Showing papers by "John Torous published in 2022"
TL;DR: 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 and offers robust support for artificial intelligence, behavioral feature extraction, interactive visualizations, and high-performance data processing through parallelization and vectorization techniques.
Abstract: 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.
16 citations
TL;DR: In this article , a number of specific adaptations could strengthen current regulatory oversight while promoting ongoing innovation of software as a medical device (SaaS) in order to maximize the potential benefits of these emerging technologies.
Abstract: Abstract Rapid innovation and proliferation of software as a medical device have accelerated the clinical use of digital technologies across a wide array of medical conditions. Current regulatory pathways were developed for traditional (hardware) medical devices and offer a useful structure, but the evolution of digital devices requires concomitant innovation in regulatory approaches to maximize the potential benefits of these emerging technologies. A number of specific adaptations could strengthen current regulatory oversight while promoting ongoing innovation.
13 citations
TL;DR: For instance, this article found that on average, college students' mood, anxiety, and stress symptoms were not influenced by monitoring their mental health on an app and engagement rates were the same for students with higher or lower symptoms, suggesting app monitoring for mental health is feasible even in those who may be more ill.
Abstract: • Engagement rates were the same for students with higher or lower symptoms, suggesting app monitoring for mental health is feasible even in those who may be more ill. • App engagement in college students is associated with offering in app data visualization but not through offering supportive messaging. • On average, college students’ mood, anxiety, and stress symptoms were not influenced by monitoring their mental health on an app.
8 citations
TL;DR: In this paper , the authors used the mindLAMP app for self-reported symptom surveys and found that selfreported symptom survey scores were highly correlated with scores on gold standard clinical assessments (r = 0.80, p = 10-11 for mood and r =0.78, p= 10-12 for anxiety).
7 citations
TL;DR: In this paper , the authors looked at existing randomised controlled trial studies on digital mental health interventions for older adults and found that four factors have been found that contributed to the success of digital health interventions: ease of use, opportunities for social interactions, having human support, and having the digital mental healthcare interventions tailored to the participants' needs.
6 citations
TL;DR: There is a need for more translational research on smartphone apps for eating disorders and current marketplace offerings present risks that may not be balanced by their limited evidence.
Abstract: OBJECTIVE
Apps purporting to assist with the management of eating disorders are proliferating; although less is known about (a) the safety or efficacy of the apps on the marketplaces and (b) if the research evidence supports dissemination of these apps. In this research forum, we seek to synthesize the current data and provide practical considerations around the use and research of these apps.
METHODS
A search of the iOS and Google Play stores was conducted in June 2021 to identify publicly available apps targeting eating disorders. A PubMed search was also conducted in June 2021 to identify relevant publications around smartphone apps for eating disorders.
RESULTS
Sixty-five apps that support the treatment of eating disorders were identified and coded across 105 data points on the publicly available mindApps.org website. The literature search revealed 13 articles. Seven percent of marketplaces apps offered any research support and the 13 published studies focused on only four apps.
DISCUSSION
There is a need for more translational research on smartphone apps for eating disorders. Current marketplace offerings present risks that may not be balanced by their limited evidence. Research efforts should focus on offering evidenced-based apps for the marketplace. Clinicians should weigh known and emerging risks and benefits of these apps within the context of research gaps when making decisions around use.
6 citations
TL;DR: Findings suggest that engagement was underreported and widely varied in RCTs of mobile app-based interventions intended to treat symptoms of depression, and the 5-element framework applied may be useful as a minimum necessary standard for DMHI engagement reporting.
