How to predict relapse in leukemia using time series data: A comparative in silico study

Abstract

Risk stratification and treatment decisions for leukemia patients are regularly based on clinical markers determined at diagnosis, while measurements on system dynamics are often neglected. However, there is increasing evidence that linking quantitative time-course information to disease outcomes can improve the predictions for patient-specific treatment responses. We designed a synthetic experiment simulating response kinetics of 5,000 patients to compare different computational methods with respect to their ability to accurately predict relapse for chronic and acute myeloid leukemia treatment. Technically, we used clinical reference data to first fit a model and then generate de novo model simulations of individual patients’ time courses for which we can systematically tune data quality (i.e. measurement error) and quantity (i.e. number of measurements). Based hereon, we compared the prediction accuracy of three different computational methods, namely mechanistic models, generalized linear models, and deep neural networks that have been fitted to the reference data. Reaching prediction accuracies between 60 and close to 100%, our results indicate that data quality has a higher impact on prediction accuracy than the specific choice of the particular method. We further show that adapted treatment and measurement schemes can considerably improve the prediction accuracy by 10 to 20%. Our proof-of-principle study highlights how computational methods and optimized data acquisition strategies can improve risk assessment and treatment of leukemia patients.

Artificial Intelligence-Based Management of Adult Chronic Myeloid Leukemia: Where Are We and Where Are We Going?

“…Probing the system’s response to this perturbation gave additional information about control mechanisms that could not be obtained from ongoing monotherapy. The reported evidence confirmed that different computational approaches are in principle suited to support relapse prediction and, in particular, neural networks present good performance for the disease relapse prediction if frequent measurements are available, as in the CML case [ 58 ]. Similarly, Shanbehzadeh et al used the data of 837 CML patients to test 8 ML tools, including eXtreme gradient boosting, multilayer perceptron, pattern recognition network, k-nearest neighborhood, probabilistic neural network, support vector machine (kernel = linear), support vector machine (kernel = RBF), and J-48.…”