Readiness for mHealth interventions in Jordan: Refugee camp and urban community survey.

Jordan hosts one of the largest populations of refugees in the world. This study evaluated the capacity, infrastructure, and interest in mobile health interventions to address unmet mental health needs among refugees and non-refugees in Jordan. We surveyed 209 (141 refugees) adults and youth in urban, rural, and refugee camp settings. Survey results indicated that mobile device ownership was lower among refugees than non-refugees (71 % vs. 100 %, respectively). Refugee phone users had less access to smartphones than non-refugees (75 % vs. 96 %, respectively). Refugees and non-refugees reported using mobile devices for diverse activities including calling (83 % vs. 100 %, respectively), texting (28 % vs. 87 %, respectively) social media (45 % vs. 94 %, respectively), watching videos (23 % vs. 90 %, respectively), and studying (34 % vs. 72 %, respectively). Most respondents had reliable access to electricity (75 % vs. 99 %, respectively) and to mobile-cellular service (67 % vs. 97 %, respectively). Refugees and non-refugees differed substantially in their access to WiFi (14 % vs. 91 %, respectively). Both groups identified anger, anxiety, depression, traumatic memories, and eating problems as the most common mental health problems in their communities. Approximately half of refugees (44 %) and non-refugees (50 %) reported that their communities had insufficient or no access to mental health resources. Most refugees (78 %) and non-refugee (87 %) believed that using mobile devices to provide support for people with mental health conditions would be helpful. Overall, both groups' reported access to mobile technologies and openness to digital mental health treatment options suggest that mHealth interventions may be feasible and welcomed in these communities.

Developing the Workforce of the Digital Future: mHealth Competency and Fidelity Measurement in Community-Based Care.

Integrating mobile health (mHealth) interventions into settings that serve diverse patient populations requires that prerequisite professional competencies are delineated and that standards for clinical quality assurance can be pragmatically assessed. Heretofore, proposed mHealth competencies have been broad and have lacked a framework to support specific applications. We outline the meta-competencies identified in the literature relevant to mHealth interventions and demonstrate how these meta-competencies can be integrated with population- and intervention-related competencies to help guide a pragmatic approach to competency assessment. We present a use case based on FOCUS-an evidence-based mHealth intervention designed for individuals with serious mental illness and currently being implemented in geographically and demographically diverse community behavioral health settings. Subsequent to identifying the cross-cutting competencies relevant to the target population (outpatients experiencing psychotic symptoms), substratal intervention (Cognitive Behavioral Therapy for psychosis), and treatment modality (mHealth), we detail the development process of an mHealth fidelity monitoring system (mHealth-FMS). We adhered to a published sequential 5-step process to design a fidelity monitoring system that aligns with our integrated mHealth competency framework and that was guided by best practices prescribed by the Treatment Fidelity Workgroup of the National Institutes of Health Behavior Change Consortium. The mHealth-FMS is intended to enhance both clinical and implementation outcomes by grounding the mHealth interventionist and the system of care in which they operate in the core functions, tasks, knowledge, and competencies associated with system-integrated mHealth delivery. Future research will explore acceptability and feasibility of the mHealth-FMS.

Combining mHealth Technology and Pharmacotherapy to Improve Mental Health Outcomes and Reduce Human Rights Abuses in West Africa: Intervention Field Trial.