Abstract: Background While many digital mental health interventions (DMHIs) have been found to be efficacious, patient engagement with DMHIs has increasingly emerged as a concern for implementation in real-world clinical settings. To address engagement, we must first understand what standard engagement levels are in the context of randomized controlled trials (RCTs) and how these compare with other treatments. Objective This scoping review aims to examine the state of reporting on intervention engagement in RCTs of mobile app–based interventions intended to treat symptoms of depression. We sought to identify what engagement metrics are and are not routinely reported as well as what the metrics that are reported reflect about standard engagement levels. Methods We conducted a systematic search of 7 databases to identify studies meeting our eligibility criteria, namely, RCTs that evaluated use of a mobile app–based intervention in adults, for which depressive symptoms were a primary outcome of interest. We then extracted 2 kinds of information from each article: intervention details and indices of DMHI engagement. A 5-element framework of minimum necessary DMHI engagement reporting was derived by our team and guided our data extraction. This framework included (1) recommended app use as communicated to participants at enrollment and, when reported, app adherence criteria; (2) rate of intervention uptake among those assigned to the intervention; (3) level of app use metrics reported, specifically number of uses and time spent using the app; (4) duration of app use metrics (ie, weekly use patterns); and (5) number of intervention completers. Results Database searching yielded 2083 unique records. Of these, 22 studies were eligible for inclusion. Only 64% (14/22) of studies included in this review specified rate of intervention uptake. Level of use metrics was only reported in 59% (13/22) of the studies reviewed. Approximately one-quarter of the studies (5/22, 23%) reported duration of use metrics. Only half (11/22, 50%) of the studies reported the number of participants who completed the app-based components of the intervention as intended or other metrics related to completion. Findings in those studies reporting metrics related to intervention completion indicated that between 14.4% and 93.0% of participants randomized to a DMHI condition completed the intervention as intended or according to a specified adherence criteria. Conclusions Findings suggest that engagement was underreported and widely varied. It was not uncommon to see completion rates at or below 50% (11/22) of those participants randomized to a treatment condition or to simply see completion rates not reported at all. This variability in reporting suggests a failure to establish sufficient reporting standards and limits the conclusions that can be drawn about level of engagement with DMHIs. Based on these findings, the 5-element framework applied in this review may be useful as a minimum necessary standard for DMHI engagement reporting.
6 citations
TL;DR: These clinically relevant findings indicate that, rather than uniformly worsening mental health, increased digital engagement may actually provide short-term relief from negative affect in youth with psychiatric comorbidities.
6 citations
TL;DR: The results confirm the conclusion of the above-cited study that patients are at significantly increased risk of psychiatric conditions after a COVID-19 diagnosis, but the degree of increased risk documented in the study is substantially lower than previously found.
6 citations
TL;DR: The differential results from the two sites, namely greater concerns about the cost of mental healthapps among the methadone maintenance treatment cohort and less experience with downloading apps among the older inpatient detoxification cohort, may indicate that clinicians should tailor technological interventions based on local demographics and practice sites.
Abstract: Background In recent years, there has been increasing interest in implementing digital technologies to diagnose, monitor, and intervene in substance use disorders. Smartphones are now a vehicle for facilitating telepsychiatry visits, measuring health metrics, and communicating with health care professionals. In light of the COVID-19 pandemic and the movement toward web-based and hybrid clinic visits and meetings, it has become especially salient to assess phone ownership among individuals with substance use disorders and their comfort in navigating phone functionality and using phones for mental health purposes. Objective The aims of this study were to summarize the current literature around smartphone ownership, smartphone utilization, and the acceptability of using smartphones for mental health purposes and assess these variables across two disparate substance use treatment sites. Methods We performed a focused literature review via a search of two academic databases (PubMed and Google Scholar) for publications since 2007 on the topics of smartphone ownership, smartphone utilization, and the acceptability of using mobile apps for mental health purposes among the substance use population. Additionally, we conducted a cross-sectional survey study that included 51 participants across two sites in New England—an inpatient detoxification unit that predominantly treats patients with alcohol use disorder and an outpatient methadone maintenance treatment clinic. Results Prior studies indicated that mobile phone ownership among the substance use population between 2013 and 2019 ranged from 83% to 94%, while smartphone ownership ranged from 57% to 94%. The results from our study across the two sites indicated 96% (49/51) mobile phone ownership and 92% (47/51) smartphone ownership among the substance use population. Although most (43/49, 88%) patients across both sites reported currently using apps on their phone, a minority (19/48, 40%) reported previously using any apps for mental health purposes. More than half of the participants reported feeling at least neutrally comfortable with a mental health app gathering information regarding appointment reminders (32/48, 67%), medication reminders (33/48, 69%), and symptom surveys (26/45, 58%). Most patients were concerned about privacy (34/51, 67%) and felt uncomfortable with an app gathering location (29/47, 62%) and social (27/47, 57%) information for health care purposes. Conclusions The majority of respondents reported owning a mobile phone (49/51, 96%) and smartphone (47/51, 92%), consistent with prior studies. Many respondents felt comfortable with mental health apps gathering most forms of personal information and with communicating with their clinician about their mental health. The differential results from the two sites, namely greater concerns about the cost of mental health apps among the methadone maintenance treatment cohort and less experience with downloading apps among the older inpatient detoxification cohort, may indicate that clinicians should tailor technological interventions based on local demographics and practice sites and that there is likely not a one-size-fits-all digital psychiatry solution.
