From evidence-based medicine to digital twin technology for predicting ventricular tachycardia in ischaemic...

Area of Science:

• Cardiology
• Biomedical Engineering
• Data Science

Background:

• Survivors of myocardial infarction are at high risk for life-threatening ventricular tachycardias (VTs).
• Current implantable cardioverter defibrillator (ICD) guidelines rely on symptoms and ejection fraction, potentially missing at-risk patients.
• Catheter ablation is a secondary treatment for scar-related VTs, improving patient outcomes after ICD implantation.

Purpose of the Study:

• To improve prediction of ventricular tachycardia (VT) occurrence and circuit identification in myocardial infarction survivors.
• To enhance patient risk stratification for VT and promote preventive ablation strategies.
• To foster interdisciplinary understanding and collaboration for developing advanced clinical decision support tools.

Main Methods:

• Proposing digital twins that integrate clinical expertise with evidence-based medicine, data-driven models, and mechanistic models.
• Incorporating multiple time-evolving pathophysiological aspects, including anatomical substrate, triggers, and modulators, into VT prediction models.
• Facilitating mutual understanding between clinical, data science, and biomedical engineering experts.

Main Results:

• The study outlines a framework for digital twin solutions for VT prediction.
• It emphasizes the potential of hybrid modeling by combining different predictive approaches.
• Identifies open challenges and potential gains for digital twin implementation in clinical practice.

Conclusions:

• Digital twins offer a promising approach to enhance VT prediction by integrating diverse data and modeling techniques.
• Improved prediction can lead to more effective preventive ablation strategies, reducing mortality and morbidity in myocardial infarction survivors.
• Interdisciplinary collaboration is crucial for advancing technological innovations in clinical decision support for arrhythmias.