Background: In West Africa, healers greatly outnumber trained mental health professionals. People with serious mental illness (SMI) are often seen by healers in "prayer camps" where they may also experience human rights abuses. We developed "M&M," an 8-week-long dual-pronged intervention involving (1) a smartphone-delivered toolkit designed to expose healers to brief psychosocial interventions and encourage them to preserve human rights (M-Healer app), and (2) a visiting nurse who provides medications to their patients (Mobile Nurse). Objective: We examined the feasibility, acceptability, safety, and preliminary effectiveness of the M&M intervention in real-world prayer camp settings. Methods: We conducted a single-arm field trial of M&M with people with SMI and healers at a prayer camp in Ghana. Healers were provided smartphones with M-Healer installed and were trained by practice facilitators to use the digital toolkit. In parallel, a study nurse visited their prayer camp to administer medications to their patients. Clinical assessors administered study measures to participants with SMI at pretreatment (baseline), midtreatment (4 weeks) and post treatment (8 weeks). Results: Seventeen participants were enrolled and most (n=15, 88.3%) were retained. Participants had an average age of 44.3 (SD 13.9) years and 59% (n=10) of them were male. Fourteen (82%) participants had a diagnosis of schizophrenia and 2 (18%) were diagnosed with bipolar disorder. Four healers were trained to use M-Healer. On average, they self-initiated app use 31.9 (SD 28.9) times per week. Healers watched an average of 19.1 (SD 21.2) videos, responded to 1.5 (SD 2.4) prompts, and used the app for 5.3 (SD 2.7) days weekly. Pre-post analyses revealed a significant and clinically meaningful reduction in psychiatric symptom severity (Brief Psychiatric Rating Scale score range 52.3 to 30.9; Brief Symptom Inventory score range 76.4 to 27.9), psychological distress (Talbieh Brief Distress Inventory score range 37.7 to 16.9), shame (Other as Shamer Scale score range 41.9 to 28.5), and stigma (Brief Internalized Stigma of Mental Illness Scale score range 11.8 to 10.3). We recorded a significant reduction in days chained (1.6 to 0.5) and a promising trend for reduction in the days of forced fasting (2.6 to 0.0, P=.06). We did not identify significant pre-post changes in patient-reported working alliance with healers (Working Alliance Inventory), depressive symptom severity (Patient Health Questionnaire-9), quality of life (Lehman Quality of Life Interview for the Mentally Ill), beliefs about medication (Beliefs about Medications Questionnaire-General Harm subscale), or other human rights abuses. No major side effects, health and safety violations, or serious adverse events occurred over the course of the trial. Conclusions: The M&M intervention proved to be feasible, acceptable, safe, and clinically promising. Preliminary findings suggest that the M-Healer toolkit may have shifted healers' behaviors at the prayer camp so that they commit fewer human rights abuses.

Loneliness in the Daily Lives of People With Mood and Psychotic Disorders.

BACKGROUND AND HYPOTHESIS: Loneliness, the subjective experience of feeling alone, is associated with physical and psychological impairments. While there is an extensive literature linking loneliness to psychopathology, limited work has examined loneliness in daily life in those with serious mental illness. We hypothesized that trait and momentary loneliness would be transdiagnostic and relate to symptoms and measures of daily functioning. STUDY DESIGN: The current study utilized ecological momentary assessment and passive sensing to examine loneliness in those with schizophrenia (N = 59), bipolar disorder (N = 61), unipolar depression (N = 60), remitted unipolar depression (N = 51), and nonclinical comparisons (N = 82) to examine relationships of both trait and momentary loneliness to symptoms and social functioning in daily life. STUDY RESULTS: Findings suggest that both trait and momentary loneliness are higher in those with psychopathology (F(4,284) = 28.00, P < .001, ηp2 = 0.27), and that loneliness significantly relates to social functioning beyond negative symptoms and depression (ß = -0.44, t = 6.40, P < .001). Furthermore, passive sensing measures showed that greater movement (ß = -0.56, t = -3.29, P = .02) and phone calls (ß = -0.22, t = 12.79, P = .04), but not text messaging, were specifically related to decreased loneliness in daily life. Individuals higher in trait loneliness show stronger relationships between momentary loneliness and social context and emotions in everyday life. CONCLUSIONS: These findings provide further evidence pointing to the importance of loneliness transdiagnostically and its strong relation to social functioning. Furthermore, we show that passive sensing technology can be used to measure behaviors related to loneliness in daily life that may point to potential treatment implications or early detection markers of loneliness.

Perception and appropriation of a web-based recovery narratives intervention: qualitative interview study.

