Large language models could change the future of behavioral healthcare: a proposal for responsible development and evaluation.

Large language models (LLMs) such as Open AI's GPT-4 (which power ChatGPT) and Google's Gemini, built on artificial intelligence, hold immense potential to support, augment, or even eventually automate psychotherapy. Enthusiasm about such applications is mounting in the field as well as industry. These developments promise to address insufficient mental healthcare system capacity and scale individual access to personalized treatments. However, clinical psychology is an uncommonly high stakes application domain for AI systems, as responsible and evidence-based therapy requires nuanced expertise. This paper provides a roadmap for the ambitious yet responsible application of clinical LLMs in psychotherapy. First, a technical overview of clinical LLMs is presented. Second, the stages of integration of LLMs into psychotherapy are discussed while highlighting parallels to the development of autonomous vehicle technology. Third, potential applications of LLMs in clinical care, training, and research are discussed, highlighting areas of risk given the complex nature of psychotherapy. Fourth, recommendations for the responsible development and evaluation of clinical LLMs are provided, which include centering clinical science, involving robust interdisciplinary collaboration, and attending to issues like assessment, risk detection, transparency, and bias. Lastly, a vision is outlined for how LLMs might enable a new generation of studies of evidence-based interventions at scale, and how these studies may challenge assumptions about psychotherapy.

Mental Health Apps for Children and Adolescents: A Clinician-Friendly Review.

Mobile apps for mental health and wellness (MH apps) have the potential to support youth mental health, expanding access to the large proportion of youth with mental health concerns who do not access formal treatment. Survey data suggest that young people are highly interested in MH apps, with minoritized youth (eg, LGBTQ individuals) and youth with elevated depressive symptoms reporting especially high rates of downloading MH apps.1 In addition, systematic reviews and meta-analyses suggest that MH apps can be effective.2 Although many popular MH apps do not have direct empirical evidence supporting their efficacy,3 they often include elements of empirically supported treatments for children and adolescents.4 The MH app space moves at a fast pace, making it difficult to stay up-to-date. More than 10,000 MH apps exist, with hundreds released each year.5 Even interested clinicians may, understandably, not have time to sort through the large number of apps, scientific papers, and app directories. Furthermore, these resources are rarely designed to offer clear, actionable advice for clinicians. Clinicians could benefit from information and guidance to help patients safely navigate MH apps and to best use MH apps in treatment. Here, we provide 3 key points about youth MH apps ("takeaways"), each with an actionable implication for clinicians ("action items"). We also provide examples of specific questions for clinicians to support their use of MH apps with children and adolescents (Table 1). More information regarding where we derived these recommendations is available in Supplement 1, available online.

A transdiagnostic, dimensional classification of anxiety shows improved parsimony and predictive noninferiority to DSM.

The current conceptualization of anxiety in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5)-which includes 11 anxiety disorders plus additional anxiety-related conditions-does not align with accumulating evidence that anxiety is transdiagnostic and dimensional in nature. Transdiagnostic dimensional anxiety models have been proposed, yet they measure anxiety at either a very broad (e.g., "anxiety") or very narrow (e.g., "performance anxiety") level, overlooking intermediate properties of anxiety that cut across DSM disorders. Using indicators from a well-validated semistructured interview of anxiety-related disorders, we constructed intermediate-level transdiagnostic dimensions representing the intensity, avoidance, pervasiveness, and onset of anxiety. We captured these content-agnostic dimensions in a sample representing varying levels and forms of anxiety (N = 268), including individuals with generalized anxiety disorder, social anxiety disorder, panic disorder, agoraphobia, specific phobia, separation anxiety disorder, posttraumatic stress disorder, and obsessive-compulsive disorder (n = 205) and individuals with no psychopathology (n = 63). In preregistered analyses, our dimensional anxiety model showed noninferiority to DSM-5 diagnoses in predicting concurrent and prospective measures of anxiety-related impairment, anxiety vulnerabilities, comorbid depression, and suicidal ideation. These results held regardless of whether the dimensions were combined into a single composite or retained as separate components. Our transdiagnostic dimensional model offers meaningful gains in parsimony over DSM, with no loss of predictive power. This project provides a methodological framework for the empirical evaluation of other transdiagnostic dimensional models of psychopathology that have been proposed as alternatives to the DSM. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Depression and anxiety symptoms, subjective well-being, and happiness among Indian high school students.

