mean, 120.1 vertical acceleration counts/min [95% CI, 115.7-124.6 vertical acceleration counts/min]) compared with the non-SSRI control group (mean, 168.8 vertical acceleration counts/min [95% CI, 162.8-174.9 vertical acceleration counts/min]). CONCLUSIONS AND RELEVANCE: This cross-sectional study found a moderate association between passive movement and SSRI use, as well as SSRI detection capacity of passive movement using time series deep learning models. The results support the use of passive sensors for exploration and characterization of psychotropic medication adverse effects.