Correction: Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study.

[This corrects the article DOI: 10.2196/31862.].

Trust of patients and families in mental healthcare providers and institutions: a cross-cultural study in Chennai, India, and Montreal, Canada.

PURPOSE: Cross-cultural psychosis research has typically focused on a limited number of outcomes (generally symptom-related). It is unknown if the purported superior outcomes for psychosis in some low- and middle-income countries extend to fundamental treatment processes like trust. Addressing this gap, we studied two similar first-episode psychosis programs in Montreal, Canada, and Chennai, India. We hypothesized higher trust in healthcare institutions and providers among patients and families in Chennai at baseline and over follow-up. METHODS: Upon treatment entry and at months 3, 12 and 24, trust in healthcare providers was measured using the Wake Forest Trust scale and trust in the healthcare and mental healthcare systems using two single items. Nonparametric tests were performed to compare trust levels across sites and mixed-effects linear regression models to investigate predictors of trust in healthcare providers. RESULTS: The study included 333 patients (Montreal = 165, Chennai = 168) and 324 family members (Montreal = 128, Chennai = 168). Across all timepoints, Chennai patients and families had higher trust in healthcare providers and the healthcare and mental healthcare systems. The effect of site on trust in healthcare providers was significant after controlling for sociodemographic characteristics known to impact trust. Patients' trust in doctors increased over follow-up. CONCLUSION: This study uniquely focuses on trust as an outcome in psychosis, via a comparative longitudinal analysis of different trust dimensions and predictors, across two geographical settings. The consistent differences in trust levels between sites may be attributable to local cultural values and institutional structures and processes and underpin cross-cultural variations in treatment engagement and outcomes.

Subjective quality of life among first-episode psychosis patients in Chennai, India and Montreal, Canada.

Differences in subjective quality of life among persons receiving early intervention for psychosis in varying geo-sociocultural contexts have rarely been examined. Our prospective longitudinal study compared the quality of life of persons with first-episode psychosis receiving two years of similar early intervention in Chennai, India and Montreal, Canada. We hypothesized that general life satisfaction would be higher in Chennai compared to Montreal, and that social relations (a specific quality of life component) would also be higher in Chennai and positively contribute to general life satisfaction. Participants completed the general satisfaction and social relations domains of the Wisconsin Quality of Life Index at baseline, months 12 and 24. Baseline weighted mean general satisfaction and social relations scores were in the low to moderate range. Generalized estimating equation analyses showed that general satisfaction scores increased with time [Wald χ2 (1) = 125.28, p < 0.001] and were higher in Chennai than in Montreal [Wald χ2 (1) = 7.50, p = 0.006]. Social relations scores showed the highest association with general satisfaction scores (B = 0.52), followed by positive symptom remission (B = 0.24) and gender (B = 0.18) with Chennai males having the highest general satisfaction scores. Social relations weighted mean scores increased with time [Wald χ2 (1) = 87.30, p < 0.001] and were positively associated with years of education [Wald χ2 (1) = 4.76, p = 0.029] and early negative symptom remission [Wald χ2 (1) = 7.38, p = 0.007]. Our results suggest that subjective quality of life may improve following early intervention for psychosis across contexts. Our findings advance knowledge about the role of sociocultural (e.g., gender) and clinical factors in influencing subjective outcomes in psychosis, and point to social support networks and symptom remission as avenues to boost quality of life.

Context and Expectations Matter: Social, Recreational, and Independent Functioning among Youth with Psychosis in Chennai, India and Montreal, Canada.

