A novel and accurate emotion recognition system for real-time and continuous patient monitoring in psychiatry

Project Information

ADAPTE

Grant agreement ID: 190129251

DOI

10.3030/190129251

Project closed

EC signature date 19 October 2023

Start date 1 November 2023

End date 30 April 2026

Funded under

• The European Innovation Council (EIC)

Total cost

€ 3 568 155,00

EU contribution

€ 2 497 708,00

Coordinated by

CEPHALGO
France

Periodic Reporting for period 1 - ADAPTE (A novel and accurate emotion recognition system for real-time and continuous patient monitoring in psychiatry)

Reporting period: 2023-11-01 to 2025-04-30

Summary of the context and overall objectives of the project

Mental healthcare support faces three critical challenges: low treatment adherence (>60% dropout rate), difficulty in tracking emotional states between clinical visits, and insufficient between-session support. Current methods rely heavily on patient self-reporting and memory, leading to potential gaps in care continuity.
ADAPTE aims to enhance mental healthcare support through an AI-powered patient-centric software solution that:

- Facilitates emotion tracking through natural speech analysis
- Supports patient engagement and adherence
- Bridges communication gaps between clinical sessions
- Provides objective insights to supplement clinical care

The project initially focuses on supporting individuals with Major Depressive Disorder (MDD), with potential expansion to other mental health conditions. Expected impact includes:

- Making emotional wellbeing support accessible to >95% through smartphone-based tools
- Supporting treatment adherence improvement to 75% (from current 40%)
- Enhancing patient-clinician communication

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

Technical Developments:

- Enhanced speech-based emotion recognition through advanced AI
- Developed robust quality assurance processes
- Created personalised engagement frameworks

Clinical Validation:

- Established partnerships with psychiatric hospitals covering 6,000 MDD patients
- Successfully tested patient conversational pathway v1.0
- Validated patient engagement modules with clinicians
- Implemented secure data management protocols

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Technical Innovation:

- Novel application of time-series AI analysis to speech patterns
- Integrated emotion recognition with patient engagement tools
- Developed scalable cloud-based architecture for widespread deployment

Market Impact:

- First-to-market patient-centric solution combining continuous monitoring with engagement
- 95% accessibility through smartphone-based approach
- Demonstrated feasibility of continuous emotion monitoring in real-world settings

Next Steps:

- Enhance AI models with larger datasets
- Ensure product-market fit with stakeholders’ feedback
- Iterate patient-centric software with early adopters
- Create sustainable business model