Introduction: Mental health recovery narratives are widely available to the public, and can benefit people affected by mental health problems. The NEON Intervention is a novel web-based digital health intervention providing access to the NEON Collection of recovery narratives. The NEON Intervention was found to be effective and cost-effective in the NEON-O Trial for people with nonpsychosis mental health problems (ISRCTN63197153), and has also been evaluated in the NEON Trial for people with psychosis experience (ISRCTN11152837). We aimed to document NEON Intervention experiences, through an integrated process evaluation. Methods: Analysis of interviews with a purposive sample of intervention arm participants who had completed trial participation. Results: We interviewed 34 NEON Trial and 20 NEON-O Trial participants (mean age 40.4 years). Some users accessed narratives through the NEON Intervention almost daily, whilst others used it infrequently or not at all. Motivations for trial participation included: exploring the NEON Intervention as an alternative or addition to existing mental health provision; searching for answers about mental health experiences; developing their practice as a mental health professional (for a subset who were mental health professionals); claiming payment vouchers. High users (10 + narrative accesses) described three forms of appropriation: distracting from difficult mental health experiences; providing an emotional boost; sustaining a sense of having a social support network. Most participants valued the scale of the NEON Collection (n = 659 narratives), but some found it overwhelming. Many felt they could describe the characteristics of a desired narrative that would benefit their mental health. Finding a narrative meeting their desires enhanced engagement, but not finding one reduced engagement. Narratives in the NEON Collection were perceived as authentic if they acknowledged the difficult reality of mental health experiences, appeared to describe real world experiences, and described mental health experiences similar to those of the participant. Discussion: We present recommendations for digital health interventions incorporating collections of digital narratives: (1) make the scale and diversity of the collection visible; (2) provide delivery mechanisms that afford appropriation; (3) enable contributors to produce authentic narratives; (4) enable learning by healthcare professionals; (5) consider use to address loneliness.

Identifying mechanisms of persecutory ideation maintenance with smartphone technology: Examining threat importance, certainty, rumination, and behavior change.

Previous cross-sectional and laboratory research has identified risk factors for persecutory ideation including rumination, negative affect, and safety-seeking behaviors. Questions remain about what in-the-moment factors link general negative affect to PI as well as which maintain PI over time. In the present study, N = 219 individuals completed momentary assessments of PI as well as four factors (attributing threats as certain and important, ruminating, and changing one's behavior in response) proposed to maintain PI over time. Linear mixed effects models were used to analyze multiple time-varying relationships, including these factors predicting negative affect and vice versa, as well as factors predicting maintenance of PI over time. Linear mixed effects models were used to analyze multiple time-varying relationships, examining each PI-related factor predicting negative affect, negative affect predicting each PI-related factor, as well as each factor predicting maintenance of PI over time. All four factors were associated with increases in subsequent day self-reported severity of PI, suggesting all four increased the likelihood of maintaining or worsening next-day PI. Results of this study confirm that the proposed factors are key in maintaining a cycle by which PI and negative affect are maintained over time. These factors may represent targets for momentary interventions.

Mental Health Priorities in the Arab World: Insights From Jordan.

War, geopolitical instability, and natural disasters have contributed to enormous unmet mental health needs in the Middle East and North Africa. Jordan is a middle-income country that needs internal and international stakeholder engagement and support to effectively provide mental health services to its citizens and to the millions of immigrants and refugees who reside there. This column presents a snapshot of the state of mental health care in Jordan and outlines areas for future investment. Potentially high-yield areas for development include digital health technology, integrated care, and youth-focused interventions.

Cost of Implementing mHealth in Community Mental Health Settings: External Versus Internal Facilitation.

OBJECTIVE: This study aimed to compare the costs of two implementation models for the mobile health (mHealth) intervention FOCUS in community mental health settings. The external facilitation (EF) approach uses a hub-and-spoke model, in which a central specialist provides support to clinicians and clients at multiple agencies. With the internal facilitation (IF) approach, frontline clinical staff at each center are trained to serve as their organization's local specialists. METHODS: Financial and economic cost data were collected in the context of a hybrid type 3 effectiveness-implementation trial by using a mixed-methods, top-down expenditure analysis with microcosting approaches. The analysis compared the incremental costs of both models and the costs of successfully engaging clients (N=210) at 20 centers. Costs were characterized as start-up or recurrent (personnel, supplies, contracted services, and indirect costs). RESULTS: The average annual financial cost per site was $23,517 for EF and $19,118 for IF. EF yielded more FOCUS users at each center, such that the average monthly financial costs were lower for EF ($167 per client [N=129]) than for IF ($177 per client [N=81]). When using a real-world scenario based on economic costs and a lower organizational indirect rate, the average monthly cost per client was $73 for EF and $59 for IF. Both models reflected substantial cost reductions (about 50%) relative to a previous deployment of FOCUS in a clinical trial. CONCLUSIONS: Compared with IF, EF yielded more clients who received mHealth at community mental health centers and had comparable or lower costs.