OBJECTIVES: Most cross-cultural psychosis research has focused on a limited number of outcomes (generally symptom-related) and perspectives (often clinician-/observer-rated). It is unknown if the purported superior outcomes for psychosis in some low- and middle-income countries extend to patient-reported measures of social, recreational, and independent functioning. Addressing this gap, this study aimed to compare these outcomes in first-episode psychosis at a high-income site and a lower middle-income site. METHODS: Patients receiving similarly designed early intervention for psychosis in Chennai, India (N = 164) and Montreal, Canada (N = 140) completed the self-reported Social Functioning Scale-Early Intervention, which measures prosocial, recreation, and independence-performance functioning. Their case managers rated expected independence-performance functioning. Both sets of assessments were done at entry and Months 6, 18, and 24. Linear mixed model analyses of differences between sites and over time were conducted, accounting for other pertinent variables, especially negative symptoms. RESULTS: Linear mixed models showed that prosocial, recreation, and independence-performance functioning scores were significantly higher in Montreal than Chennai and did not change over time. Expected independence-performance was also higher in Montreal and increased over time. Negative symptoms and education independently predicted prosocial, recreation, and expected independence-performance functioning. When added to the model, expected independence-performance predicted actual independence-performance and site was no longer significant. At both sites, prosocial and recreation scores were consistently lower (<40%) than independence-performance (40-65%). CONCLUSION: This is the first cross-cultural investigation of prosocial, recreation, and independent functioning in early psychosis. It demonstrates that these outcomes differ by socio-cultural context. Differing levels of expectations about patients, themselves shaped by cultural, illness, and social determinants, may contribute to cross-cultural variations in functional outcomes. At both sites, social, recreational, and independent functioning were in the low-to-moderate range and there was no improvement over time, underscoring the need for effective interventions specifically designed to impact these outcomes.

Trust of patients and families in mental healthcare providers and institutions: A cross-cultural study in Chennai, India and Montreal, Canada.

Purpose: Cross-cultural psychosis research has typically focused on a limited number of outcomes (generally symptom-related). It is unknown if the purported superior outcomes for psychosis in some low- and middle-income countries extend to fundamental treatment processes like trust. Addressing this gap, we studied two similar first-episode psychosis programs in Montreal, Canada and Chennai, India. We hypothesized higher trust in healthcare institutions and providers among patients and families in Chennai at baseline and over follow-up. Methods: Upon treatment entry and at months 3, 12 and 24, trust in healthcare providers was measured using the Wake Forest Trust scale and trust in the healthcare and mental healthcare systems using two single items. Non-parametric tests were performed to compare trust levels across sites and mixed-effects linear regression models to investigate predictors of trust in healthcare providers. Results: The study included 333 patients (Montreal=165, Chennai=168) and 324 family members (Montreal=128, Chennai=168). Across all timepoints, Chennai patients and families had higher trust in healthcare providers and the healthcare and mental healthcare systems. The effect of site on trust in healthcare providers was significant after controlling for sociodemographic characteristics known to impact trust. Patients' trust in doctors increased over follow-up. Conclusion: This study uniquely focuses on trust as an outcome in psychosis, via a comparative longitudinal analysis of different trust dimensions and predictors, across two geographical settings. The consistent differences in trust levels between sites may be attributable to local cultural values and institutional structures and processes and underpin cross-cultural variations in treatment engagement and outcomes.

Predictors of treatment attrition of cognitive health interventions in first episode psychosis.

AIM: Dropping out of psychological interventions is estimated to occur in up to a third of individuals with psychosis. Given the high degree of attrition in this population, identifying predictors of attrition is important to develop strategies to retain individuals in treatment. We observed a particularly high degree of attrition (48%) in a recent randomized controlled study assessing cognitive health interventions for first-episode psychosis participants with comorbid social anxiety. Due to the importance of developing interventions for social anxiety in first episode psychosis, the aim of the present study was to identify putative predictors of attrition through a secondary analysis of data. METHODS: Participants (n = 96) with first episode psychosis and comorbid social anxiety were randomized to receive cognitive behavioural therapy for social anxiety or cognitive remediation. Differences between completers and non-completers (<50% intervention completed) were compared using t-tests or chi-square analyses; statistically significant variables were entered into a multivariate logistic regression model. RESULTS: Non-completers tended to be younger, had fewer years of education and had lower levels of social anxiety compared to completers. Lower baseline social anxiety and younger age were statistically significant predictors of non-completion in the logistic regression model. CONCLUSIONS: Age and social anxiety were predictors of attrition in cognitive health interventions in first episode psychosis populations with comorbid social anxiety. In the ongoing development of social anxiety interventions for this population, future studies should investigate specific engagement strategies, intervention formats and outcome monitoring to improve participant retention in treatment.

Manualized group cognitive behavioral therapy for social anxiety in first-episode psychosis: a randomized controlled trial.