Background: Mental health problems cause significant distress and impairment in adolescents worldwide. One-fifth of the world's adolescents live in India, and much remains to be known about their mental health and wellbeing. Aim: In this preregistered study, we aimed to estimate the rates of depressive and anxiety symptoms, examine their relationship with indicators of wellbeing, and identify correlates of mental health among Indian adolescents. Methods: We administered self-report measures of depressive symptoms (PHQ-9), anxiety symptoms (GAD-7), wellbeing (WEMWBS), and happiness (SHS) to 1,213 Indian adolescents (52.0% male; Mage = 14.11, SDage = 1.48). Results: Findings from the PHQ-9 (M = 8.08, SD = 5.01) and GAD-7 (M = 7.42, SD = 4.78) indicated high levels of depressive symptoms and anxiety symptoms. Thirty seven percent of the sample scored above the clinical cutoff for depressive symptoms, and 30.6% scored above the cutoff for anxiety symptoms. Although measures of mental health symptoms (PHQ-9 and GAD-7) were associated with measures of wellbeing and happiness (WEMWBS and SHS), these associations were only modest (Correlation < 0.45). Female students reported higher symptoms (and worse wellbeing) compared to male students, and older students reported higher symptoms (and worse wellbeing and happiness) compared to younger students. Conclusion: This study highlights the high prevalence of depressive symptoms and anxiety symptoms among Indian high school students. Symptom measures correlated only modestly with measures of wellbeing and happiness, suggesting that wellbeing and happiness reflect more than the absence of internalizing symptoms. Future research is needed to identify effective and appropriate ways to promote mental health and wellness among Indian students.

The development and internal evaluation of a predictive model to identify for whom Mindfulness-Based Cognitive Therapy (MBCT) offers superior relapse prevention for recurrent depression versus maintenance antidepressant medication.

Depression is highly recurrent, even following successful pharmacological and/or psychological intervention. We aimed to develop clinical prediction models to inform adults with recurrent depression choosing between antidepressant medication (ADM) maintenance or switching to Mindfulness-Based Cognitive Therapy (MBCT). Using data from the PREVENT trial (N=424), we constructed prognostic models using elastic net regression that combined demographic, clinical and psychological factors to predict relapse at 24 months under ADM or MBCT. Only the ADM model (discrimination performance: AUC=.68) predicted relapse better than baseline depression severity (AUC=.54; one-tailed DeLong's test: z=2.8, p=.003). Individuals with the poorest ADM prognoses who switched to MBCT had better outcomes compared to those who maintained ADM (48% vs. 70% relapse, respectively; superior survival times [z=-2.7, p=.008]). For individuals with moderate-to-good ADM prognosis, both treatments resulted in similar likelihood of relapse. If replicated, the results suggest that predictive modeling can inform clinical decision-making around relapse prevention in recurrent depression.

Which Symptoms of Depression and Anxiety Matter Most? An Investigation of Subjective Importance Ratings With College Students in India.

One goal of clinical psychological science is to help people with problems that matter to them. However, little is known about which kinds of symptoms are viewed as most important, particularly among individuals in non-western settings. We examined the extent to which young adults in India rated individual symptoms of depression and anxiety as important, concerning, and undesirable. Participants were college students at Indian Universities (n = 283). They received a measure of depressive symptoms (Patient Health Questionnaire-9) and anxiety symptoms (Generalized Anxiety Disorder Screener-7). For each of the 16 symptoms, they provided three judgments relating to the extent to which they found the symptom important, harmful, and undesirable. These judgments were averaged to form a "subjective importance rating" (SIR) for each symptom. Anxiety symptoms were viewed as more important than depressive symptoms (d = 0.34), and nonsomatic symptoms were viewed as more important than somatic symptoms (d = 0.83). Females rated symptoms as more important than males (d = 0.32), and individuals with higher self-reported symptoms rated symptoms as more important. Sad mood, suicidal ideation, and controlling worries were rated as the most important symptoms, whereas concentration problems, appetite problems, and psychomotor problems were rated as the least important. Overall, some symptoms are viewed as more important and concerning than others. We discuss how this understanding can affect our conceptualization, assessment, and treatment of mental disorders around the world.

