PRimary carE digital Support ToOl in mental health (PRESTO): Design, development and study protocols

Area of Science:

• Digital health
• Machine learning
• Mental healthcare

Background:

• 30-50% of primary care users in Spain experience mild to moderate anxiety and depressive symptoms.
• Mental health issues represent a significant economic burden, accounting for 2% of Spain's GDP.
• Existing mobile health tools and machine learning show promise for cost-effective symptom management and detection.

Purpose of the Study:

• To develop a comprehensive machine learning (ML) digital support platform (PRESTO).
• To enable cost-effective screening, assessment, triage, and personalized treatment for anxiety and depressive symptoms in primary care.
• To reduce waiting times for mental healthcare services.

Main Methods:

• Phase 1: Develop an ML predictive severity model using 5 years of primary care mental health data.
• Phase 2: Develop and clinically trial a smartphone app for monitoring and delivering psychological interventions.
• Phase 3: Integrate ML models and app into the PRESTO platform for patient triage and personalized intervention assignment, tested via a stepped-wedge cluster randomized controlled trial.

Main Results:

• The PRESTO platform will integrate predictive ML models and a mobile health application.
• Patients will be triaged and assigned personalized interventions based on their clinical profiles.
• A stepped-wedge cluster randomized controlled trial will assess PRESTO's effectiveness in reducing mental healthcare waiting times.

Conclusions:

• PRESTO will provide timely, personalized, and cost-effective mental health treatment for mild to moderate anxiety and depression.
• The platform aims to decrease the societal and economic burden of mental health problems in primary care.
• This initiative seeks to improve access to and efficiency of mental healthcare services.