BACKGROUND: Social anxiety (SA), a prevalent comorbid condition in psychotic disorders with a negative impact on functioning, requires adequate intervention relatively early. Using a randomized controlled trial, we tested the efficacy of a group cognitive-behavioral therapy intervention for SA (CBT-SA) that we developed for youth who experienced the first episode of psychosis (FEP). For our primary outcome, we hypothesized that compared to the active control of group cognitive remediation (CR), the CBT-SA group would show a reduction in SA that would be maintained at 3- and 6-month follow-ups. For secondary outcomes, it was hypothesized that the CBT-SA group would show a reduction of positive and negative symptoms and improvements in recovery and functioning. METHOD: Ninety-six patients with an FEP and SA, recruited from five different FEP programs in the Montreal area, were randomized to 13 weekly group sessions of either CBT-SA or CR intervention. RESULTS: Linear mixed models revealed that multiple measures of SA significantly reduced over time, but with no significant group differences. Positive and negative symptoms, as well as functioning improved over time, with negative symptoms and functioning exhibiting a greater reduction in the CBT-SA group. CONCLUSIONS: While SA decreased over time with both interventions, a positive effect of the CBT-SA intervention on measures of negative symptoms, functioning, and self-reported recovery at follow-up suggests that our intervention had a positive effect that extended beyond symptoms specific to SA.ClinicalTrials.gov identifier: NCT02294409.

Treatment with aripiprazole once-monthly injectable formulation is effective in improving symptoms and global functioning in schizophrenia with and without comorbid substance use - a post hoc analysis of the ReLiAM study.

BACKGROUND: ReLiAM, Real-Life Assessment of Abilify Maintena, was the first reported long-term prospective non-interventional study for patients with schizophrenia treated with aripiprazole once-monthly injectable formulation (AOM) under real-life conditions. ReLiAM's primary aim was to evaluate the evolution of global functional status in patients treated with AOM for 12 months in Canada. METHODS: The objective of this post hoc analysis of the ReLiAM study is to investigate the treatment effects of real-life use of AOM over a 1-year period in the subgroup of patients with reported substance use compared with patients without substance use. RESULTS: The results of this post hoc analysis demonstrate that treatment with AOM for 12 months in patients with schizophrenia was comparably effective in improving global functioning in subgroups of patients with and without concomitant substance use. CONCLUSIONS: These results support the use of AOM for the treatment of schizophrenia in patients with or without concomitant substance use. TRIAL REGISTRATION: ClinicalTrials.gov NCT02131415, first posted on May 6, 2014. Overall trial status: Terminated.

The Best Predictor of the Future-the Metaverse, Mental Health, and Lessons Learned From Current Technologies.

The metaverse-a virtual world accessed via virtual reality technology-has been heralded as the next key digital experience. It is meant to provide the next evolution of human interaction after social media and telework. However, in the context of the growing awareness of the risks to mental health posed by current social media technologies, there is a great deal of uncertainty as to the potential effects of this new technology on mental health. This uncertainty is compounded by a lack of clarity regarding what form the metaverse will ultimately take and how widespread its application will be. Despite this, given the nascent state of the metaverse, there is an opportunity to plan the research and regulatory approaches needed to understand it and promote its positive effects while protecting vulnerable groups. In this viewpoint, we examine the following three current technologies whose functions comprise a portion of what the metaverse seeks to accomplish: teleworking, virtual reality, and social media. We attempted to understand in what ways the metaverse may have similar benefits and pitfalls to these technologies but also how it may fundamentally differ from them. These differences suggest potential research questions to be addressed in future work. We found that current technologies have enabled tools such as virtual reality-assisted therapy, avatar therapy, and teletherapy, which have had positive effects on mental health care, and that the metaverse may provide meaningful improvements to these tools. However, given its similarities to social media and its expansion upon the social media experience, the metaverse raises some of the same concerns that we have with social media, such as the possible exacerbation of certain mental health problems. These concerns led us to consider questions such as how the users will be protected and what regulatory mechanisms will be put in place to ensure user safety. Although clear answers to these questions are challenging in this early phase of metaverse research, in this viewpoint, we use the context provided by comparator technologies to provide recommendations to maximize the potential benefits and limit the putative harms of the metaverse. We hope that this paper encourages discussions among researchers and policy makers.

A systematic meta-review of patient-level predictors of psychological therapy outcome in major depressive disorder.

