An efficient dynamic Bayesian network classifier structure learning algorithm: application to sport epidemiology

Exposing an athlete to intense physical exertion when their organism is not ready for the mobilization of such resources can lead to musculoskeletal injury. In turn, sport practitioners regularly monitor athlete readiness in hopes of mitigating these tragic events. Rapid developments in athlete monitoring technologies has thus resulted in sport practitioners aspiring to siphon meaningful insight from high-throughput datasets. However, revealing the temporal sequence of biological adaptation while yielding accurate probabilistic predictions of an event, demands computationally efficient and accurate algorithms. The purpose of the present study is to create a model in the form of the intuitively appealing dynamic Bayesian network (DBN). Existing DBN approaches can be split into two varieties: either computationally burdensome and thus unscalable, or place structural constraints to increase scalability. This article introduces a novel algorithm ‘rapid incremental search for time-varying associations’ $(Rista)$, to be time-efficient without imposing structural constraints. Furthermore, it offers such flexibility and computational efficiency without compromising prediction performance. The present algorithm displays comparable results to contemporary algorithms in classification accuracy while maintaining superior speed.