User-Centered Development of Bolster, an mHealth Intervention for Early Psychosis Caregivers: Needs Assessment, Prototyping, and Field Trial.

BACKGROUND: Caregivers play a critical role in the treatment and recovery of youth and young adults at risk for psychosis. Caregivers often report feeling isolated, overwhelmed, and lacking in resources. Mobile health (mHealth) has the potential to provide scalable, accessible, and in-the-moment support to caregivers. To date, few if any mHealth resources have been developed specifically for this population. OBJECTIVE: The aim of this study was to conduct user-centered design and testing of an mHealth intervention to support early psychosis caregivers. METHODS: We conducted a multiphase user-centered development process to develop the Bolster mobile app. In phase 1, a total of 21 caregivers were recruited to participate in a qualitative needs assessment and respond to an initial prototype of the Bolster platform. Content analysis was used to identify key needs and design objectives, which guided the development of the Bolster mobile app. In phase 2, a total of 11 caregivers were recruited to participate in a 1-week field trial wherein they provided qualitative and quantitative feedback regarding the usability and acceptability of Bolster; in addition, they provided baseline and posttest assessments of the measures of distress, illness appraisals, and family communication. RESULTS: In phase 1, participants identified psychoeducation, communication coaching, a guide to seeking services, and support for coping as areas to address. Live prototype interaction sessions led to multiple design objectives, including ensuring that messages from the platform were actionable and tailored to the caregiver experience, delivering messages in multiple modalities (eg, video and text), and eliminating a messaging-style interface. These conclusions were used to develop the final version of Bolster tested in the field trial. In phase 2, of the 11 caregivers, 10 (91%) reported that they would use Bolster if they had access to it and would recommend it to another caregiver. They also reported marked changes in their appraisals of illness (Cohen d=0.55-0.68), distress (Cohen d=1.77), and expressed emotion (Cohen d=0.52). CONCLUSIONS: To our knowledge, this study is the first to design an mHealth intervention specifically for early psychosis caregivers. Preliminary data suggest that Bolster is usable, acceptable, and promising to improve key targets and outcomes. A future fully powered clinical trial will help determine whether mHealth can reduce caregiver burdens and increase engagement in services among individuals affected by psychosis.

Using Smartphones to Identify Momentary Characteristics of Persecutory Ideation Associated With Functional Disability.

Objectives: Though often a feature of schizophrenia-spectrum disorders, persecutory ideation (PI) is also common in other psychiatric disorders as well as among individuals who are otherwise healthy. Emerging technologies allow for a more thorough understanding of the momentary phenomenological characteristics that determine whether PI leads to significant distress and dysfunction. This study aims to identify the momentary phenomenological features of PI associated with distress, dysfunction, and need for clinical care. Methods: A total of 231 individuals with at least moderate PI from 43 US states participated in a study involving 30 days of data collection using a smartphone data collection system combining ecological momentary assessment and passive sensors, wherein they reported on occurrence of PI as well as related appraisals, responses, and cooccurring states. Most (N = 120, 51.9%) participants reported never having received treatment for their PI, while 50 participants had received inpatient treatment (21.6%), and 60 (26.4%) had received outpatient care only. Results: Individuals with greater functional disability did not differ in PI frequency but were more likely at the moment to describe threats as important to them, to ruminate about those threats, to experience distress related to them, and to change their behavior in response. Groups based on treatment-seeking patterns largely did not differ in baseline measures or momentary phenomenology of PI as assessed by self-report or passive sensors. Conclusions: Smartphone data collection allows for granular assessment of PI-related phenomena. Functional disability is associated with differences in appraisals of and responses to PI at the moment.