5 citations
TL;DR: In this article, the authors review the current domains of technology utilization, describe standards for quality evaluation, and forecast future developments, and examine technology-based assessments of cognition, emotion, functional capacity and everyday functioning, virtual reality approaches to assessment and treatment, ecological momentary assessment, passive measurement strategies including geolocation, movement, and physiological parameters.
Abstract: Technology is ubiquitous in society and is now being extensively used in mental health applications. Both assessment and treatment strategies are being developed and deployed at a rapid pace. The authors review the current domains of technology utilization, describe standards for quality evaluation, and forecast future developments. This review examines technology-based assessments of cognition, emotion, functional capacity and everyday functioning, virtual reality approaches to assessment and treatment, ecological momentary assessment, passive measurement strategies including geolocation, movement, and physiological parameters, and technology-based cognitive and functional skills training. There are many technology-based approaches that are evidence based and are supported through the results of systematic reviews and meta-analyses. Other strategies are less well supported by high-quality evidence at present, but there are evaluation standards that are well articulated at this time. There are some clear challenges in selection of applications for specific conditions, but in several areas, including cognitive training, randomized clinical trials are available to support these interventions. Some of these technology-based interventions have been approved by the U.S. Food and Drug administration, which has clear standards for which types of applications, and which claims about them, need to be reviewed by the agency and which are exempt.
TL;DR: In this paper , the authors evaluated studies on e-mental health for personality disorders published over the last three years (2019-2022) and identified 19 studies, including four randomized controlled trials and one meta-analysis.
Abstract: Provision of mental health services through digital technologies (e-mental health) can potentially expand access to treatments for personality disorders (PDs). We evaluated studies on e-mental health for PDs published over the last 3 years (2019-2022).Studies published in English that used e-mental health to treat people with PDs or PD-related symptoms were identified. We identified 19 studies, including four randomized controlled trials and one meta-analysis. Most interventions were based on Dialectical Behavior Therapy and delivered through smartphone applications for adults with Borderline Personality Disorder [BPD] or related symptoms. User experiences of the interventions were generally positive. Evidence for efficacy was limited. The current literature on e-mental health for PDs is limited in scope. Research in understudied populations and randomized controlled trials designed to establish efficacy are warranted. It is not yet clear whether e-mental health may be helpful for the treatment of PDs.
TL;DR: In this paper , the authors performed a weighted logistic regression analysis to identify sociodemographic predictors of portal usage among those with depression/anxiety and found that significant sociodemic predictors included gender, age, income, race/ethnicity and education level.
TL;DR: The immediate potential as well as concrete steps towards realizing this potential of a new, more personalized, and scalable mental health system are outlined.
Abstract: COVID-19 has accelerated the use of telehealth and technology in mental health care, creating new avenues to increase both access to and quality of care. As video visits and synchronous telehealth become more routine, the field is now on the verge of embracing asynchronous telehealth, with the potential to radically transform mental health. However, sustaining the use of basic synchronous telehealth, let alone embracing asynchronous telehealth, requires new and immediate effort. Programs to increase digital literacy and competencies among both clinicians and patients are now critical to ensure all parties have the knowledge, confidence, and ability to equitably benefit from emerging innovations. This editorial outlines the immediate potential as well as concrete steps toward realizing the potential of a new, more personalized, scalable mental health system.