Socioeconomic Indicators of Treatment Prognosis for Adults With Depression: A Systematic Review and Individual Patient Data Meta-analysis.

Importance: Socioeconomic factors are associated with the prevalence of depression, but their associations with prognosis are unknown. Understanding this association would aid in the clinical management of depression. Objective: To determine whether employment status, financial strain, housing status, and educational attainment inform prognosis for adults treated for depression in primary care, independent of treatment and after accounting for clinical prognostic factors. Data Sources: The Embase, International Pharmaceutical Abstracts, MEDLINE, PsycINFO, and Cochrane (CENTRAL) databases were searched from database inception to October 8, 2021. Study Selection: Inclusion criteria were as follows: randomized clinical trials that used the Revised Clinical Interview Schedule (CIS-R; the most common comprehensive screening and diagnostic measure of depressive and anxiety symptoms in primary care randomized clinical trials), measured socioeconomic factors at baseline, and sampled patients with unipolar depression who sought treatment for depression from general physicians/practitioners or who scored 12 or more points on the CIS-R. Exclusion criteria included patients with depression secondary to a personality or psychotic disorder or neurologic condition, studies of bipolar or psychotic depression, studies that included children or adolescents, and feasibility studies. Studies were independently assessed against inclusion and exclusion criteria by 2 reviewers. Data Extraction and Synthesis: Data were extracted and cleaned by data managers for each included study, further cleaned by multiple reviewers, and cross-checked by study chief investigators. Risk of bias and quality were assessed using the Quality in Prognosis Studies (QUIPS) and Grading of Recommendations, Assessment, Development and Evaluation (GRADE) tools, respectively. This study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses-Individual Participant Data (PRISMA-IPD) reporting guidelines. Main Outcomes and Measures: Depressive symptoms at 3 to 4 months after baseline. Results: This systematic review and individual patient data meta-analysis identified 9 eligible studies that provided individual patient data for 4864 patients (mean [SD] age, 42.5 (14.0) years; 3279 women [67.4%]). The 2-stage random-effects meta-analysis end point depressive symptom scale scores were 28% (95% CI, 20%-36%) higher for unemployed patients than for employed patients and 18% (95% CI, 6%-30%) lower for patients who were homeowners than for patients living with family or friends, in hostels, or homeless, which were equivalent to 4.2 points (95% CI, 3.6-6.2 points) and 2.9 points (95% CI, 1.1-4.9 points) on the Beck Depression Inventory II, respectively. Financial strain and educational attainment were associated with prognosis independent of treatment, but unlike employment and housing status, there was little evidence of associations after adjusting for clinical prognostic factors. Conclusions and Relevance: Results of this systematic review and meta-analysis revealed that unemployment was associated with a poor prognosis whereas home ownership was associated with improved prognosis. These differences were clinically important and independent of the type of treatment received. Interventions that address employment or housing difficulties could improve outcomes for patients with depression.

Improving Mental Health on College Campuses: Perspectives of Indian College Students.

The mental health of college students is increasingly viewed as an important public health priority. However, there has been little attention paid specifically to college students' perspectives on factors that contribute to mental health challenges or on potential initiatives that could address them. Even less research has focused on students in low- and middle-income countries. In an effort to better understand how to improve mental health and wellness on college campuses, we administered an open-ended survey to 141 Indian college students (Mage = 19.47, 65% female). We asked the students to identify: (a) issues that contribute to mental health problems among college students, (b) potential initiatives or strategies that could be used to improve mental health and wellness, and (c) topics that students would like to learn about in a course about mental health and wellness. Applying thematic analysis, we identified academic stressors (e.g., pressure to succeed, competitiveness) and social stressors (e.g., lack of community, party culture and substance abuse) that students reported as contributors to mental health problems. Students also described mental health promotion strategies that could be implemented by faculty members (e.g., providing academic accommodations for students with mental health concerns), the student body (e.g., establishing peer counseling groups), and individual students (e.g., checking in with others). Finally, they identified topics that they would like to learn about in mental health and wellness courses (e.g., how to identify mental health concerns, how to support friends). By raising several potential targets for mental health and wellness interventions for Indian college students, our study illustrates how open-ended surveys can be a useful and feasible way to solicit input from stakeholders in low- and middle-income countries. Future research will be needed to assess the effectiveness and feasibility of mental health promotion strategies, including those proposed by students.

