The FEMaLe project has benefited greatly from applying the Half Double Methodology to improve collaboration, communication, and cross-disciplinary understanding (WP1 and WP10). Systematic data collection enabled real-time progress tracking and adaptation, fostering early value creation and better project outcomes. A 'Reflective Learning Evaluation Framework' combined realistic evaluation with a learning perspective, reducing complexity, shortening time to impact, and strengthening trust and stakeholder engagement. This approach established a model for balancing accountability with adaptability, improving governance in complex research projects.
The project successfully developed ethical, gender-inclusive, and open science frameworks (WP2), supporting responsible research and innovation for endometriosis diagnosis and care. Multiple white papers were published, and stakeholder engagement ensured alignment with EU principles of inclusivity and innovation.
Large-scale epidemiological research (WP3) in Denmark and the UK advanced understanding of endometriosis prevalence, symptoms, and diagnostic delays, highlighting regional disparities and socioeconomic consequences. Findings were widely disseminated, including at major conferences, with award-winning research presented in 2024. Machine learning models for early detection using health records further demonstrated potential for clinical application.
The project also made significant contributions to genetic research (WP4), developing a novel risk classifier and identifying genetic subtypes linked to proteomic markers, such as PAEP and LPA. A clinical decision support tool prototype integrating genetic, proteomic, and clinical data marked a step toward precision medicine. These achievements were shared at high-profile international conferences, enhancing awareness and impact.
Digital health innovation was advanced through Lucy App (WP5), which collected over 3 million data entries from more than 20,000 users across Europe, creating one of the largest prospective data banks for endometriosis research. Machine learning confirmed the reliability of self-reported data, and a longitudinal study identified symptom patterns, quality-of-life impacts, and environmental factors. A digital psychological intervention, MY-ENDO (WP8), was developed and integrated into Lucy App, demonstrating effectiveness in improving emotional resilience and self-management, supported by a successful randomised controlled trial.
AI and augmented reality (AR) technologies significantly improved laparoscopic diagnosis and treatment of endometriosis. Advanced lesion detection algorithms (WP6) enhanced real-time surgical precision, particularly benefiting junior surgeons, and were validated through structured interviews and video-based assessments. The integration of these algorithms into AR-assisted surgical workflows set a new standard for AI-driven surgery (WP7), with strong clinician feedback confirming safety and usability. Dissemination included conference presentations, webinars, and planned journal publications.
The project’s outreach and dissemination activities achieved an organic reach of over 20 million views by 2024 (WP9), driven by popularised publications, media appearances, social media campaigns, conference participation, scientific publications, and engagement through the Lucy app. This exceptional reach significantly boosted awareness and engagement with FEMaLe’s results across diverse audiences.
