Digital phenotyping data and anomaly detection methods to assess changes in mood and anxiety symptoms across a transdiagnostic clinical sample.

INTRODUCTION: Clinical assessment of mood and anxiety change often relies on clinical assessment or self-reported scales. Using smartphone digital phenotyping data and resulting markers of behavior (e.g., sleep) to augment clinical symptom scores offers a scalable and potentially more valid method to understand changes in patients' state. This paper explores the potential of using a combination of active and passive sensors in the context of smartphone-based digital phenotyping to assess mood and anxiety changes in two distinct cohorts of patients to assess the preliminary reliability and validity of this digital phenotyping method. METHODS: Participants from two different cohorts, each n = 76, one with diagnoses of depression/anxiety and the other schizophrenia, utilized mindLAMP to collect active data (e.g., surveys on mood/anxiety), along with passive data consisting of smartphone digital phenotyping data (geolocation, accelerometer, and screen state) for at least 1 month. Using anomaly detection algorithms, we assessed if statistical anomalies in the combination of active and passive data could predict changes in mood/anxiety scores as measured via smartphone surveys. RESULTS: The anomaly detection model was reliably able to predict symptom change of 4 points or greater for depression as measured by the PHQ-9 and anxiety as measured for the GAD-8 for both patient populations, with an area under the ROC curve of 0.65 and 0.80 for each respectively. For both PHQ-9 and GAD-7, these AUCs were maintained when predicting significant symptom change at least 7 days in advance. Active data alone predicted around 52% and 75% of the symptom variability for the depression/anxiety and schizophrenia populations respectively. CONCLUSION: These results indicate the feasibility of anomaly detection for predicting symptom change in transdiagnostic cohorts. These results across different patient groups, different countries, and different sites (India and the US) suggest anomaly detection of smartphone digital phenotyping data may offer a reliable and valid approach to predicting symptom change. Future work should emphasize prospective application of these statistical methods.

Digital phenotyping of student mental health during COVID-19: an observational study of 100 college students.

Objective: This study assessed the feasibility of capturing smartphone based digital phenotyping data in college students during the COVID-19 pandemic with the goal of understanding how digital biomarkers of behavior correlate with mental health. Participants: Participants were 100 students enrolled in 4-year universities. Methods: Each participant attended a virtual visit to complete a series of gold-standard mental health assessments, and then used a mobile app for 28 days to complete mood assessments and allow for passive collection of GPS, accelerometer, phone call, and screen time data. Students completed another virtual visit at the end of the study to collect a second round of mental health assessments. Results: In-app daily mood assessments were strongly correlated with their corresponding gold standard clinical assessment. Sleep variance among students was correlated to depression scores (ρ = .28) and stress scores (ρ = .27). Conclusions: Digital Phenotyping among college students is feasible on both an individual and a sample level. Studies with larger sample sizes are necessary to understand population trends, but there are practical applications of the data today.

Enabling Research and Clinical Use of Patient-Generated Health Data (the mindLAMP Platform): Digital Phenotyping Study.

BACKGROUND: There is a growing need for the integration of patient-generated health data (PGHD) into research and clinical care to enable personalized, preventive, and interactive care, but technical and organizational challenges, such as the lack of standards and easy-to-use tools, preclude the effective use of PGHD generated from consumer devices, such as smartphones and wearables. OBJECTIVE: This study outlines how we used mobile apps and semantic web standards such as HTTP 2.0, Representational State Transfer, JSON (JavaScript Object Notation), JSON Schema, Transport Layer Security (version 1.3), Advanced Encryption Standard-256, OpenAPI, HTML5, and Vega, in conjunction with patient and provider feedback to completely update a previous version of mindLAMP. METHODS: The Learn, Assess, Manage, and Prevent (LAMP) platform addresses the abovementioned challenges in enhancing clinical insight by supporting research, data analysis, and implementation efforts around PGHD as an open-source solution with freely accessible and shared code. RESULTS: With a simplified programming interface and novel data representation that captures additional metadata, the LAMP platform enables interoperability with existing Fast Healthcare Interoperability Resources-based health care systems as well as consumer wearables and services such as Apple HealthKit and Google Fit. The companion Cortex data analysis and machine learning toolkit offer robust support for artificial intelligence, behavioral feature extraction, interactive visualizations, and high-performance data processing through parallelization and vectorization techniques. CONCLUSIONS: The LAMP platform incorporates feedback from patients and clinicians alongside a standards-based approach to address these needs and functions across a wide range of use cases through its customizable and flexible components. These range from simple survey-based research to international consortiums capturing multimodal data to simple delivery of mindfulness exercises through personalized, just-in-time adaptive interventions.