Mapping Female Patients' Judgments of Satisfaction to Hypothetical Changes in Depression Symptom Severity.

Within mental health, approaches to determine whether a patient experienced "meaningful" change from treatment have predominantly involved imposing thresholds on three types of metrics derived from assessments of symptom severity: end score (posttreatment score), absolute change (pre- minus posttreatment score), and proportion of change. However, none of these approaches have considered input from the consumer. This study examined correspondences between various reductions from pre- to posttreatment symptom severity levels and patients' judgments of satisfaction with change. Former or currently depressed patients were asked to provide judgments of their satisfaction reflected in vignettes that used descriptions from the Hamilton Rating Scale for Depression. Judgments from 108 female participants were fit using four metrics: end score, absolute change, proportion of change, and the combination of end score and absolute change. Akaike information criteria (AICs) and Akaike weights were used to determine the best-fitting model. Cutoffs were calculated for the five levels of satisfaction with change. Proportion of change best accounted for variation in the patients' ratings. For "slightly … ," "somewhat … ," "moderately … ," and "very … ," the proportions of reduction that corresponded with each of these ratings of satisfaction were, respectively: 17%, 39%, 62%, and 84%. Our a priori level of satisfaction (between "somewhat" and "moderately") corresponded to a 50% reduction in pretreatment severity. This study may provide services some insight into their female patients' satisfaction with change from treatment for depression using only the proportion of reduction from pretreatment severity. A similar procedure could be applied to other diagnostic groups, as well as other constructs that attend to the patient's perspective.

Individual differences in response to once versus twice weekly sessions of CBT and IPT for depression.

OBJECTIVE: The Personalized Advantage Index (PAI) is a method to guide treatment selection by investigating which of two or more treatments is optimal for a given individual. Recently, it was shown that, on average, twice-weekly sessions of psychotherapy for depression lead to better outcomes compared to once-weekly sessions. The present study applied the PAI method to assess if subgroups of patients may have a differential response to psychotherapy frequency. METHOD: Data came from a clinical trial (n = 200) randomizing depressed patients into different session frequencies: weekly sessions versus twice-weekly sessions. Machine-learning techniques were used to select pretreatment variables and develop a multivariable prediction model that calculated each patient's PAI. Differences in observed depression post-treatment scores (Beck Depression Inventory-II [BDI-II]) were tested between patients that received their PAI-indicated versus non-indicated session frequency. Between-group effect sizes (Cohen's d) were reported. RESULTS: We identified prognostic indicators generally associated with lower post-treatment BDI-II regardless of treatment assignment. In addition, we identified specific demographic and psychometric features associated with differential response to weekly- versus twice-weekly therapy sessions. Observed post-treatment BDI-II scores were significantly different between individuals receiving the PAI-indicated versus non-indicated session frequency (d = .37). CONCLUSIONS: Although a higher session frequency is more effective on average, different session frequencies seem beneficial for different patients. Future studies should externally validate these findings before they can be generalized to other settings. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Patients' judgments of the importance of treatment-induced reductions in symptoms of depression: The role of specific symptoms, magnitudes of change, and post-treatment levels.

Objective: An implicit assumption in the use of depressive severity measures to assess change during treatment, such as the Hamilton Rating Scale for Depression (HRSD), is that reductions from pre- to post-treatment that are equal to each other are of equal value. However, stakeholders' valuations of changes might depart substantially from this assumption. Method: Vignettes were constructed that reflected the six possible 1, 2, and 3-point reductions on five cognitive and four somatic symptoms derived from the HRSD. Former or currently depressed patients provided judgments of the importance of the symptom reductions. Mean importance ratings were modeled using symptom category and the pre/post-treatment combination. Differences were explored using the Tukey method. Results: Results indicated that mean ratings, from most to least important, were: Anxiety, Suicide, Depressed Mood, Work, and Guilt (the cognitive symptoms) followed by Somatic, Sleep, Appetite & Weight, and Retardation (the somatic symptoms). Participants valued reductions that resulted in posttreatment scores of zero more than expected, given the magnitude of the reductions. Conclusions: The value of reductions in symptoms captured by the HRSD, as judged by patients, appears to differ as a function of symptom category and the post-treatment score. Similar patterns might characterize other measures of depression severity.

