1Department of General Surgery, Meenakshi Medical College Hospital & Research Institute, Meenakshi Academy of Higher Education and Research
2Department of Cardiology, Meenakshi Medical College Hospital & Research Institute, Meenakshi Academy of Higher Education and Research
3Department of Periodontology, Meenakshi Ammal Dental College and Hospital, Meenakshi Academy of Higher Education and Research
4Arulmigu Meenakshi College of Nursing, Meenakshi Academy of Higher Education and Research
5Meenakshi College of Nursing, Meenakshi Academy of Higher Education and Research
6Meenakshi College of Pharmacy, Meenakshi Academy of Higher Education and Research
Aim: To create and test a hybrid architecture to incorporate digital twin coronary models and clinical real-world data to improve personalized planning to perform percutaneous coronary intervention (PCI).
Background: The current planning of PCI is largely based on angiography and operator experience which might not be accurate enough to reflect patient-specific hemodynamics or lesion behavior. Computational models of the coronary structures and physiology of a patient known as the digital twins can serve as an extremely effective intervention prediction tool. Nonetheless, their precision will be determined by the quality of inputs and the strength of adherence to the actual experiences of patients.
Methods: The enrolled 260 patients undergoing coronary evaluation were part of this study. The digital twin of every patient was created on the basis of CT angiography geometry, fractional flow reserve calculations, and physiological model of microvascular resistance. A machine-learning integration layer provided access to real-world data (RWD), such as demographics, the presence of biomarkers, nature of lesions, functional tests, and results of the procedures. The hybrid system generated personalized premonition of post-PCI hemodynamic enhancement, stent size, and probability of residual ischemia. Cross-validation and prospective clinical comparisons were used as a measure of model performance.
Results: The hybrid model proved to be more precise in the prediction than a system based solely on digital-twin modeling (AUC 0.89 vs. 0.78) or the conventional angiography-only planning (AUC 0.71). In 82 percent, post-PCI fractional flow reserve was not more than ±0.05. Prediction of complex lesion outcomes and microvascular dysfunction were enhanced with incorporation of RWD.
Conclusion: Currently, the application of hybrid digital twin-RWD would result in more accurate and clinically-actable predictions than what is currently used in personalized PCI planning. These results justify the further implementation of evidence-based personalization in interventional cardiology.
Keywords: Digital twin, coronary CTA, real world data, PCI planning, fractional flow reserve.
How to cite this article: Babu SK, Aashish A, Kumari BN, Uma S, Cathrine TR, Kumar AA. Hybrid Digital Twin and Real-World Data for Personalized Coronary Intervention Planning. Int J Drug Deliv Technol. 2026;16(10s): 162-167; DOI: 10.25258/ijddt.16.10s.24
Source of support: Nil.
Conflict of interest: None