Applying machine learning to smartphone based cognitive and sleep assessments in schizophrenia.

BACKGROUND: Cognitive impairment in schizophrenia remains a chief source of functional disability and impairment, despite the potential for effective interventions. This is in part related to a lack of practical and easy to administer screening strategies that can identify and help triage cognitive impairment. This study explores how smartphone-based assessments may help address this need. METHODS: In this study, data was analyzed from 25 subjects with schizophrenia and 30 controls who engaged with a gamified mobile phone version of the Trails-B cognitive assessment in their everyday life over 90 days and complete a clinical neurocognitive testing battery at the beginning and end of the study. Machine learning was applied to the resulting dataset to predict disease status and neurocognitive function and understand which features were most important for accurate prediction. RESULTS: The generated models predicted disease status with high accuracy using static features alone (AUC = 0.94), with the total number of items collected and the total duration of interaction with the application most predictive. The addition of temporal data statistically significantly improved performance (AUC = 0.95), with the amount of idle time a significant new predictor. Correlates of sleep dysfunction were also predicted (AUC = 0.80), with similar feature importance. DISCUSSION: Machine learning enabled the highly accurate identification of subjects with schizophrenia versus healthy controls, and the accurate prediction of neurocognitive function. The addition of temporal data significantly improved the performance of these models, underscoring the value of smartphone-based assessments of cognition as a practical tool for assessing cognition.

Assessing mental health apps marketplaces with objective metrics from 29,190 data points from 278 apps.

OBJECTIVE: Utilizing a standard framework that may help clinicians and patients to identify relevant mental health apps, we sought to gain a comprehensive picture of the space by searching for, downloading, and reviewing 278 mental health apps from both the iOS and Android stores. METHODS: 278 mental health apps from the Apple iOS store and Google Play store were downloaded and reviewed in a standardized manner by trained app raters using a validated framework. Apps were evaluated with this framework comprising 105 questions and covering app origin and accessibility, privacy and security, inputs and outputs, clinical foundation, features and engagement style, and interoperability. RESULTS: Our results confirm that app stars and downloads-even for the most popular apps by these metrics-did not correlate with more clinically relevant metrics related to privacy/security, effectiveness, and engagement. Most mental health apps offer similar functionality, with 16.5% offering both mood tracking and journaling and 7% offering psychoeducation, deep breathing, mindfulness, journaling, and mood tracking. Only 36.4% of apps were updated with a 100-day window, and 7.5% of apps had not been updated in four years. CONCLUSION: Current app marketplace metrics commonly used to evaluate apps do not offer an accurate representation of individual apps or a comprehensive overview of the entire space. The majority of apps overlap in terms of features offered, with many domains and other features not well represented. Selecting an appropriate app continues to require personal matching given no clear trends or guidance offered by quantitative metrics alone.

Anomaly detection to predict relapse risk in schizophrenia.

The integration of technology in clinical care is growing rapidly and has become especially relevant during the global COVID-19 pandemic. Smartphone-based digital phenotyping, or the use of integrated sensors to identify patterns in behavior and symptomatology, has shown potential in detecting subtle moment-to-moment changes. These changes, often referred to as anomalies, represent significant deviations from an individual's baseline, may be useful in informing the risk of relapse in serious mental illness. Our investigation of smartphone-based anomaly detection resulted in 89% sensitivity and 75% specificity for predicting relapse in schizophrenia. These results demonstrate the potential of longitudinal collection of real-time behavior and symptomatology via smartphones and the clinical utility of individualized analysis. Future studies are necessary to explore how specificity can be improved, just-in-time adaptive interventions utilized, and clinical integration achieved.

Changes to the Psychiatric Chatbot Landscape: A Systematic Review of Conversational Agents in Serious Mental Illness: Changements du paysage psychiatrique des chatbots: une revue systématique des agents conversationnels dans la maladie mentale sérieuse.

