Predicting Disease Progression in Atrial Fibrillation: A Multiparametric Approach for Prognostic Marker Identification and Personalized Patient Management

Predicting Disease Progression in Atrial Fibrillation: A Multiparametric Approach for Prognostic Marker Identification and Personalized Patient Management

This project leverages artificial intelligence (AI) to decipher Atrial Fibrillation (AF) progression and optimize treatment strategies. By recruiting a diverse cohort of 322 AF patients, we will gather a robust multiparametric dataset including clinical, genetic, electrocardiographic, and echocardiographic data. Harnessing AI, we will extract and correlate hidden components within ECG-obtained P-wave data and echocardiographic studies with atrial fibrosis, culminating in an atrial fibrosis score (AFS). The AFS will non-invasively predict fibrosis extent and AF clinical progression, including metrics like rehospitalization, cardiac morbidity, and mortality. Ultimately, this endeavor aims to improve AF patient management, significantly reducing healthcare costs, and enhancing patient quality of life.

Inclusion Criteria:

• History of paroxysmal or persistent atrial fibrillation
• Clinical indication for Atrial Fibrosis (AF) ablation according to the 2020 ESC Guidelines

Exclusion Criteria:

• Age below 18 years old
• Refusal to sign consent
• Noncompliance with the study protocol