EIBIR Session

EIBIR 5 - AI meets obesity: from promise to trustworthy cardiovascular risk prediction

March 3, 15:00 - 16:00 CET

5 min
Chairperson's introduction
8 min
The AI‑POD risk score: performance, explainability and added value
  1. To learn about the potential of AI tools for improved obesity-related prediction of cardiovascular disease.
  2. To learn about the trustworthy AI tools for the prediction of obesity-related vascular diseases (AI‑POD) project's risk score and ist development, structure, and performance.
  3. To appreciate the added predictive value of integrating imaging, clinical, and lifestyle data.
8 min
From prediction to practice: the AI‑POD Clinical Decision Support System
  1. To understand the clinical need for AI tools for clinical decision making for obesity-related cardiovascular disease.
  2. To learn about the functionalities of the AI-POD CDSS and how it translates risk prediction into clinical decision support.
  3. To appreciate the integration of imaging based AI into clinical workflows.
8 min
Future directions in wearable patient monitoring: the AI‑POD Citizen App
  1. To learn about the potential and design of the AI-POD Citizen App.
  2. To appreciate the role of lifestyle data in dynamic risk assessment.
  3. To understand user engagement, adherence, and acceptance in real world settings.
8 min
Trustworthy by design: can we build AI that clinicians and patients believe in?
  1. To learn about findings on acceptability, usability, and trust among clinicians and patients from the AI‑POD study and surveys.
  2. To appreciate how ethical frameworks, stakeholder perspectives, and user feedback were integrated into the design and evaluation of AI‑POD tools.
  3. To understand how fairness, transparency, and user expectations influence the successful adoption of AI based risk prediction systems.
8 min
Closing the cardiovascular risk gap in obesity: clinical evidence and key findings from AI‑POD
  1. To learn about the key findings from the AI‑POD project and the multicentre feasibility study.
  2. To appreciate how AI‑POD translates clinical evidence into concrete recommendations for cardiovascular risk assessment in obesity.
  3. To understand the potential impact of the IA-POD findings for future clinical practice and imaging‑driven risk stratification.
15 min
Panel discussion: From tools to adoption: what will it take?