Dissociation of Cognitive Effort-Based Decision Making and Its Associations With Symptoms, Cognition, and Everyday Life Function Across Schizophrenia, Bipolar Disorder, and Depression.

BACKGROUND: Anhedonia and amotivation are symptoms of many different mental health disorders that are frequently associated with functional disability, but it is not clear whether the same processes contribute to motivational impairments across disorders. This study focused on one possible factor, the willingness to exert cognitive effort, referred to as cognitive effort-cost decision making. METHODS: We examined performance on the deck choice task as a measure of cognitive effort-cost decision making, in which people choose to complete an easy task for a small monetary reward or a harder task for larger rewards, in 5 groups: healthy control (n = 80), schizophrenia/schizoaffective disorder (n = 50), bipolar disorder with psychosis (n = 58), current major depression (n = 60), and past major depression (n = 51). We examined cognitive effort-cost decision making in relation to clinician and self-reported motivation symptoms, working memory and cognitive control performance, and life function measured by ecological momentary assessment and passive sensing. RESULTS: We found a significant diagnostic group × reward interaction (F8,588 = 4.37, p < .001, ηp2 = 0.056). Compared with the healthy control group, the schizophrenia/schizoaffective and bipolar disorder groups, but not the current or past major depressive disorder groups, showed a reduced willingness to exert effort at the higher reward values. In the schizophrenia/schizoaffective and bipolar disorder groups, but not the major depressive disorder groups, reduced willingness to exert cognitive effort for higher rewards was associated with greater clinician-rated motivation impairments, worse working memory and cognitive control performance, and less engagement in goal-directed activities measured by ecological momentary assessment. CONCLUSIONS: These findings suggest that the mechanisms contributing to motivational impairments differ among individuals with psychosis spectrum disorders versus depression.

Relapse prevention through health technology program reduces hospitalization in schizophrenia.

BACKGROUND: Psychiatric hospitalization is a major driver of cost in the treatment of schizophrenia. Here, we asked whether a technology-enhanced approach to relapse prevention could reduce days spent in a hospital after discharge. METHODS: The Improving Care and Reducing Cost (ICRC) study was a quasi-experimental clinical trial in outpatients with schizophrenia conducted between 26 February 2013 and 17 April 2015 at 10 different sites in the USA in an outpatient setting. Patients were between 18 and 60 years old with a diagnosis of schizophrenia, schizoaffective disorder, or psychotic disorder not otherwise specified. Patients received usual care or a technology-enhanced relapse prevention program during a 6-month period after discharge. The health technology program included in-person, individualized relapse prevention planning with treatments delivered via smartphones and computers, as well as a web-based prescriber decision support program. The main outcome measure was days spent in a psychiatric hospital during 6 months after discharge. RESULTS: The study included 462 patients, of which 438 had complete baseline data and were thus used for propensity matching and analysis. Control participants (N = 89; 37 females) were enrolled first and received usual care for relapse prevention followed by 349 participants (128 females) who received technology-enhanced relapse prevention. During 6-month follow-up, 43% of control and 24% of intervention participants were hospitalized (χ2 = 11.76, p<0.001). Days of hospitalization were reduced by 5 days (mean days: b = -4.58, 95% CI -9.03 to -0.13, p = 0.044) in the intervention condition compared to control. CONCLUSIONS: These results suggest that technology-enhanced relapse prevention is an effective and feasible way to reduce rehospitalization days among patients with schizophrenia.

Automated Detection of Cognitive Distortions in Text Exchanges Between Clinicians and People With Serious Mental Illness.

