Discovery of Dynamic Models for AML Disease Progression from Longitudinal Multi-Modal Clinical Data Using Explainable Machine Learning

Acute Myeloid Leukemia (AML) is a complex and heterogeneous disease identified by severe clinical progression, fast cellular proliferation, and often high mortality rates. Incorporating diverse medical data and longitudinal information on patients’ medical histories is essential for developing effective disease predictive models applicable to both research and clinical settings. Here, we present a robust methodology for discovering dynamic predictive models to elucidate AML disease progression dynamics from a novel longitudinal multimodal clinical dataset, including the dynamics of patient information, leukemia-associated genetic parameters, and disease management strategies. The clinical dataset of 467 patients diagnosed with AML at the University of Maryland Medical Center was curated and analyzed to reveal the main clinical, genetic, and treatment features modulating disease progression. To efficiently discover mathematical models that can predict AML progression—including the interactions, parameters, and nodes required—we present an explainable machine learning algorithm based on high-performance evolutionary computation. The results demonstrate that the predictive methodology could accurately estimate the clinical dynamics of AML progression in terms of blast percentages for both training and novel patients. This study demonstrated that the developed explainable machine learning approach can successfully predict AML progression by leveraging the inherent heterogeneous and longitudinal dynamics of patients’ clinical data. More importantly, this methodology shows significant potential for application in modeling the progression dynamics of other acute diseases, providing a flexible and adaptable framework for advancing clinical and translational research.