BACKGROUND: Psychological therapies are effective for treating major depressive disorder, but current clinical guidelines do not provide guidance on the personalization of treatment choice. Established predictors of psychotherapy treatment response could help inform machine learning models aimed at predicting individual patient responses to different therapy options. Here we sought to comprehensively identify known predictors. METHODS: EMBASE, Medline, PubMed, PsycINFO were searched for systematic reviews with or without meta-analysis published until June 2020 to identify individual patient-level predictors of response to psychological treatments. 3113 abstracts were identified and 300 articles assessed. We qualitatively synthesized our findings by predictor category (sociodemographic; symptom profile; social support; personality features; affective, cognitive, and behavioural; comorbidities; neuroimaging; genetics) and treatment type. We used the AMSTAR 2 to evaluate the quality of included reviews. RESULTS: Following screening and full-text assessment, 27 systematic reviews including 12 meta-analyses were eligible for inclusion. 74 predictors emerged for various psychological treatments, primarily cognitive behavioural therapy, interpersonal therapy, and mindfulness-based cognitive therapy. LIMITATIONS: A paucity of studies examining predictors of psychological treatment outcome, as well as methodological heterogeneities and publication biases limit the strength of the identified predictors. CONCLUSIONS: The synthesized predictors could be used to supplement clinical decision-making in selecting psychological therapies based on individual patient characteristics. These predictors could also be used as a priori input features for machine learning models aimed at predicting a given patient's likelihood of response to different treatment options for depression, and may contribute toward the development of patient-specific treatment recommendations in clinical guidelines.

An observational study of antipsychotic medication discontinuation in first-episode psychosis: clinical and functional outcomes.

PURPOSE: To study the impact of supervised antipsychotic medication discontinuation on clinical and functional outcomes in first-episode psychosis (FEP) in two different cultural environments. METHOD: FEP patients(N = 253), treated in two early intervention services (Montreal, Canada and Chennai, India) for 2 years, were assessed for medication use, positive and negative symptom remission and social-occupational functioning at regular intervals. RESULTS: Between months 4 and 24 of treatment, 107 patients discontinued medication ('Off'group) as compared to 146 who stayed on medication ('On'group). Medication discontinuation was higher in Chennai as compared to Montreal (n = 80, 49.07% vs n = 27, 16.87%; χ2 37.80, p < 0.001), with no difference in time to discontinuation [Means(SDs) = 10.64(6.82) and 10.04(5.43), respectively, p = 0.71). At month 24 (N = 235), there were no differences in the rate of positive symptom remission between the on and Off groups (81.5 vs 88.0%, respectively) at both sites. The rate of negative symptom remission was lower among patients in the On compared to the Off group (63.2 vs 87.9%, respectively, χ2 = 17.91, p < 0.001), but only in Montreal (55.4% vs 80.0%, respectively, χ2 = 4.12, p < 0.05). Social and Occupational Functioning Assessment Scale scores were equally high in both Off and On medication groups in Chennai [Means (SDs) = 79.43(12.95) and 73.59(17.63), respectively] but higher in the Off compared to the On group in Montreal Means (SDs) = 77.47(14.97) and 64.94(19.02), respectively; Time × site interaction F = 3.96(1,217), p < 0.05]. Medication status (On-Off) had no impact on the outcomes, independent of other variables known to influence outcomes. CONCLUSION: Certain cultural environments and patient characteristics may facilitate supervised discontinuation of antipsychotic medication following treatment of an FEP without negative consequences.

Whose responsibility? Part 2 of 2: views of patients, families, and clinicians about responsibilities for addressing the needs of persons with mental health problems in Chennai, India and Montreal, Canada.