OBJECTIVE: The authors tested whether natural language processing (NLP) methods can detect and classify cognitive distortions in text messages between clinicians and people with serious mental illness as effectively as clinically trained human raters. METHODS: Text messages (N=7,354) were collected from 39 clients in a randomized controlled trial of a 12-week texting intervention. Clinical annotators labeled messages for common cognitive distortions: mental filtering, jumping to conclusions, catastrophizing, "should" statements, and overgeneralizing. Multiple NLP classification methods were applied to the same messages, and performance was compared. RESULTS: A tuned model that used bidirectional encoder representations from transformers (F1=0.62) achieved performance comparable to that of clinical raters in classifying texts with any distortion (F1=0.63) and superior to that of other models. CONCLUSIONS: NLP methods can be used to effectively detect and classify cognitive distortions in text exchanges, and they have the potential to inform scalable automated tools for clinical support during message-based care for people with serious mental illness.

The relationship between appraisals of auditory verbal hallucinations and real-time affect and social functioning.

In addition to being a hallmark symptom of schizophrenia-spectrum disorders, auditory verbal hallucinations (AVH) are present in a range of psychiatric disorders as well as among individuals who are otherwise healthy. People who experience AVH are heterogeneous, and research has aimed to better understand what characteristics distinguish, among those who experience AVH, those who experience significant disruption and distress from those who do not. The cognitive model of AVH suggests that appraisals of voices determine the extent to which voices cause distress and social dysfunction. Previous work has relied largely on comparisons of "clinical" and "non-clinical" voice hearers, and few studies have been able to provide insight into the moment-to-moment relationships between appraisals and outcomes. The current study examines longitudinal data provided through ecological momentary assessment and passive sensors of 465 individuals who experience cross-diagnostic AVH. Results demonstrated associations of AVH appraisals to negative affect and social functioning. Above and beyond within-individual averages, when a participant reported increased appraisals of their voices as powerful and difficult to control, they were more likely to feel increased negative affect and reduced feelings of safety. AVH power appraisals were also associated with next-day number and duration of phone calls placed, and AVH controllability appraisals were associated with increased time near speech and reduced next-day time away from primary location. These results suggest that appraisals are state-like characteristics linked with day-to-day and moment-to-moment changes in impactful affective and behavioral outcomes; intervention approaches should aim to address these domains in real-time.

Developing the Workforce of the Digital Future: Leveraging Technology to Train Community-Based Mobile Mental Health Specialists.

Challenges in training, dissemination, and implementation have impeded the ability of providers to integrate promising digital health tools in real-world services. There is a need for generalizable strategies to rapidly train real-world providers at scale to support the adoption of digital health. This study describes the development of principles guiding rapid training of community-based clinicians in the support of digital health. This training approach was developed in the context of an ongoing trial examining implementation strategies for FOCUS, a mobile mental health intervention designed for people with serious mental illness. The SAIL (Simple, Accessible, Inverted, Live) model introduces how digital tools can be leveraged to facilitate rapid training of community agency-based personnel to serve as digital mental health champions, promoters, and providers. This model emphasizes simple and flexible principles of intervention delivery, accessible materials in a virtual learning environment, inverted or "flipped" live training structure, and live consultation calls for ongoing support. These initial insights lay the groundwork for future work to test and replicate generalizable training strategies focused on real-world delivery of digital mental health services. These strategies have the potential to remove key obstacles to the implementation and dissemination of digital health interventions for mental health.

Predicting Psychotic Relapse in Schizophrenia With Mobile Sensor Data: Routine Cluster Analysis.

