Development, Feasibility and Effectiveness of a Digital Support Platform for Mental Health in Primary Care (PRESTO).

Overview

The prevalence of mental health disorders in Primary Care (PC) largely exceeds the limited resources available. The main aim of this project is to develop a comprehensive machine learning (ML) digital support platform (PRESTO) to approach people with mental health symptoms in PC. PRESTO will offer a transdiagnostic triage of those cases needing specialized care while most of the mild and moderate cases with anxiety and depressive symptoms will be allocated through ML models to either: 1.a periodic follow-up, 2.symptoms monitoring and brief psychological intervention with a smartphone app, or 3.a specific psychopharmacological treatment. To reach this objective, first, a ML predictive severity model will be build based on all the cases referred to the PC mental health support programme during the last 5 years retrieved from electronic health records from 5 PC centres(PCC) in Barcelona. Simultaneously, a smartphone app (PRESTOapp) monitoring symptoms and delivering a psychological intervention for non-severe anxious and depressive symptomatology will be developed and tested in a feasibility study and in a randomized clinical trial. Finally, the ML models obtained from the first phase of the project and the data from the PRESTOapp study will be integrated in a comprehensive self-learning web platform which will triage and assign to each case a specific intervention based on the predicted outcome. The effectiveness of PRESTO to reduce waiting times in receiving appropriate and specific care of mental health problems will be tested by means of a stepped-wedge randomized controlled trial in 5 PCCs in Barcelona. Here we register a Randomized controlled clinical trial with PRESTOapp 2.0 detailed afterwards:

