Project GEN-SIGNAL (HORIZON-HLTH-2026-01-DISEASE-11)

Project Aim

GEN-SIGNAL aims to uncover sex- and gender-specific determinants, risk factors, and biological pathways underlying cardiovascular diseases (CVDs), and to translate these findings into tailored risk-prediction models and decision-support tools for clinicians. The project leverages advanced multi-modal datasets (clinical, molecular, behavioural, social, environmental), coupled with machine-learning analytics via Selvi’s Sezi platform, to explain why CVDs differ across sexes and genders in incidence, symptoms, progression, and treatment response.
The project also integrates social sciences and humanities (SSH) to ensure determinants such as sociocultural patterns, economic conditions, patient behaviour, and gender norms are adequately modelled and contextualised.

Project Outputs

1. A harmonised multi-modal data resource combining registries, biobanks, imaging, lifestyle surveys, hormonal status, genetic/epigenetic markers, and social determinants of health. Data generated within the project will comply with FAIR principles and interoperable formats.

2. ML-powered sex/gender-specific CVD risk models, built and validated using Sezi’s customisable analytics engine. These models will incorporate biological and behavioural variables, hormonal life-stage differences, pregnancy-related risks, socioeconomic factors, and environmental exposures.

3. Identification and validation of novel risk pathways, including hormonal signalling routes, structural cardiovascular distinctions, inflammatory and metabolic markers, and psychosocial contributors.

4. Prototype clinical decision-support tool, integrating the Sezi-based risk-prediction engine into clinical workflow to support tailored prevention, early detection, diagnosis and personalised treatment planning.

5. Evidence-based guidelines and intervention recommendations for healthcare professionals and policymakers to incorporate sex/gender-specific considerations into cardiovascular care.

6. SSH-integrated behavioural and sociocultural models explaining how gender roles, care access, lifestyle patterns and structural inequalities shape CVD risks across populations.

7. Contribution to EU-wide networking activities (e.g., GACD meetings), joint workshops and knowledge-exchange events, as requested by the call text.

Required Stakeholders and Their Roles

1. Clinical & Biomedical Research Centres

Capabilities needed: CVD expertise, clinical study execution, access to cohorts/registries, biobank integration.
Roles:

• Lead patient recruitment, phenotyping, imaging and biomarker sampling.

• Validate ML-derived risk factors and pathways experimentally.

• Provide longitudinal datasets covering male/female differences across life stages.

2. SSH Institutions (Sociology, Behavioural Science, Economics)

Capabilities needed: gender studies, behavioural modelling, determinants-of-health analytics.
Roles:

• Model sociocultural and socioeconomic influences on CVD risk.

• Design qualitative/quantitative studies on gender norms and behavioural patterns.

• Co-develop interventions that are clinically relevant and societally feasible.

3. Data & Epidemiology Institutes

Capabilities needed: large-scale data harmonisation, biostatistics, cohort analysis.
Roles:

• Integrate registry data, biobanks, exposure records and environmental datasets.

• Support statistical validation of ML outputs and bias-mitigation strategies.

4. Technology & AI Partners (including SMEs)

Capabilities needed: digital health, explainable AI, secure data platforms, ML-model deployment.
Roles:

• Build digital pipelines feeding harmonised data into ML models.

• Deploy clinical decision-support prototypes compliant with GDPR, ethics and medical-device guidelines.

5. Patient Organisations & Healthcare Providers

Capabilities needed: access to patient communities, clinical implementation settings.
Roles:

• Support co-creation of user-centric tools.

• Facilitate adoption pathways for sex/gender-specific CVD care.

Selvi’s Role in the Project

Selvi contributes as the core ML and data-analytics technology partner, leveraging its Sezi platform and advanced machine-learning capabilities.