BACKGROUND: Behavioral representations obtained from mobile sensing data can be helpful for the prediction of an oncoming psychotic relapse in patients with schizophrenia and the delivery of timely interventions to mitigate such relapse. OBJECTIVE: In this study, we aim to develop clustering models to obtain behavioral representations from continuous multimodal mobile sensing data for relapse prediction tasks. The identified clusters can represent different routine behavioral trends related to daily living of patients and atypical behavioral trends associated with impending relapse. METHODS: We used the mobile sensing data obtained from the CrossCheck project for our analysis. Continuous data from six different mobile sensing-based modalities (ambient light, sound, conversation, acceleration, etc) obtained from 63 patients with schizophrenia, each monitored for up to a year, were used for the clustering models and relapse prediction evaluation. Two clustering models, Gaussian mixture model (GMM) and partition around medoids (PAM), were used to obtain behavioral representations from the mobile sensing data. These models have different notions of similarity between behaviors as represented by the mobile sensing data, and thus, provide different behavioral characterizations. The features obtained from the clustering models were used to train and evaluate a personalized relapse prediction model using balanced random forest. The personalization was performed by identifying optimal features for a given patient based on a personalization subset consisting of other patients of similar age. RESULTS: The clusters identified using the GMM and PAM models were found to represent different behavioral patterns (such as clusters representing sedentary days, active days but with low communication, etc). Although GMM-based models better characterized routine behaviors by discovering dense clusters with low cluster spread, some other identified clusters had a larger cluster spread, likely indicating heterogeneous behavioral characterizations. On the other hand, PAM model-based clusters had lower variability of cluster spread, indicating more homogeneous behavioral characterization in the obtained clusters. Significant changes near the relapse periods were observed in the obtained behavioral representation features from the clustering models. The clustering model-based features, together with other features characterizing the mobile sensing data, resulted in an F2 score of 0.23 for the relapse prediction task in a leave-one-patient-out evaluation setting. The obtained F2 score was significantly higher than that of a random classification baseline with an average F2 score of 0.042. CONCLUSIONS: Mobile sensing can capture behavioral trends using different sensing modalities. Clustering of the daily mobile sensing data may help discover routine and atypical behavioral trends. In this study, we used GMM-based and PAM-based cluster models to obtain behavioral trends in patients with schizophrenia. The features derived from the cluster models were found to be predictive for detecting an oncoming psychotic relapse. Such relapse prediction models can be helpful in enabling timely interventions.

Fully automated detection of formal thought disorder with Time-series Augmented Representations for Detection of Incoherent Speech (TARDIS).

Formal thought disorder (ThD) is a clinical sign of schizophrenia amongst other serious mental health conditions. ThD can be recognized by observing incoherent speech - speech in which it is difficult to perceive connections between successive utterances and lacks a clear global theme. Automated assessment of the coherence of speech in patients with schizophrenia has been an active area of research for over a decade, in an effort to develop an objective and reliable instrument through which to quantify ThD. However, this work has largely been conducted in controlled settings using structured interviews and depended upon manual transcription services to render audio recordings amenable to computational analysis. In this paper, we present an evaluation of such automated methods in the context of a fully automated system using Automated Speech Recognition (ASR) in place of a manual transcription service, with "audio diaries" collected in naturalistic settings from participants experiencing Auditory Verbal Hallucinations (AVH). We show that performance lost due to ASR errors can often be restored through the application of Time-Series Augmented Representations for Detection of Incoherent Speech (TARDIS), a novel approach that involves treating the sequence of coherence scores from a transcript as a time-series, providing features for machine learning. With ASR, TARDIS improves average AUC across coherence metrics for detection of severe ThD by 0.09; average correlation with human-labeled derailment scores by 0.10; and average correlation between coherence estimates from manual and ASR-derived transcripts by 0.29. In addition, TARDIS improves the agreement between coherence estimates from manual transcripts and human judgment and correlation with self-reported estimates of AVH symptom severity. As such, TARDIS eliminates a fundamental barrier to the deployment of automated methods to detect linguistic indicators of ThD to monitor and improve clinical care in serious mental illness.

FOCUS mHealth Intervention for Veterans With Serious Mental Illness in an Outpatient Department of Veterans Affairs Setting: Feasibility, Acceptability, and Usability Study.