Stratified Care vs Stepped Care for Depression: A Cluster Randomized Clinical Trial.

Importance: Depression is a major cause of disability worldwide. Although empirically supported treatments are available, there is scarce evidence on how to effectively personalize psychological treatment selection. Objective: To compare the clinical effectiveness and cost-effectiveness of 2 treatment selection strategies: stepped care and stratified care. Design, Setting, and Participants: This multisite, cluster randomized clinical trial recruited participants from the English National Health Service from July 5, 2018, to February 1, 2019. Thirty clinicians working across 4 psychological therapy services were randomly assigned to provide stratified (n = 15) or stepped (n = 15) care. In stepped care, patients sequentially access low-intensity guided self-help followed by high-intensity psychotherapy. In stratified care, patients are matched with either low- or high-intensity treatments at initial assessment. Data were analyzed from May 18, 2020, to October 13, 2021, using intention-to-treat principles. Interventions: All clinicians used the same interview schedule to conduct initial assessments with patients seeking psychological treatment for common mental disorders, but those in the stratified care group received a personalized treatment recommendation for each patient generated by a machine learning algorithm. Eligible patients received either stratified or stepped care (ie, treatment as usual). Main Outcomes and Measures: The preregistered outcome was posttreatment reliable and clinically significant improvement (RCSI) of depression symptoms (measured using the 9-item Patient Health Questionnaire). The RCSI outcome was compared between groups using logistic regression adjusted for baseline severity. Cost-effectiveness analyses compared incremental costs and health outcomes of the 2 treatment pathways. Results: A total of 951 patients were included (618 women among 950 with data available [65.1%]; mean [SD] age, 38.27 [14.53] years). The proportion of cases of RCSI was significantly higher in the stratified care arm compared with the stepped care arm (264 of 505 [52.3%] vs 134 of 297 [45.1%]; odds ratio, 1.40 [95% CI, 1.04-1.87]; P = .03). Stratified care was associated with a higher mean additional cost per patient (£104.5 [95% CI, £67.5-£141.6] [$139.83 (95% CI, $90.32-$189.48)]; P < .001) because more patients accessed high-intensity treatments (332 of 583 [56.9%] vs 107 of 368 [29.1%]; χ2 = 70.51; P < .001), but this additional cost resulted in an approximately 7% increase in the probability of RCSI. Conclusions and Relevance: In this cluster randomized clinical trial of adults with common mental disorders, stratified care was efficacious and cost-effective for the treatment of depression symptoms compared with stepped care. Stratified care can improve depression treatment outcomes at a modest additional cost. Trial Registration: isrctn.org Identifier: ISRCTN11106183.

Emotion regulation strategy correlates with discrete state emotion in major depression.

BACKGROUND AND OBJECTIVES: Research has shown that state emotion can affect emotion regulation strategies in healthy samples. Emotion regulation plays an important role in depression. We hypothesized that for depressed individuals, experiencing anxiety or anger affects emotion regulation strategy use differently than experiencing sadness. DESIGN AND METHODS: Individuals diagnosed with chronic or recurrent depression (N = 386) responded to vignettes of hypothetical stressors and reported their state emotions and emotion regulation strategies in a thought-listing procedure. We modeled the effect of reporting anger or anxiety compared to sadness on the use of seven emotion regulation strategies: avoidance, distraction, other-blame, problem-solving, rumination, self-blame, and social support. RESULTS: Compared to sadness, anger was associated with a greater likelihood of using other-blame, and a lower likelihood of using avoidance, rumination, or self-blame. Compared to sadness, anxiety was associated with a greater likelihood of using self-blame. Responses with anger or anxiety did not significantly differ from sadness in coder-rated adaptiveness. CONCLUSIONS: Differences in observed emotion regulation strategy use were correlated with the discrete emotions experienced, and not overall adaptiveness of a response. These results highlight the importance of assessing for emotion type when studying emotion regulation strategy use in depression.

Life events and treatment prognosis for depression: A systematic review and individual patient data meta-analysis.