OBJECTIVE: The need for digital tools in mental health is clear, with insufficient access to mental health services. Conversational agents, also known as chatbots or voice assistants, are digital tools capable of holding natural language conversations. Since our last review in 2018, many new conversational agents and research have emerged, and we aimed to reassess the conversational agent landscape in this updated systematic review. METHODS: A systematic literature search was conducted in January 2020 using the PubMed, Embase, PsychINFO, and Cochrane databases. Studies included were those that involved a conversational agent assessing serious mental illness: major depressive disorder, schizophrenia spectrum disorders, bipolar disorder, or anxiety disorder. RESULTS: Of the 247 references identified from selected databases, 7 studies met inclusion criteria. Overall, there were generally positive experiences with conversational agents in regard to diagnostic quality, therapeutic efficacy, or acceptability. There continues to be, however, a lack of standard measures that allow ease of comparison of studies in this space. There were several populations that lacked representation such as the pediatric population and those with schizophrenia or bipolar disorder. While comparing 2018 to 2020 research offers useful insight into changes and growth, the high degree of heterogeneity between all studies in this space makes direct comparison challenging. CONCLUSIONS: This review revealed few but generally positive outcomes regarding conversational agents' diagnostic quality, therapeutic efficacy, and acceptability, which may augment mental health care. Despite this increase in research activity, there continues to be a lack of standard measures for evaluating conversational agents as well as several neglected populations. We recommend that the standardization of conversational agent studies should include patient adherence and engagement, therapeutic efficacy, and clinician perspectives.

Patient Innovation in Investigating the Effects of Environmental Pollution in Schizophrenia: Case Report of Digital Phenotyping Beyond Apps.

This patient perspective highlights the role of patients in the innovation and codesign of digital mental health technology. Though digital mental health apps have evolved and become highly functional, many still act as data collection silos without adequate support for patients to understand and investigate potentially meaningful inferences in their own data. Few digital health platforms respect the patient's agency and curiosity, allowing the individual to wear the hat of researcher and data scientist and share their experiences and insight with their clinicians. This case is cowritten with an individual with lived experiences of schizophrenia who has decided to openly share their name and experiences to share with others the methods and results of their curiosity and encourage and inspire others to follow their curiosity as well.

Digital Opportunities for Outcomes in Recovery Services (DOORS): A Pragmatic Hands-On Group Approach Toward Increasing Digital Health and Smartphone Competencies, Autonomy, Relatedness, and Alliance for Those With Serious Mental Illness.

Digital health technologies such as smartphones present the potential for increased access to care and on-demand services. However, many patients with serious mental illnesses (eg, schizophrenia) have not been offered the digital health training necessary to fully utilize these innovative approaches. To bridge this digital divide in knowledge and skills, we created a hands-on and interactive training program grounded in self-determination theory, technology use cases, and the therapeutic alliance. This article introduces the need and theoretical foundation for and the experience of running the resulting Digital Opportunities for Outcomes in Recovery Services (DOORS) group in the setting of 2 programs: a first-episode psychosis program and a clubhouse for individuals with serious mental illness. The experience of running these 2 DOORS groups resulted in 2 publicly available, free training manuals to empower others to run such groups and adapt them for local needs. Future work on DOORS will expand the curriculum to best support digital health needs and increase equity of access to and knowledge and skills related to technology use in serious mental illness.

Multiple uses of app instead of using multiple apps - a case for rethinking the digital health technology toolbox.

There are tens of thousands of mental health-related apps available today - representing extreme duplication in this digital age. Instead of a plethora of apps, there is a need for a few that meet the needs of many. Focusing on transparency and free sharing of software, we argue that a collaborative approach towards apps can advance care through creating customisable and future proofed digital tools that allow all stakeholders to engage in their design and use.

Assessing Cognition Outside of the Clinic: Smartphones and Sensors for Cognitive Assessment Across Diverse Psychiatric Disorders.

Traditionally, the assessment of cognition and the administration of cognitive therapies has been performed in the clinic, but with modern technology, this clinic-centric view is changing. This article explores the landscape of digital devices used to measure cognition in settings outside the clinic. These devices range in mobility from user-friendly mobile devices to setting-specific devices able to provide powerful, robust cognitive therapy and living assistance in the comfort of a patient's home. Although these methods remain in early stages of developmental, initial studies suggest they may prove useful in treating patients with serious mental illnesses in a widespread clinical setting.

Proteomic Analysis of 3T3-L1 Adipocytes Treated with Insulin and TNF-α.

