Digital Phenotyping for Mood Disorders: Methodology-Oriented Pilot Feasibility Study.

BACKGROUND: In the burgeoning area of clinical digital phenotyping research, there is a dearth of literature that details methodology, including the key challenges and dilemmas in developing and implementing a successful architecture for technological infrastructure, patient engagement, longitudinal study participation, and successful reporting and analysis of diverse passive and active digital data streams. OBJECTIVE: This article provides a narrative rationale for our study design in the context of the current evidence base and best practices, with an emphasis on our initial lessons learned from the implementation challenges and successes of this digital phenotyping study. METHODS: We describe the design and implementation approach for a digital phenotyping pilot feasibility study with attention to synthesizing key literature and the reasoning for pragmatic adaptations in implementing a multisite study encompassing distinct geographic and population settings. This methodology was used to recruit patients as study participants with a clinician-validated diagnostic history of unipolar depression, bipolar I disorder, or bipolar II disorder, or healthy controls in 2 geographically distinct health care systems for a longitudinal digital phenotyping study of mood disorders. RESULTS: We describe the feasibility of a multisite digital phenotyping pilot study for patients with mood disorders in terms of passively and actively collected phenotyping data quality and enrollment of patients. Overall data quality (assessed as the amount of sensor data obtained vs expected) was high compared to that in related studies. Results were reported on the relevant demographic features of study participants, revealing recruitment properties of age (mean subgroup age ranged from 31 years in the healthy control subgroup to 38 years in the bipolar I disorder subgroup), sex (predominance of female participants, with 7/11, 64% females in the bipolar II disorder subgroup), and smartphone operating system (iOS vs Android; iOS ranged from 7/11, 64% in the bipolar II disorder subgroup to 29/32, 91% in the healthy control subgroup). We also described implementation considerations around digital phenotyping research for mood disorders and other psychiatric conditions. CONCLUSIONS: Digital phenotyping in affective disorders is feasible on both Android and iOS smartphones, and the resulting data quality using an open-source platform is higher than that in comparable studies. While the digital phenotyping data quality was independent of gender and race, the reported demographic features of study participants revealed important information on possible selection biases that may result from naturalistic research in this domain. We believe that the methodology described will be readily reproducible and generalizable to other study settings and patient populations given our data on deployment at 2 unique sites.

Systematic review: Wearable remote monitoring to detect nonalcohol/nonnicotine-related substance use disorder symptoms.

BACKGROUND AND OBJECTIVES: Substance use disorders (SUDs) are chronic relapsing diseases characterized by significant morbidity and mortality. Phenomenologically, patients with SUDs present with a repeating cycle of intoxication, withdrawal, and craving, significantly impacting their diagnosis and treatment. There is a need for better identification and monitoring of these disease states. Remote monitoring chronic illness with wearable devices offers a passive, unobtrusive, constant physiological data assessment. We evaluate the current evidence base for remote monitoring of nonalcohol, nonnicotine SUDs. METHODS: We performed a systematic, comprehensive literature review and screened 1942 papers. RESULTS: We found 15 studies that focused mainly on the intoxication stage of SUD. These studies used wearable sensors measuring several physiological parameters (ECG, HR, O2 , Accelerometer, EDA, temperature) and implemented study-specific algorithms to evaluate the data. DISCUSSION AND CONCLUSIONS: Studies were extracted, organized, and analyzed based on the three SUD disease states. The sample sizes were relatively small, focused primarily on the intoxication stage, had low monitoring compliance, and required significant computational power preventing "real-time" results. Cardiovascular data was the most consistently valuable data in the predictive algorithms. This review demonstrates that there is currently insufficient evidence to support remote monitoring of SUDs through wearable devices. SCIENTIFIC SIGNIFICANCE: This is the first systematic review to show the available data on wearable remote monitoring of SUD symptoms in each stage of the disease cycle. This clinically relevant approach demonstrates what we know and do not know about the remote monitoring of SUDs within disease states.

Clinician Satisfaction with Rapid Adoption and Implementation of Telehealth Services During the COVID-19 Pandemic.

Background: To examine clinician perspectives on the acceptability, appropriateness/suitability, and feasibility of video telehealth as a way to deliver mental health services during the COVID-19 pandemic. Materials and Methods: Mental health clinicians were surveyed with 27 Likert questions, using previously validated measures, on satisfaction and implementation experience with video telehealth visits between March and June 2020. Results: A total of 112 of 193 clinicians completed the survey (58.0%), including psychiatrists, psychologists, trainees (i.e., residents and fellows), advanced practice providers, and licensed mental health counselors. Clinicians reported high levels of acceptability, feasibility, and appropriateness of video telehealth; they also reported high levels of satisfaction with video telehealth visits. Seventy-nine and a half (79.5%) reported that their patients seemed highly satisfied with video telehealth visits, and 107 (95.5%) of clinicians responded that they would like video telehealth visits to represent at least 25% of their practice in the future. Discussion: Mental health clinicians showed positive attitudes toward the implementation of video telehealth visits, high levels of satisfaction with this care, and indicated strong interest in continuing this modality as a significant portion of clinical practice. Conclusions: This study demonstrates the ability of mental health clinicians to embrace new technology to expand access to care during the COVID-19 pandemic. Results indicate that telemental health is likely to be an integral part of clinic practice in the future.

