Project Overview
AI MEDICARD is an integrated digital health project designed to enhance the entire clinical decision-making and patient care, from diagnosis and prognosis to therapeutic planning and monitoring, in individuals affected by diabetes, cardiovascular, and renal diseases
Artificial intelligence, medical research and advanced informatics combined to deliver personalized, evidence-based medicine through a scalable software platform accessible to healthcare professionals
Prevention and early detection of acute cardiovascular events, excluding heart failure, in high-risk patients with comorbidities (e.g., Type 2 Diabetes Mellitus (T2DM) and End-Stage Renal Disease (ESRD))
AIM
To develop an integrated Digital Health Platform:
To support diagnosis, treatment, and monitoring of complex patients with T2DM, cardiovascular issues, and renal comorbidities
To enable the visualization of clinical data via a dashboard, enriched by AI-generated predictive insights
To assist healthcare professionals in understanding and predicting the triggering factors behind acute cardiovascular events, thereby contributing to prevention strategies
To deliver a high-impact, innovative clinical service that incorporates personalized medicine tools
Method
WP1 – Clinical Correlation Analysis: Examination of relationships between cardiac, pulmonary function, sleep apnea, and T2DM, with and without ESRD
WP2 – Predictive Algorithm Development: AI models for forecasting cardiac disease onset and progression in T2DM patients with chronic and terminal renal comorbidities
WP3 – Genomic Profiling: Analysis of genomic variability in diabetic patients with differing disease severities to develop risk stratification algorithms
WP4 – RNA Biomarker Identification: Detection and validation of genomic and epigenomic RNA biomarkers (including microRNAs) through liquid biopsy techniques
WP5 – Multiparametric Biomarker Panel: Development and clinical validation of a predictive, diagnostic, and/or prognostic biomarker panel to be integrated into the AI platform
Results
- Improved personalization of therapy and clinical pathways tailored to individual risk profiles
- Enhanced care quality and reduced cardiovascular complication risk in diabetic patients
- Early identification of at-risk patients, enabling timely interventions
- Data-driven clinical decision-making, supported by AI and biomarker insights
- Efficient use of medical resources, through optimized treatment selection and follow-up plans
- Reduction of adverse effects by targeting therapy to the patient’s biological and clinical profile
Conclusion
A step forward in precision medicine, combining AI algorithms with genomic and clinical data to deliver a powerful decision-support tool for clinicians
By integrating diagnostics, monitoring, and predictive modeling into a single platform, it can improve patient outcomes, particularly among those with high-risk comorbidities, and realize more sustainable healthcare delivery