TL;DR: Representing the largest combined dataset of smartphone digital phenotyping, this work reports on the impact of sampling frequency, active engagement with the app, phone type (Android vs Apple), gender, and study protocol features may have on missingness / data quality.
Abstract: Objectives: Digital phenotyping methods present a scalable tool to realize the potential of personalized medicine. But underlying this potential is the need for digital phenotyping data to represent accurate and precise health measurements. This requires a focus on the data quality of digital phenotyping and assessing the nature of the smartphone data used to derive clinical and health-related features. Design: Retrospective cohorts. Representing the largest combined dataset of smartphone digital phenotyping, we report on the impact of sampling frequency, active engagement with the app, phone type (Android vs Apple), gender, and study protocol features may have on missingness / data quality. Setting: mindLAMP smartphone app digital phenotyping studies run at BIDMC between May 2019 and March 2022. Participants: 1178 people who partook in mindLAMP studies. Main outcome measures: Rates of missing digital phenotyping data. Results: Missingness from sensors in digital phenotyping is related to active user engagement with the app. There are small but notable differences in missingness between phone models and genders. Datasets with high degrees of missingness can generate incorrect behavioral features that may lead to faulty clinical interpretations. Conclusions: Digital phenotyping data quality is a moving target that requires ongoing technical and protocol efforts to minimize missingness. Adding run-in periods, education with hands-on support, and tools to easily monitor data coverage are all productive strategies studies can utilize today.
TL;DR: In this paper , the authors explored correlations between passive data features and survey scores and found that passive data alone may not provide enough information to predict survey scores, augmenting this data with short daily surveys can improve performance.
Abstract: Background Smartphones can facilitate patients completing surveys and collecting sensor data to gain insight into their mental health conditions. However, the utility of sensor data is still being explored. Prior studies have reported a wide range of correlations between passive data and survey scores. Aims To explore correlations in a large data-set collected with the mindLAMP app. Additionally, we explored whether passive data features could be used in models to predict survey results. Method Participants were asked to complete daily and weekly mental health surveys. After screening for data quality, our sample included 147 college student participants and 270 weeks of data. We examined correlations between six weekly surveys and 13 metrics derived from passive data features. Finally, we trained logistic regression models to predict survey scores from passive data with and without daily surveys. Results Similar to other large studies, our correlations were lower than prior reports from smaller studies. We found that the most useful features came from GPS, call, and sleep duration data. Logistic regression models performed poorly with only passive data, but when daily survey scores were included, performance greatly increased. Conclusions Although passive data alone may not provide enough information to predict survey scores, augmenting this data with short daily surveys can improve performance. Therefore, it may be that passive data can be used to refine survey score predictions and clinical utility may be derived from the combination of active and passive data.
TL;DR: In this article , the authors examined the association between excessive screen time and cognitive deficits in youth and found that about one in three (34.1%) adolescents had cognitive difficulties, and 45% of adolescents engaged in excessive screen-time behaviors on an average school day.
Abstract: The widespread use of digital media by young people has generated speculations that their excessive use may have deleterious cognitive effects. Previous studies examining the association between screen time and cognitive deficits in youth have yielded mixed conclusions. We study this association using a nationally representative sample of school going adolescents in the United States. We queried data from the 2017 and 2019 Youth Risk Behavior Survey. An analytic sample of 17,076 adolescents was analyzed using binary logistic regression. Outcome variable was cognitive difficulties (difficulty in concentrating, remembering, or making decisions), and the explanatory variable was excessive screen-time behaviors. Of the 17,076 adolescents, about one in three (34.1%) had cognitive difficulties, and 45% of adolescents engaged in excessive screen-time behaviors on an average school day. After adjusting for covariates, the odds were 1.28 times higher for adolescents who engaged in excessive screen-time behaviors to report serious cognitive difficulties compared to adolescents who did not engage in excessive screen-time behaviors (AOR = 1.28, p < .001, 95% CI = 1.18–1.40). Study results support the association between excessive screen behaviors and cognitive difficulties in adolescence. Findings of this study are discussed with implications for practice and research.
