Evaluation of various traditional machine learning techniques for predicting the acute effect of different hamstring muscle stretching methods among male soccer players
Authors
Elham Hosseini 1 , Mohammad Alimoradi 1,2 , Mojtaba Iranmanesh 1 , Sahar Zaidi 3 , Arian Azizian 4 , Andreas Konrad 5, Hadis Mohseni 4
1 Department of Sports Injuries and Corrective Exercises, Faculty of Sports Sciences, Shahid Bahonar University of Kerman, Kerman, Iran.
2 HERC – Health, Exercise & Research Center, Mina Rashid, Dubai Maritime City, Dubai, United Arab Emirates.
3 Department of Physiotherapy, School of Nursing Sciences and Allied Health, Jamia Hamdard, New Delhi, India.
4 Department of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran.
5 Institute of Human Movement Science, Sport and Health, Graz University, Graz A-8010, Austria.
Phase
The Project
Abstract
This study investigated the acute effects of static (SS), dynamic (DS), and ballistic (BS) hamstring stretching on performance in male soccer players and applied machine learning (ML) to predict protocol efficacy.
A total of 249 players with and without hamstring shortening completed each protocol across three sessions with 72 hours of rest. Hamstring shortening classified via passive knee extension test (>32.2° knee angle). Flexibility, strength, sprint, power, and agility were measured pre- and post-stretching. Each protocol: 4 sets × 30 s (holds/swings/bounces at 50-60 bpm), 10 s rest. ML models (k-NN, SVM, random forest) were trained on pre–post difference scores, with feature selection applied to identify key predictors and Synthetic Minority Over-sampling Technique used to address class imbalance. Findings indicate SS optimally acutely improves flexibility, whereas DS offers broader immediate performance benefits for a subsequent activity.
Combining feature selection and data balancing increased k-NN accuracy to 53% (only ~20 percentage points above the chance level of 33.3% for this three-class problem), highlighting methodological challenges in predicting individual responses. Exploratory analysis using ML using synthetic minority over-sampling technique reached a peak accuracy of 53.06% (compared to a baseline of 33.3%), demonstrating the promise of the approach but also highlighting the challenges of applying ML to predict individual responses to stretching interventions, underscoring the need for larger datasets and more advanced models.