Determining the Level of Reaction to a Moving Object in Combat Sports Athletes Using an Composite Index and Machine Learning

Background: and Objectives. Reaction to a moving object (RMO) is an important psychophysiological function in combat sports, supporting situational perception, anticipation of an opponent’s movements, and timely technical and tactical actions. This study aimed to assess this function in combat sports athletes using an composite index and to develop a machine learning model for automated classification. Methods. The study included 312 combat sports athletes aged 10-25 years. Reaction to a moving object was assessed using the specialized “Reaction RMO Pro” test. The RMO_Index was calculated from standardized measures of mean reaction time and its variability, with higher values indicating better overall performance. The model was trained using stage-specific test indicators and characteristics of premature, delayed, and accurate responses. Results. Mean reaction time was 32.44 ± 10.29 ms, and variability was 21.88 ± 6.87 ms. The proportions of premature, delayed, and accurate responses were 48.18 ± 10.18%, 44.66 ± 10.45%, and 7.16 ± 4.40%, respectively. A balanced target variable, RMO_Level_Target, was derived from the RMO_Index: High, 104; Medium, 104; and Low, 104. The Boosted Tree Classifier achieved 100% accuracy on the training and validation sets and 94% on the independent test set. The F1-scores were 0.97, 0.94, and 0.90 for the High, Low, and Medium classes, respectively. Conclusions. The RMO_Index provides a composite measure of response speed and stability, while the derived levels provide a basis for automated classification. Stage-specific indicators and response-timing characteristics were informative for determining levels of reaction to a moving object. The model can be integrated into an iPadOS mobile app as an on-device Core ML solution for rapid sports monitoring.