COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Functional digital twinning for in silico phenotyping and therapy response prediction: applications of the novel CircAdapt framework
Functional digital twinning for in silico phenotyping and therapy response prediction: applications of the novel CircAdapt frameworkAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact nobody. FHTW02 - Fickle Heart: The intersection of UQ, AI and Digital Twins Joost Lumens, PhD, Nick van Osta, PhD This presentation discusses the application of the Digital Twin (DT) concept using the CircAdapt cardiovascular modeling and simulation framework, highlighting its effectiveness in creating DTs of a patient’s cardiac pump and tissue function. Furthermore, it will be discussed how this technology was used for tracking myocardial disease progression and for predicting response to therapy at individual patient level. In the context of arrhythmogenic cardiomyopathy (ACM), our research demonstrates how CircAdapt-based DTs can identify patient-specific myocardial abnormalities and monitor disease evolution. By employing a robust parameter reduction and estimation pipeline, we successfully personalized the CircAdapt model using a limited set of echocardiographic data on cardiac function, in particular regional strain patterns. The resulting DTs provided unique insight in an individual’s heterogeneity of right ventricular myocardial properties that correlate with disease progression. Longitudinal DTs of ACM patients showed that myocardial function deteriorates similarly across different age groups, challenging current clinical practice guidelines by suggesting the need for continuous follow-up in older populations. Further extending the utility of CircAdapt-based DTs, we evaluated heart failure (HF) patients undergoing cardiac resynchronization therapy (CRT). By generating DTs and simulating virtual pacing therapy, we were able to predict the degree of left ventricular reverse remodeling post-CRT. Our findings indicate that DT-derived metrics, such as pacing-induced change of septal-to-lateral myocardial work difference, correlate strongly with real-world clinical outcomes, offering a potential support tool for patient selection or even optimization of therapy delivery. Overall, these studies underscore the potential of CircAdapt-based Digital Twins in providing a deeper understanding of an individual’s myocardial phenotype and enhancing personalized treatment strategies. This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsTQS Journal Clubs Qualitative methods in health research Extragalactic GatheringOther talksStatistics Clinic Easter 2024 I Stochastic Gradient Descent with Adaptive Data TODAY'S TALK CANCELLED DUE TO SICKNESS Machine learning: applications to cancer Applications of proofs to network security Cambridge RNA Club - July session ON ZOOM Adaptive Importance Sampling for accelerating the minimization of tail risks |