BACKGROUND: Veterans with serious mental illnesses (SMIs) face barriers to accessing in-person evidence-based interventions that improve illness management. Mobile health (mHealth) has been demonstrated to be feasible, acceptable, effective, and engaging among individuals with SMIs in community mental health settings. mHealth for SMIs has not been tested within the Department of Veterans Affairs (VA). OBJECTIVE: This study examines the feasibility, acceptability, and preliminary effectiveness of an mHealth intervention for SMI in the context of VA outpatient care. METHODS: A total of 17 veterans with SMIs were enrolled in a 1-month pilot trial of FOCUS, a smartphone-based self-management intervention for SMI. At baseline and posttest, they completed measures examining symptoms and functional recovery. The participants provided qualitative feedback related to the usability and acceptability of the intervention. RESULTS: Veterans completed on an average of 85.0 (SD 96.1) interactions with FOCUS over the 1-month intervention period. They reported high satisfaction, usability, and acceptability, with nearly all participants (16/17, 94%) reporting that they would recommend the intervention to a fellow veteran. Clinicians consistently reported finding mHealth-related updates useful for informing their care. Qualitative feedback indicated that veterans thought mHealth complemented their existing VA services well and described potential opportunities to adapt FOCUS to specific subpopulations (eg, combat veterans) as well as specific delivery modalities (eg, groups). In the 1-month period, the participants experienced small improvements in self-assessed recovery, auditory hallucinations, and quality of life. CONCLUSIONS: The FOCUS mHealth intervention is feasible, acceptable, and usable among veterans. Future work should develop and examine VA-specific implementation approaches of FOCUS for this population.

A Smartphone Intervention for People With Serious Mental Illness: Fully Remote Randomized Controlled Trial of CORE.

BACKGROUND: People with serious mental illness (SMI) have significant unmet mental health needs. Development and testing of digital interventions that can alleviate the suffering of people with SMI is a public health priority. OBJECTIVE: The aim of this study is to conduct a fully remote randomized waitlist-controlled trial of CORE, a smartphone intervention that comprises daily exercises designed to promote reassessment of dysfunctional beliefs in multiple domains. METHODS: Individuals were recruited via the web using Google and Facebook advertisements. Enrolled participants were randomized into either active intervention or waitlist control groups. Participants completed the Beck Depression Inventory-Second Edition (BDI-II), Generalized Anxiety Disorder-7 (GAD-7), Hamilton Program for Schizophrenia Voices, Green Paranoid Thought Scale, Recovery Assessment Scale (RAS), Rosenberg Self-Esteem Scale (RSES), Friendship Scale, and Sheehan Disability Scale (SDS) at baseline (T1), 30-day (T2), and 60-day (T3) assessment points. Participants in the active group used CORE from T1 to T2, and participants in the waitlist group used CORE from T2 to T3. Both groups completed usability and accessibility measures after they concluded their intervention periods. RESULTS: Overall, 315 individuals from 45 states participated in this study. The sample comprised individuals with self-reported bipolar disorder (111/315, 35.2%), major depressive disorder (136/315, 43.2%), and schizophrenia or schizoaffective disorder (68/315, 21.6%) who displayed moderate to severe symptoms and disability levels at baseline. Participants rated CORE as highly usable and acceptable. Intent-to-treat analyses showed significant treatment×time interactions for the BDI-II (F1,313=13.38; P<.001), GAD-7 (F1,313=5.87; P=.01), RAS (F1,313=23.42; P<.001), RSES (F1,313=19.28; P<.001), and SDS (F1,313=10.73; P=.001). Large effects were observed for the BDI-II (d=0.58), RAS (d=0.61), and RSES (d=0.64); a moderate effect size was observed for the SDS (d=0.44), and a small effect size was observed for the GAD-7 (d=0.20). Similar changes in outcome measures were later observed in the waitlist control group participants following crossover after they received CORE (T2 to T3). Approximately 41.5% (64/154) of participants in the active group and 60.2% (97/161) of participants in the waitlist group were retained at T2, and 33.1% (51/154) of participants in the active group and 40.3% (65/161) of participants in the waitlist group were retained at T3. CONCLUSIONS: We successfully recruited, screened, randomized, treated, and assessed a geographically dispersed sample of participants with SMI entirely via the web, demonstrating that fully remote clinical trials are feasible in this population; however, study retention remains challenging. CORE showed promise as a usable, acceptable, and effective tool for reducing the severity of psychiatric symptoms and disability while improving recovery and self-esteem. Rapid adoption and real-world dissemination of evidence-based mobile health interventions such as CORE are needed if we are to shorten the science-to-service gap and address the significant unmet mental health needs of people with SMI during the COVID-19 pandemic and beyond. TRIAL REGISTRATION: ClinicalTrials.gov NCT04068467; https://clinicaltrials.gov/ct2/show/NCT04068467.