BACKGROUND: Individuals with mental health problems have many insufficiently met support needs. Across sociocultural contexts, various parties (e.g., governments, families, persons with mental health problems) assume responsibility for meeting these needs. However, key stakeholders' opinions of the relative responsibilities of these parties for meeting support needs remain largely unexplored. This is a critical knowledge gap, as these perceptions may influence policy and caregiving decisions. METHODS: Patients with first-episode psychosis (n = 250), their family members (n = 228), and clinicians (n = 50) at two early intervention services in Chennai, India and Montreal, Canada were asked how much responsibility they thought the government versus persons with mental health problems; the government versus families; and families versus persons with mental health problems should bear for meeting seven support needs of persons with mental health problems (e.g., housing; help covering costs of substance use treatment; etc.). Two-way analyses of variance were conducted to examine differences in ratings of responsibility between sites (Chennai, Montreal); raters (patients, families, clinicians); and support needs. RESULTS: Across sites and raters, governments were held most responsible for meeting each support need and all needs together. Montreal raters assigned more responsibility to the government than did Chennai raters. Compared to those in Montreal, Chennai raters assigned more responsibility to families versus persons with mental health problems, except for the costs of substance use treatment. Family raters across sites assigned more responsibility to governments than did patient raters, and more responsibility to families versus persons with mental health problems than did patient and clinician raters. At both sites, governments were assigned less responsibility for addressing housing- and school/work reintegration-related needs compared to other needs. In Chennai, the government was seen as most responsible for stigma reduction and least for covering substance use services. CONCLUSIONS: All stakeholders thought that governments should have substantial responsibility for meeting the needs of individuals with mental health problems, reinforcing calls for greater government investment in mental healthcare across contexts. The greater perceived responsibility of the government in Montreal and of families in Chennai may both reflect and influence differences in cultural norms and healthcare systems in India and Canada.

Whose responsibility? Part 1 of 2: A scale to assess how stakeholders apportion responsibilities for addressing the needs of persons with mental health problems.

BACKGROUND: Individuals with mental health problems have multiple, often inadequately met needs. Responsibility for meeting these needs frequently falls to patients, their families/caregivers, and governments. Little is known about stakeholders' views of who should be responsible for these needs and there are no measures to assess this construct. This study's objectives were to present the newly designed Whose Responsibility Scale (WRS), which assesses how stakeholders apportion responsibility to persons with mental health problems, their families, and the government for addressing various needs of persons with mental health problems, and to report its psychometric properties. METHODS: The 22-item WRS asks respondents to assign relative responsibility to the government versus persons with mental health problems, government versus families, and families versus persons with mental health problems for seven support needs. The items were modelled on a World Values Survey item comparing the government's and people's responsibility for ensuring that everyone is provided for. We administered English, Tamil, and French versions to 57 patients, 60 family members, and 27 clinicians at two early psychosis programs in Chennai, India, and Montreal, Canada, evaluating test-retest reliability, internal consistency, and ease of use. Internal consistency estimates were also calculated for confirmatory purposes with the larger samples from the main comparative study. RESULTS: Test-retest reliability (intra-class correlation coefficients) generally ranged from excellent to fair across stakeholders (patients, families, and clinicians), settings (Montreal and Chennai), and languages (English, French, and Tamil). In the standardization and larger confirmatory samples, internal consistency estimates (Cronbach's alphas) ranged from acceptable to excellent. The WRS scored average on ease of comprehension and completion. Scores were spread across the 1-10 range, suggesting that the scale captured variations in views on how responsibility for meeting needs should be distributed. On select items, scores at one end of the scale were never endorsed, but these reflected expected views about specific needs (e.g., Chennai patients never endorsed patients as being substantially more responsible for housing needs than families). CONCLUSIONS: The WRS is a promising measure for use across geo-cultural contexts to inform mental health policies, and to foster dialogue and accountability among stakeholders about roles and responsibilities. It can help researchers study stakeholders' views about responsibilities, and how these shape and are shaped by sociocultural contexts and mental healthcare systems.

Context and contact: a comparison of patient and family engagement with early intervention services for psychosis in India and Canada.