OBJECTIVE: To investigate associations between major life events and prognosis independent of treatment type: (1) after adjusting for clinical prognostic factors and socio-demographics; (2) amongst patients with depressive episodes at least six-months long; and (3) patients with a first life-time depressive episode. METHODS: Six RCTs of adults seeking treatment for depression in primary care met eligibility criteria, individual patient data (IPD) were collated from all six (n = 2858). Participants were randomized to any treatment and completed the same baseline assessment of life events, demographics and clinical prognostic factors. Two-stage random effects meta-analyses were conducted. RESULTS: Reporting any major life events was associated with poorer prognosis regardless of treatment type. Controlling for baseline clinical factors, socio-demographics and social support resulted in minimal residual evidence of associations between life events and treatment prognosis. However, removing factors that might mediate the relationships between life events and outcomes reporting: arguments/disputes, problem debt, violent crime, losing one's job, and three or more life events were associated with considerably worse prognoses (percentage difference in 3-4 months depressive symptoms compared to no reported life events =30.3%(95%CI: 18.4-43.3)). CONCLUSIONS: Assessing for clinical prognostic factors, social support, and socio-demographics is likely to be more informative for prognosis than assessing self-reported recent major life events. However, clinicians might find it useful to ask about such events, and if they are still affecting the patient, consider interventions to tackle problems related to those events (e.g. employment support, mediation, or debt advice). Further investigations of the efficacy of such interventions will be important.

A Patient Stratification Approach to Identifying the Likelihood of Continued Chronic Depression and Relapse Following Treatment for Depression.

BACKGROUND: Subgrouping methods have the potential to support treatment decision making for patients with depression. Such approaches have not been used to study the continued course of depression or likelihood of relapse following treatment. METHOD: Data from individual participants of seven randomised controlled trials were analysed. Latent profile analysis was used to identify subgroups based on baseline characteristics. Associations between profiles and odds of both continued chronic depression and relapse up to one year post-treatment were explored. Differences in outcomes were investigated within profiles for those treated with antidepressants, psychological therapy, and usual care. RESULTS: Seven profiles were identified; profiles with higher symptom severity and long durations of both anxiety and depression at baseline were at higher risk of relapse and of chronic depression. Members of profile five (likely long durations of depression and anxiety, moderately-severe symptoms, and past antidepressant use) appeared to have better outcomes with psychological therapies: antidepressants vs. psychological therapies (OR (95% CI) for relapse = 2.92 (1.24-6.87), chronic course = 2.27 (1.27-4.06)) and usual care vs. psychological therapies (relapse = 2.51 (1.16-5.40), chronic course = 1.98 (1.16-3.37)). CONCLUSIONS: Profiles at greater risk of poor outcomes could benefit from more intensive treatment and frequent monitoring. Patients in profile five may benefit more from psychological therapies than other treatments.

Which symptoms of depression and anxiety are most strongly associated with happiness? A network analysis of Indian and Kenyan adolescents.

BACKGROUND: Network analyses have been applied to understand the relationships between individual symptoms of depression and anxiety. However, little is known about which symptoms are most strongly associated with "positive" indicators of mental health, such as happiness. Furthermore, few studies have examined symptom networks in participants from low- and middle-income countries. METHODS: To address these gaps, we applied network analyses in a sample of Indian adolescents (Study 1; n=1080) and replicated these analyses in a pre-registered study with Kenyan adolescents (Study 2; n=2176). Participants from both samples completed the same measures of depressive symptoms, anxiety symptoms, and happiness. RESULTS: Feeling sad and feeling like a failure had the strongest (negative) associations with happiness items. These two symptoms, as well as worrying and feeling nervous, had the strongest associations with other symptoms of depression and anxiety. Symptoms of depression and anxiety formed a single cluster, which was distinct from a cluster of happiness items. Main findings were consistent across the two samples, suggesting a cross-culturally robust pattern. LIMITATIONS: We used cross-sectional data, and we administered scales assessing a limited subset of symptoms and happiness items. CONCLUSIONS: Our findings support the idea that some symptoms of depression and anxiety are more strongly associated with happiness. These findings contribute to a body of literature emphasizing the advantages of symptom-level analyses. We discuss how efforts to understand associations between individual symptoms and "positive" mental health indicators, like happiness, could have theoretical and practical implications for clinical psychological science.

Economic evaluation of an online single-session intervention for depression in Kenyan adolescents.