Transitioning Virtual-Only Group Therapy for Substance Use Disorder Patients to a Hybrid Model.

Purpose: Telehealth is associated with a myriad of benefits; however, little is known regarding substance use disorder (SUD) treatment outcomes when participants join group therapy sessions in a combination in-person and virtual setting (hybrid model). We sought to determine if treatment completion rates differed. Patients and Methods: Policy changes caused by the COVID-19 pandemic created a naturalistic, observational cohort study at seven intensive outpatient (IOP) programs in rural Minnesota. Virtual-only delivery occurred 6/1/2020-6/30/2021, while hybrid groups occurred 7/1/2021-7/31/2022. Data was evaluated retrospectively for participants who initiated and discharged treatment during the study period. Participants were IOP group members 18 years and older who had a SUD diagnosis that both entered and discharged treatment during the 26-month period. A consecutive sample of 1502 participants (181-255 per site) was available, with 644 removed: 576 discharged after the study conclusion, 49 were missing either enrollment or discharge data, 14 transferred sites during treatment, and 5 initiated treatment before the study initiation. Helmert contrasts evaluated the impact of hybrid group exposure. Results: A total of 858 individuals were included. Data was not from the medical chart and was deidentified preventing specific demographics; however, the overall IOP sample for 2020-2022, from which the sample was derived, was 29.8% female, and 64.1% were 18-40 years of age. For completed treatment, hybrid group exposure relative to virtual-only had a univariate odds ratio of 1.88 (95% CI: 1.50-2.41, p < 0.001). No significant difference was seen across IOP sites. Conclusion: These results describe a novel hybrid group approach to virtual care for SUDs with outcome data not previously documented in the literature. While virtual treatment delivery can increase access, these results suggest a benefit is derived from including an in-person option. Further research is needed to identify how an in-person component may change dynamics and if it can be replicated in virtual-only models.

Improving Supervisor Confidence in Responding to Distressed Health Care Employees.

BACKGROUND: Professional distress and burnout are increasingly common among health professionals. This trend prompted stakeholders at a large multicenter health care system to survey supervisors for improvement opportunities. The stakeholders learned that workplace leaders lacked tools and direction for appropriately responding to distressed employees. The authors implemented a supervisor training video on providing resources to improve employee mental health. METHODS: Using the DMAIC (Define, Measure, Analyze, Improve, and Control) methodology, the authors conducted key stakeholder interviews to identify strengths, weaknesses, opportunities, and threats. Next, an e-mail survey was administered to a representative sample of supervisors that asked about degree of confidence in responding appropriately to distressed employees, with the response options "very confident," "somewhat confident," and "not at all confident." After identifying factors contributing to low supervisor confidence, the research team developed and disseminated a six-minute, on-demand video to train supervisors to respond appropriately to employees during a mental health crisis. The same group of supervisors were surveyed using the same survey after exposure to the video, and responses were collected from those who had viewed the video but had not answered the preintervention survey. RESULTS: The proportion of supervisors who responded "not at all confident" in the survey decreased from 7.1% (15/210) of responses to 0.8% (1/123), while the proportion of supervisors who chose "somewhat confident" increased significantly, from 62.9% (132/210) to 69.1% (85/123) (p = 0.03). Of the 28 supervisors who had not participated in the presurvey and viewed the video, none indicated that they were "not at all confident." The percentage of supervisors who felt distress "sometimes" or more frequently from navigating and supporting employee emotional concerns decreased nonsignificantly from 41.9% (88/210) to 37.4% (46/123) (p = 0.87). CONCLUSION: Simple, on-demand supervisor training videos can improve the confidence of supervisors to respond appropriately to distressed employees, which may indirectly contribute to improved employee mental health.

Therapeutic Content of Mobile Phone Applications for Substance Use Disorders: An Umbrella Review.