TL;DR: In this article , the authors explored the perceived needs and barriers of patients with schizophrenia, caregivers and clinicians in using digital mental health applications, and generated a multitude of suggestions on app functionality and components.
Abstract: About 3.5 million people are living with schizophrenia in India, with most failing to receive minimally adequate care. Digital mental health applications could potentially decrease this treatment gap; however, these applications should be tailored to meet the needs and overcoming barriers of its end-users to ensure their adoption and sustained usage. Few studies in India have explored the perspectives of target stakeholders to understand how digital tools could be viable for supporting care. Therefore, this study explores the perceived needs and barriers of patients with schizophrenia, caregivers and clinicians in using digital mental health applications.Focus group discussions (FGDs) were conducted with patients having schizophrenia attending outpatient clinics at a government tertiary hospital, and their caregivers, and mental health clinicians in Bhopal, Madhya Pradesh, India. FGDs were audio-recorded and coded. Framework analysis was employed to guide the analysis, involving deductive and inductive generation of themes, data triangulation and comparison of perspectives between participant groups.Six FGDs were conducted with individuals with schizophrenia (n = 11), their caregivers (n = 14), and mental health clinicians (n = 19). Four a priori themes were established: a) Prior experiences with health applications; b) Content of a mental health application; c) Involvement of caregivers in mental health application usage and d) Supporting doctors' work through mental health applications. Additionally, two themes were generated inductively: a) Qualities of a mental health application and b) Data privacy and confidentiality.Exploration of stakeholder perspectives on the content, features, and uses of mental health applications is crucial to yield initial insights about the use of these digital programs in India. This study generated a multitude of suggestions on app functionality and components, which can guide ongoing efforts to develop and deliver digital mental health applications for patients living with schizophrenia in low-resource settings, with limited access to mental health services.
TL;DR: In this article , a review of schizophrenia apps offered on marketplaces and research literature with a focus on accessibility and availability is presented. But, less is known about the current state of schizophrenia applications in research and how those translate to publicly available apps.
Abstract: App-based interventions have the potential to enhance access to and quality of care for patients with schizophrenia. However, less is known about the current state of schizophrenia apps in research and how those translate to publicly available apps. This study, therefore, aimed to review schizophrenia apps offered on marketplaces and research literature with a focus on accessibility and availability. A search of recent reviews, gray literature, PubMed, and Google Scholar was conducted in August 2022. A search of the U.S. Apple App Store and Google Play App Store was conducted in July 2022. All eligible studies and apps were systematically screened/reviewed. The academic research search produced 264 results; 60 eligible studies were identified. 51.7% of research apps were built on psychosis-specific platforms and 48.3% of research apps were built on non-specific platforms. 83.3% of research apps offered monitoring functionalities. Only nine apps, two designed on psychosis-specific platforms and seven on non-specific platforms were easily accessible. The search of app marketplaces uncovered 537 apps; only six eligible marketplace apps were identified. 83.3% of marketplace apps only offered psychoeducation. All marketplace apps lacked frequent updates with the average time since last update 1121 days. There are few clinically relevant apps accessible to patients on the commercial marketplaces. While research efforts are expanding, many research apps are unavailable today. Better translation of apps from research to the marketplace and a focus on sustainable interventions are important targets for the field.
TL;DR: In this article , the authors analyzed data from a 4-week observational digital phenotyping study using the mindLAMP app for 695 college students with elevated stress who specified if they were exposed to COVID-19.
Abstract: The urgency to understand the long-term neuropsychiatric sequala of COVID-19, a part of the Post-Acute COVID-19 Syndrome (PACS), is expanding as millions of infected individuals experience new unexplained symptoms related to mood, anxiety, insomnia, headache, pain, and more. Much research on PACS involves cross sectional surveys which limits ability to understand the dynamic trajectory of this emerging phenomenon. In this secondary analysis, we analyzed data from a 4-week observational digital phenotyping study using the mindLAMP app for 695 college students with elevated stress who specified if they were exposed to COVID-19. Students also completed a biweekly survey of clinical assessments to obtain active data. Additionally, passive data streams like GPS, accelerometer, and screen state were extracted from phone sensors and through features the group built. Three hundred and eighty-second number participants successfully specified their COVID-19 exposure and completed the biweekly survey. From active smartphone data, we found significantly higher scores for the Prodromal Questionnaire (PQ) and the Pittsburgh Sleep Quality Index (PSQI) for students reporting exposure to COVID-19 compared to those who were not (ps < 0.05). Additionally, we found significantly decreased sleep duration as captured from the smartphone via passive data for the COVID-19 exposed group (p < 0.05). No significant differences were detected for other surveys or passive sensors. Smartphones can capture both self-reported symptoms and behavioral changes related to PACS. Our results around changes in sleep highlight how digital phenotyping methods can be used in a scalable and accessible manner toward better capturing the evolving phenomena of PACS. The present study further provides a foundation for future research to implement improving digital phenotyping methods.
