A review on machine learning approaches in cardiac tissue engineering

Abstract

Cardiac tissue engineering (CTE) holds promise in addressing the clinical challenges posed by cardiovascular disease, the leading global cause of mortality. Human induced pluripotent stem cells (hiPSCs) are pivotal for cardiac regeneration therapy, offering an immunocompatible, high density cell source. However, hiPSC-derived cardiomyocytes (hiPSC-CMs) exhibit vital functional deficiencies that are not yet well understood, hindering their clinical deployment. We argue that machine learning (ML) can overcome these challenges, by improving the phenotyping and functionality of these cells via robust mathematical models and predictions. This review paper explores the transformative role of ML in advancing CTE, presenting a primer on relevant ML algorithms. We focus on how ML has recently addressed six key address six key challenges in CTE: cell differentiation, morphology, calcium handling and cell-cell coupling, contraction, and tissue assembly. The paper surveys common ML models, from tree-based and probabilistic to neural networks and deep learning, illustrating their applications to better understand hiPSC-CM behavior. While acknowledging the challenges associated with integrating ML, such as limited biomedical datasets, computational costs of learning data, and model interpretability and reliability, we examine suggestions for improvement, emphasizing the necessity for more extensive and diverse datasets that incorporate temporal and imaging data, augmented by synthetic generative models. By integrating ML with mathematical models and existing expert knowledge, we foresee a fruitful collaboration that unites innovative data-driven models with biophysics-informed models, effectively closing the gaps within CTE.