Mobile phone applications (MPAs) for substance use disorder (SUD) treatment are increasingly used by patients. Although pilot studies have shown promising results, multiple previous systematic reviews noted insufficient evidence for MPA use in SUD treatment-many of the previously published reviews evaluated different trials. Subsequently, we aimed to conduct an umbrella review of previously published reviews investigating the efficacy of MPAs for SUD treatment, excluding nicotine/tobacco because umbrella reviews have been done in this population and the nicotine/tobacco MPA approach often differs from SUD-focused MPAs. No previous reviews have included a statistical meta-analysis of clinical trials to quantify an estimated overall effect. Seven reviews met inclusion criteria, and 17 unique studies with available data were taken from those reviews for the meta-analysis. Overall, reviews reported a lack of evidence for recommending MPAs for SUD treatment. However, MPA-delivered recovery support services, cognitive behavioral therapy, and contingency management were identified across multiple reviews as having promising evidence for SUD treatment. Hedges g effect size for an MPA reduction in substance use-related outcomes relative to the control arm was insignificant (0.137; 95% CI, -0.056 to 0.330; P=.16). In subgroup analysis, contingency management (1.29; 95% CI, 1.088-1.482; τ 2=0; k=2) and cognitive behavioral therapy (0.02; 95% CI, 0.001-0.030; τ 2=0; k=2) were significant. Although contingency management's effect was large, both trials were small (samples of 40 and 30). This review includes an adapted framework for the American Psychiatric Association's MPA guidelines that clinicians can implement to review MPAs critically with patients.

Classifying and clustering mood disorder patients using smartphone data from a feasibility study.

Differentiating between bipolar disorder and major depressive disorder can be challenging for clinicians. The diagnostic process might benefit from new ways of monitoring the phenotypes of these disorders. Smartphone data might offer insight in this regard. Today, smartphones collect dense, multimodal data from which behavioral metrics can be derived. Distinct patterns in these metrics have the potential to differentiate the two conditions. To examine the feasibility of smartphone-based phenotyping, two study sites (Mayo Clinic, Johns Hopkins University) recruited patients with bipolar I disorder (BPI), bipolar II disorder (BPII), major depressive disorder (MDD), and undiagnosed controls for a 12-week observational study. On their smartphones, study participants used a digital phenotyping app (mindLAMP) for data collection. While in use, mindLAMP gathered real-time geolocation, accelerometer, and screen-state (on/off) data. mindLAMP was also used for EMA delivery. MindLAMP data was then used as input variables in binary classification, three-group k-nearest neighbors (KNN) classification, and k-means clustering. The best-performing binary classification model was able to classify patients as control or non-control with an AUC of 0.91 (random forest). The model that performed best at classifying patients as having MDD or bipolar I/II had an AUC of 0.62 (logistic regression). The k-means clustering model had a silhouette score of 0.46 and an ARI of 0.27. Results support the potential for digital phenotyping methods to cluster depression, bipolar disorder, and healthy controls. However, due to inconsistencies in accuracy, more data streams are required before these methods can be applied to clinical practice.

A risk identification model for detection of patients at risk of antidepressant discontinuation.

Purpose: Between 30 and 68% of patients prematurely discontinue their antidepressant treatment, posing significant risks to patient safety and healthcare outcomes. Online healthcare forums have the potential to offer a rich and unique source of data, revealing dimensions of antidepressant discontinuation that may not be captured by conventional data sources. Methods: We analyzed 891 patient narratives from the online healthcare forum, "askapatient.com," utilizing content analysis to create PsyRisk-a corpus highlighting the risk factors associated with antidepressant discontinuation. Leveraging PsyRisk, alongside PsyTAR [a publicly available corpus of adverse drug reactions (ADRs) related to antidepressants], we developed a machine learning-driven algorithm for proactive identification of patients at risk of abrupt antidepressant discontinuation. Results: From the analyzed 891 patients, 232 reported antidepressant discontinuation. Among these patients, 92% experienced ADRs, and 72% found these reactions distressful, negatively affecting their daily activities. Approximately 26% of patients perceived the antidepressants as ineffective. Most reported ADRs were physiological (61%, 411/673), followed by cognitive (30%, 197/673), and psychological (28%, 188/673) ADRs. In our study, we employed a nested cross-validation strategy with an outer 5-fold cross-validation for model selection, and an inner 5-fold cross-validation for hyperparameter tuning. The performance of our risk identification algorithm, as assessed through this robust validation technique, yielded an AUC-ROC of 90.77 and an F1-score of 83.33. The most significant contributors to abrupt discontinuation were high perceived distress from ADRs and perceived ineffectiveness of the antidepressants. Conclusion: The risk factors identified and the risk identification algorithm developed in this study have substantial potential for clinical application. They could assist healthcare professionals in identifying and managing patients with depression who are at risk of prematurely discontinuing their antidepressant treatment.

Short Term Second-Generation Antidepressant Monotherapy in Acute Depressive Episodes of Bipolar II Disorder: A Systematic Review and Meta-Analysis.