Objective: To evaluate the costs and cost-effectiveness of Shamiri-Digital, an online single-session intervention (SSI) for depression among Kenyan adolescents. Method: Data were drawn from a randomized clinical trial with n = 103 Kenyan high school students (64% female, Mage = 15.5). All students were eligible to participate, regardless of baseline depression symptomatology. We estimated delivery costs in 2020 U.S. dollars from multiple perspectives. To account for uncertainty, we performed sensitivity analyses with different cost assumptions and definitions of effectiveness. Using number needed to treat (NNT) estimates, we also evaluated the cost required to achieve a clinically meaningful reduction in depressive symptoms. Results: In the base-case (the most realistic cost estimate), it costs U.S. $3.57 per student to deliver Shamiri-Digital. Depending on the definition of clinically meaningful improvement, 7.1-9.7 students needed to receive the intervention for one student to experience a clinically meaningful improvement, which translated to a cost of U.S. $25.35 to U.S. $34.62 per student. Under a worst-case scenario (i.e., assuming the highest treatment cost and the strictest effectiveness definition), the cost to achieve clinically meaningful improvement was U.S. $92.05 per student. Conclusions: Shamiri-Digital is a low-cost intervention for reducing depression symptomatology. The public health benefit of empirically supported SSIs is especially important in low-income countries, where funding for mental health care is most limited. Future research can compare the cost-effectiveness of online SSIs to higher-cost treatments and estimate the robustness of Shamiri-Digital's effects over a longer time horizon. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Online single-session interventions for Kenyan adolescents: study protocol for a comparative effectiveness randomised controlled trial.

BACKGROUND: Mental health problems are the leading cause of disability among adolescents worldwide, yet access to treatment is limited. Brief digital interventions have been shown to improve youth mental health, but little is known about which digital interventions are most effective. AIMS: To evaluate the effectiveness of two digital single-session interventions (Shamiri-Digital and Digital-CBT (cognitive-behavioural therapy)) among Kenyan adolescents. METHODS: We will perform a school-based comparative effectiveness randomised controlled trial. Approximately 926 Kenyan adolescents will be randomly assigned to one of three conditions: Shamiri-Digital (focused on gratitude, growth mindsets and values), Digital-CBT (focused on behavioural activation, cognitive restructuring and problem solving) or a study-skills control condition (focused on note-taking and essay writing skills). The primary outcomes include depressive symptoms (measured by the Patient Health Questionnaire-8), anxiety symptoms (Generalized Anxiety Disorder Screener-7) and subjective well-being (Short Warwick-Edinburgh Mental Well-being Scale). The secondary outcomes include acceptability, appropriateness, primary control and secondary control. Acceptability and appropriateness will be measured immediately post-intervention; other outcomes will be measured 2 weeks, 4 weeks and 12 weeks post-intervention. RESULTS: We hypothesise that adolescents assigned to Shamiri-Digital and adolescents assigned to Digital-CBT will experience greater improvements (assessed via hierarchical linear models) than those assigned to the control group. We will also compare Shamiri-Digital with Digital-CBT, although we do not have a preplanned hypothesis. CONCLUSIONS: Our findings will help us evaluate two digital single-session interventions with different theoretical foundations. If effective, such interventions could be disseminated to reduce the public health burden of common mental health problems. TRIAL REGISTRATION NUMBER: PACTR202011691886690.

Evaluating the Effectiveness of Personalized Medicine With Software.

We present methodological advances in understanding the effectiveness of personalized medicine models and supply easy-to-use open-source software. Personalized medicine involves the systematic use of individual patient characteristics to determine which treatment option is most likely to result in a better average outcome for the patient. Why is personalized medicine not done more in practice? One of many reasons is because practitioners do not have any easy way to holistically evaluate whether their personalization procedure does better than the standard of care, termed improvement. Our software, "Personalized Treatment Evaluator" (the R package PTE), provides inference for improvement out-of-sample in many clinical scenarios. We also extend current methodology by allowing evaluation of improvement in the case where the endpoint is binary or survival. In the software, the practitioner inputs 1) data from a single-stage randomized trial with one continuous, incidence or survival endpoint and 2) an educated guess of a functional form of a model for the endpoint constructed from domain knowledge. The bootstrap is then employed on data unseen during model fitting to provide confidence intervals for the improvement for the average future patient (assuming future patients are similar to the patients in the trial). One may also test against a null scenario where the hypothesized personalization are not more useful than a standard of care. We demonstrate our method's promise on simulated data as well as on data from a randomized comparative trial investigating two treatments for depression.