Insulin resistance is an indication of early stage Type 2 diabetes (T2D). Insulin resistant adipose tissues contain higher levels of insulin than the physiological level, as well as higher amounts of intracellular tumor necrosis factor-α (TNF-α) and other cytokines. However, the mechanism of insulin resistance remains poorly understood. To better understand the roles played by insulin and TNF-α in insulin resistance, we performed proteomic analysis of differentiated 3T3-L1 adipocytes treated with insulin (Ins), TNF-α (TNF), and both (Ins + TNF). Out of the 693 proteins identified, the abundances of 78 proteins were significantly different (p < 0.05). Carnitine parmitoyltransferase-2 (CPT2), acetyl CoA carboxylase 1 (ACCAC-1), ethylmalonyl CoA decarboxylase (ECHD1), and methylmalonyl CoA isomerase (MCEE), enzymes required for fatty acid ß-oxidation and respiratory electron transport, and ß-glucuronidase, an enzyme responsible for the breakdown of complex carbohydrates, were down-regulated in all the treatment groups, compared to the control group. In contrast, superoxide dismutase 2 (SOD2), protein disulfide isomerase (PDI), and glutathione reductase, which are the proteins responsible for cytoskeletal structure, protein folding, degradation, and oxidative stress responses, were up-regulated. This suggests higher oxidative stress in cells treated with Ins, TNF, or both. We proposed a conceptual metabolic pathway impacted by the treatments and their possible link to insulin resistance or T2D.

Actionable digital phenotyping: a framework for the delivery of just-in-time and longitudinal interventions in clinical healthcare.

Designed to improve health, today numerous wearables and smartphone apps are used by millions across the world. Yet the wealth of data generated from the many sensors on these wearables and smartwatches has not yet transformed routine clinical care. One central reason for this gap between data and clinical insights is the lack of transparency and standards around data generated from mobile device that hinders interoperability and reproducibility. The clinical informatics community has offered solutions via the Fast Healthcare Interoperability Resources (FHIR) standard which facilities electronic health record interoperability but is less developed towards precision temporal contextually-tagged sensor measurements generated from today's ubiquitous mobile devices. In this paper we explore the opportunities and challenges of various theoretical approaches towards FHIR compatible digital phenotyping, and offer a concrete example implementing one such framework as an Application Programming Interface (API) for the open-source mindLAMP platform. We aim to build a community with contributions from statisticians, clinicians, patients, family members, researchers, designers, engineers, and more.

Chatbots and Conversational Agents in Mental Health: A Review of the Psychiatric Landscape.

OBJECTIVE: The aim of this review was to explore the current evidence for conversational agents or chatbots in the field of psychiatry and their role in screening, diagnosis, and treatment of mental illnesses. METHODS: A systematic literature search in June 2018 was conducted in PubMed, EmBase, PsycINFO, Cochrane, Web of Science, and IEEE Xplore. Studies were included that involved a chatbot in a mental health setting focusing on populations with or at high risk of developing depression, anxiety, schizophrenia, bipolar, and substance abuse disorders. RESULTS: From the selected databases, 1466 records were retrieved and 8 studies met the inclusion criteria. Two additional studies were included from reference list screening for a total of 10 included studies. Overall, potential for conversational agents in psychiatric use was reported to be high across all studies. In particular, conversational agents showed potential for benefit in psychoeducation and self-adherence. In addition, satisfaction rating of chatbots was high across all studies, suggesting that they would be an effective and enjoyable tool in psychiatric treatment. CONCLUSION: Preliminary evidence for psychiatric use of chatbots is favourable. However, given the heterogeneity of the reviewed studies, further research with standardized outcomes reporting is required to more thoroughly examine the effectiveness of conversational agents. Regardless, early evidence shows that with the proper approach and research, the mental health field could use conversational agents in psychiatric treatment.

Understanding the quality, effectiveness and attributes of top-rated smartphone health apps.

OBJECTIVE: This study aimed to understand the attributes of popular apps for mental health and comorbid medical conditions, and how these qualities relate to consumer ratings, app quality and classification by the WHO health app classification framework. METHODS: We selected the 10 apps from the Apple iTunes store and the US Android Google Play store on 20 July 2018 from six disease states: depression, anxiety, schizophrenia, addiction, diabetes and hypertension. Each app was downloaded by two authors who provided information on the apps' attributes, functionality, interventions, popularity, scientific backing and WHO app classification rating. RESULTS: A total of 120 apps were examined. Although none of these apps had Food and Drug Administration marketing approval, nearly 50% made claims that appeared medical. Most apps offered a similar type of services with 87.5% assigned WHO classification 1.4.2 'self-monitoring of health or diagnostic data by a client' or 1.6.1 'client look-up of health information'. The 'last updated' attribute was highly correlated with a quality rating of the app although no apps features (eg, uses Global Positioning System, reminders and so on) were. CONCLUSION: Due to the heterogeneity of the apps, we were unable to define a core set of features that would accurately assess app quality. The number of apps making unsupported claims combined with the number of apps offering questionable content warrants a cautious approach by both patients and clinicians in selecting safe and effective ones. CLINICAL IMPLICATIONS: 'Days since last updated' offers a useful and easy clinical screening test for health apps, regardless of the condition being examined.