Purpose: Bipolar II disorder (BD-II) has limited evidence-based treatment guidelines. The aim of this systematic review and meta-analysis was to estimate the efficacy and safety of second-generation antidepressant (SGAD) monotherapy in acute BD-II depression. Methods: A literature search was conducted from the database inception through March 2021. Only randomized controlled trials (RCTs) were included. Outcome measures included: response rates, treatment-emergent affective switch (TEAS) rates, discontinuation due to side-effects, and all-cause discontinuation. Risk ratio (RR) was calculated using the Mantel-Haenszel random effects model. Results: 3301 studies were screened, and 15 articles were selected for full-text review. Five studies met the inclusion criteria: Four double-blind RCTs (n = 533) and one open-label RCT (n = 83) were included. Two double-blind RCTs [n = 223, SGAD = 110 (venlafaxine = 65, sertraline = 45), lithium/control = 113] were included for meta-analysis. The response rate for SGAD monotherapy compared to lithium monotherapy were similar (RR = 1.44, 95% CI 0.78, 2.66). The TEAS rate for SGAD monotherapy was not significantly different from lithium monotherapy (p = 0.76). The discontinuation rate due to side-effects for SGAD monotherapy was significantly lower than lithium monotherapy with a RR = 0.32, 95% CI 0.11, 0.96, p = 0.04 but all-cause discontinuation rates were similar in both groups. Conclusions: Limited data suggests short-term efficacy of venlafaxine and sertraline monotherapy in patients with acute BD-II depression with good side effect tolerability and without significantly increased switch rate. There is an urgent need for RCTs investigating the role of SGAD monotherapy in short and long-term among patients with BD-II.

Implementation of a Centralized Telepsychiatry Consult Service in a Multi-Hospital Metropolitan Health Care System: Challenges and Opportunities.

BACKGROUND: Providing adequate psychiatry consultation capacity on a 24/7 basis is an intrinsic challenge throughout many multihospital health care systems. At present, implementation research has not adequately defined the effectiveness and feasibility of a centralized telepsychiatry consultation service within a multihospital health care system. OBJECTIVE: To demonstrate feasibility of a hub and spoke model for provision of inpatient consult telepsychiatry service from an academic medical center to 2 affiliated regional hospital sites, to reduce patient wait time, and to develop best practice guidelines for telepsychiatry consultations to the acutely medically ill. METHODS: The implementation, interprofessional workflow, process of triage, and provider satisfaction were described from the first 13 months of the service. RESULTS: This pilot study resulted in 557 completed telepsychiatry consults over the course of 13 months from 2018 to 2019. A range of psychiatric conditions commonly encountered by consultation-liaison services were diagnosed and treated through the teleconferencing modality. The most common barriers to successful use of telepsychiatry were defined for the 20% of consult requests that were retriaged to face-to-face evaluation. The average patient wait time from consult request to initial consultation was reduced from >24 hours to 92 minutes. CONCLUSIONS: This study demonstrated the feasibility of a centralized telepsychiatry hub to improve delivery of psychiatry consultation within a multihospital system with an overall reduction in patient wait time. This work may serve as a model for further design innovation across many health care settings and new patient subpopulations.

Substance Use Disorders and Telehealth in the COVID-19 Pandemic Era: A New Outlook.

During the current coronavirus disease 2019 epidemic, many outpatient chemical dependency treatment programs and clinics are decreasing their number of in-person patient contacts. This has widened an already large gap between patients with substance use disorders (SUDs) who need treatment and those who have actually received treatment. For a disorder where group therapy has been the mainstay treatment option for decades, social distancing, shelter in place, and treatment discontinuation have created an urgent need for alternative approaches to addiction treatment. In an attempt to continue some care for patients in need, many medical institutions have transitioned to a virtual environment to promote safe social distancing. Although there is ample evidence to support telemedical interventions, these can be difficult to implement, especially in the SUD population. This article reviews current literature for the use of telehealth interventions in the treatment of SUDs and offers recommendations on safe and effective implementation strategies based on the current literature.

Social determinants of health in mental health care and research: a case for greater inclusion.

Social determinants of health (SDOH) are known to influence mental health outcomes, which are independent risk factors for poor health status and physical illness. Currently, however, existing SDOH data collection methods are ad hoc and inadequate, and SDOH data are not systematically included in clinical research or used to inform patient care. Social contextual data are rarely captured prospectively in a structured and comprehensive manner, leaving large knowledge gaps. Extraction methods are now being developed to facilitate the collection, standardization, and integration of SDOH data into electronic health records. If successful, these efforts may have implications for health equity, such as reducing disparities in access and outcomes. Broader use of surveys, natural language processing, and machine learning methods to harness SDOH may help researchers and clinical teams reduce barriers to mental health care.