The prevalence of mental health disorders in Primary Care (PC) largely exceeds the limited resources available. The main aim of this project is to develop a comprehensive machine learning (ML) digital support platform (PRESTO) to approach people with mental health symptoms in PC. PRESTO will offer a transdiagnostic triage of those cases needing specialized care while most of the mild and moderate cases with anxiety and depressive symptoms will be allocated through ML models to either: 1.a periodic follow-up, 2.symptoms monitoring and brief psychological intervention with a smartphone app, or 3.a specific psychopharmacological treatment. To reach this objective, first, a ML predictive severity model will be build based on all the cases referred to the PC mental health support programme during the last 5 years retrieved from electronic health records from 5 PC centres(PCC) in Barcelona. Simultaneously, a smartphone app (PRESTOapp) monitoring symptoms and delivering a psychological intervention for non-severe anxious and depressive symptomatology will be developed and tested in a feasibility study and in a randomized clinical trial. Finally, the ML models obtained from the first phase of the project and the data from the PRESTOapp study will be integrated in a comprehensive self-learning web platform which will triage and assign to each case a specific intervention based on the predicted outcome. The effectiveness of PRESTO to reduce waiting times in receiving appropriate and specific care of mental health problems will be tested by means of a stepped-wedge randomized controlled trial in 5 PCCs in Barcelona. Here we register a Randomized controlled clinical trial with PRESTOapp 2.0. * Design: Single-blind randomized controlled clinical trial. * Sample: Referrals to mental health support programme (PCMHSP) by GPs from the 5 primary care centres included in the study. * Sample size calculation: Considering the priority (primary outcome) the reduction of depressive symptoms assessed by PHQ-9 and taking into account two groups (PRESTOapp 2.0 vs. treatment as usual) in addition to previous results of effect sizes between 0.30 - 0.35 from similar studies (similar intervention, same scale), we have established a power of 0.80 and a α of 0.05. Considering the current numbers of visits by all members of the PCMHSP who can potentially be offered inclusion in the study in 6 months (1000 individuals), the total sample should have at least 122 participants. However, experience in similar studies indicates an expected 25-30% drop-out. Therefore, it was decided to add 15 more subjects per branch for preventive purposes and to ensure that at the end of the study there would be a sufficient sample to guarantee the strength of the data. * Intervention Group (PRESTOapp 2.0): 76 participants * Control Group (Treatment as usual): 76 participants TOTAL: 152 participants. Considering the number of PCMHSP members involved in the project as well as the high number of referrals (which is the main problem this project is trying to solve), reaching these numbers is fully feasible within the stipulated time. * Inclusion criteria: Individuals 18-65 years of age who are referred to or are being followed up by members of the PCMHSP in the 5 PCCs corresponding to the 5 Barcelona catchment areas (ABS), scoring between 4 and 14 points on the PHQ-9 scale, or 6 to 15 on the GAD-7 scale. They must also accept and sign the informed consent for study participation and must have a compatible smartphone (Android or iPhone). * Exclusion criteria: Individuals who do not know and/or do not wish to learn the skills required to operate a smartphone. Estimated IQ less than 70 with functional impairment Patients with a severe mental disorder (Bipolar Disorder, Schizophrenic Disorder, Schizoaffective, Obsessive-Compulsive) or substance use disorder, PHQ-9 \>= 15, GAD-7 \>= 16. People with moderate to severe suicidal ideation (PHQ-9 Question 9 with a score of 2 or 3) * Recruitment procedure: All users referred to PCMHSPs by GPs from the PCC included in the study will be offered participation in the study. Once the information on the study has been provided, which will also be available in printed form in the waiting room for consultations, any doubts presented by the user will be cleared up and the signature of the informed consent will be requested. * Randomization: Once users are recruited, an independent researcher will randomize the participants using a 1:1 sequential method in two groups of 76 individuals and will assign a 6-digit identification code (IC) to each participant. The IC will be given to the participant on a reminder card and will be used to access the app to guaranteeing its confidentiality. The name of the subjects and their respective code will be stored in independent servers for methodological, security, and legal reasons. The intervention group will be asked to use the app for a period of 2 months. The control group will receive the usual follow-up and treatment during the same time by the PCMHSP team. * Data collection: \* Initial evaluation: The estimated time used for the initial evaluation including an explanation of the study, signing of the informed consent, and data collection is of about 30 minutes. ■ Intervention Group: In this first visit, a brief explanation of how the app works and a brochure explaining PRESTOapp 2.0 will be given. Users will be asked to use the app on their smartphone for the next 2 months. During this first visit, we will help the participant to install the app. Subsequently, the following data will be collected: * Demographic variables: gender, age, marital status, housing condition, number of children, years of education, educational level, employment status. * Clinical variables: medical comorbidities, hospitalizations, number of depressive episodes and previous hospitalizations, history of psychotic symptoms, seasonal pattern, history of melancholy, atypical, psychotic or catatonic symptoms in depressive episodes, comorbidity (axes I, II and III), family history (first degree) of psychiatric disorders and suicide, number of self-initiated attempts and method. * Care variables: Number of visits in MAP in the last 5 years, number of visits in PSP, number of consultations in the emergency department. The 9-items Patient Health Questionnaire (PHQ-9) * The 7-item Generalized Anxiety Disorder Questionnaire (GAD-7) * World Health Organization 5-item General Welfare Index (WHO-5) * Holmes and Rahe Stress Scale Participants will be informed that the next follow-up visit (and clinical assessment) by the PCMHSP will be in 2 months at the end of the study unless the app indicates or symptoms that require urgent care arise. ■ Control Group: The same information and scales as for the intervention group will be collected. \* Follow-up evaluation: A follow-up appointment will be carried out in both groups after 2 months, lasting approximately 30 minutes, during which the same data collected in the baseline interview will be collected, in addition to the Technology Acceptance Model (TAM), usability with the System usability scale (SUS), and satisfaction with the Health App Usability Questionnaire (MAUQ). * Statistical analysis: All the data will be collected by the project researchers and the PCMHSP team, and stored in encrypted and secure servers. The data from the app will be managed by the researchers only. Statistical analyses will be conducted using specific R packages. The analyses of all the subjects included will be considered until the abandonment or end of the study. The main variable is the change in symptoms measured by PHQ-9, GAD-7, secondarily it will be considered WHO-5, during the 2 months, controlled by life stressors as assessed by the Holmes y Rahe scale. We will use a mixed effects linear model with random interception for each participant. The differences in the primary measures will be analyzed first in an unadjusted manner and then adjusted for sociodemographic and clinical factors collected, if you present a p≤0.1 in univariate analysis. An analysis by intention to treat (ITT) with last observation carried performed (LOCF) will also be employed. A threshold of statistical significance p≤0.05 (two-tailed) will be set. * Study limitations: There is no investigator blinded for logistical and ethical reasons, nor is there a placebo in the case of controls. The main reason for this design is that the methodological effects of providing a placebo app to the control group are unclear. Assumable risks are the placebo effect in the intervention group, natural progression, and regression to the mean.