Title: Doping control analysis in athletes steroid profile: A multivariate Bayesian learning approach
Authors: Dimitra Eleftheriou - University of Glasgow (United Kingdom) [presenting]
Abstract: Anabolic androgenic steroids (AAS) are frequently detected as doping substances in competitive sports. In order to detect AAS doping with pseudo-endogenous steroids, i.e. steroids that are produced in the human body like testosterone, urinary concentrations of the athlete's steroid profile are measured over time in the steroidal module of the Athlete Biological Passport (ABP). This research work focuses on extending the current univariate Bayesian model, which monitors each biomarker in the steroid profile separately, to a multivariate multilevel adaptive model, which is able to accommodate repeated measurements from various sensitive biomarkers and their concentration ratios. The developed methodology was applied to urine sample data obtained from professional athletes. Among these samples, normal, atypical, and abnormal values were identified. An anomaly detection technique based on a one-class classification (OCC) algorithm was carried out to detect anomalies within the athletes' steroid profiles, either due to AAS misuse or other confounding factors. In a Bayesian context, the main idea is to construct adaptive decision boundaries around normal concentration values as new recordings come, and differentiate them from the abnormal ones. Improved prediction performance was obtained compared to standard methodologies suggesting the proposed approach as an improved tool for doping detection.