BACKGROUND: It is unknown whether patient disengagement from early intervention services for psychosis is as prevalent in low- and middle-income countries (LMICs) like India, as it is in high-income countries (HICs). Addressing this gap, we studied two first-episode psychosis programs in Montreal, Canada and Chennai, India. We hypothesized lower service disengagement among patients and higher engagement among families in Chennai, and that family engagement would mediate cross-site differences in patient disengagement. METHODS: Sites were compared on their 2-year patient disengagement and family engagement rates conducting time-to-event analyses and independent samples t tests on monthly contact data. Along with site and family involvement, Cox proportional hazards regression included known predictors of patient disengagement (e.g. gender). RESULTS: The study included data about 333 patients (165 in Montreal, 168 in Chennai) and their family members (156 in Montreal, 168 in Chennai). More Montreal patients (19%) disengaged before 24 months than Chennai patients (1%), χ2(1, N = 333) = 28.87, p < 0.001. Chennai families had more contact with clinicians throughout treatment (Cohen's d = -1.28). Family contact significantly predicted patient disengagement in Montreal (HR = 0.87, 95% CI 0.81-0.93). Unlike in Chennai, family contact declined over time in Montreal, with clinicians perceiving such contact as not necessary (Cohen's d = 1.73). CONCLUSIONS: This is the first investigation of early psychosis service engagement across a HIC and an LMIC. Patient and family engagement was strikingly higher in Chennai. Maintaining family contact may benefit patient engagement, irrespective of context. Findings also suggest that differential service utilization may underpin cross-cultural variations in psychosis outcomes.

Evaluating the perceived utility of an artificial intelligence-powered clinical decision support system for depression treatment using a simulation center.

Aifred is a clinical decision support system (CDSS) that uses artificial intelligence to assist physicians in selecting treatments for major depressive disorder (MDD) by providing probabilities of remission for different treatment options based on patient characteristics. We evaluated the utility of the CDSS as perceived by physicians participating in simulated clinical interactions. Twenty physicians who were either staff or residents in psychiatry or family medicine completed a study in which they had three 10-minute clinical interactions with standardized patients portraying mild, moderate, and severe episodes of MDD. During these scenarios, physicians were given access to the CDSS, which they could use in their treatment decisions. The perceived utility of the CDSS was assessed through self-report questionnaires, scenario observations, and interviews. 60% of physicians perceived the CDSS to be a useful tool in their treatment-selection process, with family physicians perceiving the greatest utility. Moreover, 50% of physicians would use the tool for all patients with depression, with an additional 35% noting that they would reserve the tool for more severe or treatment-resistant patients. Furthermore, clinicians found the tool to be useful in discussing treatment options with patients. The efficacy of this CDSS and its potential to improve treatment outcomes must be further evaluated in clinical trials.

Unfinished business: Functional outcomes in a randomized controlled trial of a three-year extension of early intervention versus regular care following two years of early intervention for psychosis.

OBJECTIVE: To investigate whether first-episode psychosis patients receiving extended early intervention had better functional outcomes than those in regular care and to examine the predictors of functional outcomes. METHODS: This is a randomized controlled single-blind trial of 220 patients randomized after 2 years of early intervention to receive early intervention or regular care for the subsequent 3 years. Outcomes included cumulative time in functional recovery during the 3-year trial assessed using the Social and Occupational Functioning Assessment Scale (SOFAS); and employment/education at last assessment which were, respectively, analyzed using multiple linear regression and logistic regression, accounting for well-known predictors. Linear mixed and generalized linear models were also used to examine the course of SOFAS and employment/education over the 3-year period. RESULTS: The extended early intervention and regular care groups did not differ on time in functional recovery (mean = 50.17 weeks, SD = 46.62 vs. mean = 46.18 weeks, SD = 51.54); percent employed/in school (60.4% vs. 68.8%) or change in SOFAS or employment/education status over time. SOFAS scores were stable between years 2 and 5. Individuals with longer periods of total symptom remission experienced significantly longer periods of functional recovery and were likelier to be employed/in school. Those who had completed high school were nine times likelier to be employed/studying. CONCLUSION: Most individuals maintained functional gains accrued from 2 years of early intervention with no further improvement whether in extended early intervention or regular care. There was a gap between symptomatic and functional recovery, and one-third were unemployed/not in school at year 5. The lack of additional progress even in extended early intervention suggests that specific interventions addressing functional roles need to be provided beyond the first 2 years of early intervention. Sustaining symptom remission and high-school completion may be additional avenues for targeting functional recovery.

Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study.