TL;DR: For example, this paper conducted a survey of 400 GPs in the United Kingdom to explore their experiences and opinions about the impact on patients and GPs' practices to offer patients full online access to their health records.
Abstract: Background In 2022, NHS England announced plans to ensure that all adult primary care patients in England would have full online access to new data added to their general practitioner (GP) record. However, this plan has not yet been fully implemented. Since April 2020, the GP contract in England has already committed to offering patients full online record access on a prospective basis and on request. However, there has been limited research into UK GPs’ experiences and opinions about this practice innovation. Objective This study aimed to explore the experiences and opinions of GPs in England about patients’ access to their full web-based health record, including clinicians’ free-text summaries of the consultation (so-called “open notes”). Methods In March 2022, using a convenience sample, we administered a web-based mixed methods survey of 400 GPs in the United Kingdom to explore their experiences and opinions about the impact on patients and GPs’ practices to offer patients full online access to their health records. Participants were recruited using the clinician marketing service Doctors.net.uk from registered GPs currently working in England. We conducted a qualitative descriptive analysis of written responses (“comments”) to 4 open-ended questions embedded in a web-based questionnaire. Results Of 400 GPs, 224 (56%) left comments that were classified into 4 major themes: increased strain on GP practices, the potential to harm patients, changes to documentation, and legal concerns. GPs believed that patient access would lead to extra work for them, reduced efficiency, and increased burnout. The participants also believed that access would increase patient anxiety and incur risks to patient safety. Experienced and perceived documentation changes included reduced candor and changes to record functionality. Anticipated legal concerns encompassed fears about increased litigation risks and lack of legal guidance to GPs about how to manage documentation that would be read by patients and potential third parties. Conclusions This study provides timely information on the views of GPs in England regarding patient access to their web-based health records. Overwhelmingly, GPs were skeptical about the benefits of access both for patients and to their practices. These views are similar to those expressed by clinicians in other countries, including Nordic countries and the United States before patient access. The survey was limited by the convenience sample, and it is not possible to infer that our sample was representative of the opinions of GPs in England. More extensive, qualitative research is required to understand the perspectives of patients in England after experiencing access to their web-based records. Finally, further research is needed to explore objective measures of the impact of patient access to their records on health outcomes, clinician workload, and changes to documentation.
TL;DR: In this article , the authors used digital medicine systems (DMSs) to increase medication adherence in patients with severe mental health disorders, which is an important barrier to treatment of psychiatric disorders.
Abstract: Digital medicine systems (DMSs) offer a potential solution to increase medication adherence, which is an important barrier to treatment of psychiatric disorders. In this pilot, we enrolled N = 24 individuals diagnosed with severe mental illness to use an FDA-approved DMS for 5 months. We also collected digital phenotyping smartphone data to study behavioral associations with medication adherence. Our results suggest it is feasible to use the system, and we identified longitudinal associations between adherence and some of the communication-based phenotyping features. Larger studies and a focus on data quality are important next steps for this work.
TL;DR: In this paper , the authors present a study design to explore engagement with mental health apps in college students, using the Technology Acceptance Model as a theoretical framework, and assess the accuracy of predicting mental health changes using digital phenotyping data.
Abstract: Background Smartphone apps that capture surveys and sensors are increasingly being leveraged to collect data on clinical conditions. In mental health, this data could be used to personalize psychiatric support offered by apps so that they are more effective and engaging. Yet today, few mental health apps offer this type of support, often because of challenges associated with accurately predicting users’ actual future mental health. Objective In this protocol, we present a study design to explore engagement with mental health apps in college students, using the Technology Acceptance Model as a theoretical framework, and assess the accuracy of predicting mental health changes using digital phenotyping data. Methods There are two main goals of this study. First, we present a logistic regression model fit on data from a prior study on college students and prospectively test this model on a new student cohort to assess its accuracy. Second, we will provide users with data-driven activity suggestions every 4 days to determine whether this type of personalization will increase engagement or attitudes toward the app compared to those receiving no personalized recommendations. Results The study was completed in the spring of 2022, and the manuscript is currently in review at JMIR Publications. Conclusions This is one of the first digital phenotyping algorithms to be prospectively validated. Overall, our results will inform the potential of digital phenotyping data to serve as tailoring data in adaptive interventions and to increase rates of engagement. International Registered Report Identifier (IRRID) PRR1-10.2196/37954
01 Jan 2022
TL;DR: In this article, the reader can learn how to set goals toward quality outcomes and be efficient while remaining patient-centered using technology, and adapt to technological components and processes used by systems.
Abstract: We continue to increase our exchange of information through health technologies, used to access, disseminate, and analyze information. Clinical informatics is a rapidly expanding area and facilitates patient-centered care as defined by quality, affordability, and timely health care. This chapter covers developments in information systems, electronic health records, electronic communications with patients and staff (e.g., alerts, texts), behavioral health indicators and related digital advances to improve practice and research. The reader can learn how to set goals toward quality outcomes and be efficient while remaining patient-centered using technology, and adapt to technological components and processes used by systems. By grasping how systems are designed and tailored to collect data, clinicians can use technology to inform decisions and facilitate outcomes. Setting priorities involves input from all care participants, as well as technological competencies for the clinician and institutional/organizational. Patient, clinician, and institutional competencies for skills, attitudes, and behaviors can align clinical care, training, and research missions and stimulate quality improvement.
TL;DR: In this article , the authors present a future in which delivery of evidence-based care will reduce the global disease burden of mental health by more than 40% by combining nonspecialist providers with digital interventions with unique potential to expand reach, engagement and effectiveness.
TL;DR: In this article , a cross-sectional study of 578 mental health apps, an app marketplace assessment found that while more apps were collecting passive data, most apps still offered similar foundational features.
Abstract: Key Points Question What do mental health smartphone apps offer patients, how has the app landscape changed, and are app popularity metrics associated with privacy? Findings In this cross-sectional study of 578 mental health apps, an app marketplace assessment found that while more apps were collecting passive data, most apps still offered similar foundational features. There was no statistically significant correlation between privacy scores and star ratings, but there was a weak correlation between privacy scores and app downloads. Meaning These findings suggest that apps on the marketplace offer overlapping features, and metrics such as star ratings or the number of downloads may not provide adequate information about the privacy or efficacy of mental health apps.
TL;DR: As affective variability is a potential indicator of poor outcomes among individuals with mental health conditions, in the future, a brief, mobile assessment of affective responses to social comparisons may be useful for screening among Individuals with schizophrenia.
Abstract: Background Digital tools may help to address social deficits in schizophrenia, particularly those that engage social comparison processes (ie, evaluating oneself relative to others). Yet, little is known about social comparison processes in schizophrenia or how best to capture between- versus within-person variability, which is critical to engaging comparisons in digital interventions. Objective The goals of this pilot study were to (1) better understand affective responses to social comparisons among individuals with schizophrenia, relative to healthy controls, using a validated global self-report measure; and (2) test a new brief, mobile assessment of affective responses to social comparison among individuals with schizophrenia, relative to the full measure. This study was conducted in 2 phases. Methods We first compared self-reported affective responses to social comparisons between individuals with schizophrenia (n=39) and healthy controls (n=38) using a traditional self-report measure, at 2 time points. We examined the temporal stability in responses and differences between groups. We then evaluated the performance of brief, mobile assessment of comparison responses among individuals with schizophrenia, completed over 12 weeks (n=31). Results Individuals with schizophrenia showed greater variability in affective responses to social comparison than controls on traditional measures and completed an average of 7.46 mobile assessments over 12 weeks. Mobile assessments captured within-person variability in affective responses in the natural environment (intraclass correlation coefficients of 0.40-0.60). Average scores for mobile assessments were positively correlated with responses to traditional measures. Conclusions Affective responses to social comparison vary both between and within individuals with schizophrenia and capturing this variability via smartphone surveys shows some evidence of feasibility. As affective variability is a potential indicator of poor outcomes among individuals with mental health conditions, in the future, a brief, mobile assessment of affective responses to social comparisons may be useful for screening among individuals with schizophrenia. Further research on this process is needed to identify when specific comparison messaging may be most effective in digital interventions and could suggest new therapeutic targets for illnesses such as schizophrenia.