BACKGROUND: Approximately two-thirds of patients with major depressive disorder do not achieve remission during their first treatment. There has been increasing interest in the use of digital, artificial intelligence-powered clinical decision support systems (CDSSs) to assist physicians in their treatment selection and management, improving the personalization and use of best practices such as measurement-based care. Previous literature shows that for digital mental health tools to be successful, the tool must be easy for patients and physicians to use and feasible within existing clinical workflows. OBJECTIVE: This study aims to examine the feasibility of an artificial intelligence-powered CDSS, which combines the operationalized 2016 Canadian Network for Mood and Anxiety Treatments guidelines with a neural network-based individualized treatment remission prediction. METHODS: Owing to the COVID-19 pandemic, the study was adapted to be completed entirely remotely. A total of 7 physicians recruited outpatients diagnosed with major depressive disorder according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition criteria. Patients completed a minimum of one visit without the CDSS (baseline) and 2 subsequent visits where the CDSS was used by the physician (visits 1 and 2). The primary outcome of interest was change in appointment length after the introduction of the CDSS as a proxy for feasibility. Feasibility and acceptability data were collected through self-report questionnaires and semistructured interviews. RESULTS: Data were collected between January and November 2020. A total of 17 patients were enrolled in the study; of the 17 patients, 14 (82%) completed the study. There was no significant difference in appointment length between visits (introduction of the tool did not increase appointment length; F2,24=0.805; mean squared error 58.08; P=.46). In total, 92% (12/13) of patients and 71% (5/7) of physicians felt that the tool was easy to use; 62% (8/13) of patients and 71% (5/7) of physicians rated that they trusted the CDSS. Of the 13 patients, 6 (46%) felt that the patient-clinician relationship significantly or somewhat improved, whereas 7 (54%) felt that it did not change. CONCLUSIONS: Our findings confirm that the integration of the tool does not significantly increase appointment length and suggest that the CDSS is easy to use and may have positive effects on the patient-physician relationship for some patients. The CDSS is feasible and ready for effectiveness studies. TRIAL REGISTRATION: ClinicalTrials.gov NCT04061642; http://clinicaltrials.gov/ct2/show/NCT04061642.

Using a simulation centre to evaluate preliminary acceptability and impact of an artificial intelligence-powered clinical decision support system for depression treatment on the physician-patient interaction.

BACKGROUND: Recently, artificial intelligence-powered devices have been put forward as potentially powerful tools for the improvement of mental healthcare. An important question is how these devices impact the physician-patient interaction. AIMS: Aifred is an artificial intelligence-powered clinical decision support system (CDSS) for the treatment of major depression. Here, we explore the use of a simulation centre environment in evaluating the usability of Aifred, particularly its impact on the physician-patient interaction. METHOD: Twenty psychiatry and family medicine attending staff and residents were recruited to complete a 2.5-h study at a clinical interaction simulation centre with standardised patients. Each physician had the option of using the CDSS to inform their treatment choice in three 10-min clinical scenarios with standardised patients portraying mild, moderate and severe episodes of major depression. Feasibility and acceptability data were collected through self-report questionnaires, scenario observations, interviews and standardised patient feedback. RESULTS: All 20 participants completed the study. Initial results indicate that the tool was acceptable to clinicians and feasible for use during clinical encounters. Clinicians indicated a willingness to use the tool in real clinical practice, a significant degree of trust in the system's predictions to assist with treatment selection, and reported that the tool helped increase patient understanding of and trust in treatment. The simulation environment allowed for the evaluation of the tool's impact on the physician-patient interaction. CONCLUSIONS: The simulation centre allowed for direct observations of clinician use and impact of the tool on the clinician-patient interaction before clinical studies. It may therefore offer a useful and important environment in the early testing of new technological tools. The present results will inform further tool development and clinician training materials.

Patient satisfaction with random assignment to extended early intervention for psychosis vs regular care: Relationship with service engagement.

AIM: We investigated whether individuals varied in their satisfaction with being randomized to an extension of early intervention (EI) for psychosis or regular care after 2 years of EI, and whether satisfaction was associated with service engagement 3 years later. METHODS: Following randomization, patients (N = 220) indicated if they were happy with, unhappy or indifferent to their group assignment. Follow-up with service providers was recorded monthly. RESULTS: Patients randomized to extended EI were more likely to express satisfaction with their group assignment than those in the regular care group (88.2% vs 31.5%, χ2 = 49.96, P < .001). In the extended EI group, those happy with their assigned group were likelier to continue seeing their case manager for the entire five-year period than those who were unhappy/indifferent (χ2 = 5.61, P = .030). CONCLUSIONS: Perceptions about EI, indicated by satisfaction with being assigned to extended EI, may have lasting effects on service engagement.