TL;DR: In this article , the authors explored patient app engagement patterns and associated clinical outcomes gathered from piloting a digital clinic and found significant differences in the change of both PHQ-9 and GAD-7 depending on participants' average app satisfaction and clinician/coach satisfaction with engagement.
Abstract: Despite the growing prevalence of mental health-related smartphone apps, low real-world engagement has prevented these apps from transforming the mental health landscape. Integrating mental health apps into more traditional therapeutic models appears to support better clinical outcomes, but also raises questions about the relationship between app engagement, the app itself, and the coach or clinician. This study explores patient app engagement patterns and the associated clinical outcomes gathered from piloting a digital clinic. Patients with anxiety or depression completed eight clinical visits and coach visits over a median of 83 days with a standard deviation of 17.25 days. Between clinical visits, patients completed therapeutic activities on the mindLAMP app. Mean PHQ-9 and GAD-7 scores decreased from the intake visit to both visit 4 and visit 8. Patients had high app engagement, but engagement did not correlate with outcomes. From intake visit to visit 4, the interaction effects indicate significant differences in the change of both PHQ-9 and GAD-7 depending on participants' average app satisfaction and clinician/coach satisfaction (as measured by WAI-SR) with engagement. Overall, results support the feasibility of incorporating an app into a hybrid clinic.
TL;DR: In this paper, the authors assess the prospective validity of mental health symptom prediction using the mindLAMP app through a replication study and explore secondary aims around app intervention personalization and correlations of engagement with the Technology Acceptance Model and Digital Working Alliance Inventory scale in the context of automating the study.
Abstract: Background Mental health apps offer a transformative means to increase access to scalable evidence-based care for college students. Yet low rates of engagement currently preclude the effectiveness of these apps. One promising solution is to make these apps more responsive and personalized through digital phenotyping methods able to predict symptoms and offer tailored interventions. Objective Following our protocol and using the exact model shared in that paper, our primary aim in this study is to assess the prospective validity of mental health symptom prediction using the mindLAMP app through a replication study. We also explored secondary aims around app intervention personalization and correlations of engagement with the Technology Acceptance Model (TAM) and Digital Working Alliance Inventory scale in the context of automating the study. Methods The study was 28 days in duration and followed the published protocol, with participants collecting digital phenotyping data and being offered optional scheduled and algorithm-recommended app interventions. Study compensation was tied to the completion of weekly surveys and was not otherwise tied to engagement or use of the app. Results The data from 67 participants were used in this analysis. The area under the curve values for the symptom prediction model ranged from 0.58 for the UCLA Loneliness Scale to 0.71 for the Patient Health Questionnaire-9. Engagement with the scheduled app interventions was high, with a study mean of 73%, but few participants engaged with the optional recommended interventions. The perceived utility of the app in the TAM was higher (P=.01) among those completing at least one recommended intervention. Conclusions Our results suggest how digital phenotyping methods can be used to create generalizable models that may help create more personalized and engaging mental health apps. Automating studies is feasible, and our results suggest targets to increase engagement in future studies. International Registered Report Identifier (IRRID) RR2-10.2196/37954
TL;DR: In this paper , the authors examined rates of wearable devices adoption and identified factors associated with the use and willingness to share WD data among a national sample of adults with depression and/or anxiety in the US.