Finding Pre-Injury Patterns in Triathletes from Lifestyle, Recovery and Load Dynamics Features

TL;DR

This paper presents a novel synthetic data framework for triathletes that integrates lifestyle, recovery, and load factors to improve injury prediction using machine learning models with high accuracy.

Contribution

It introduces a new synthetic data generation method that combines physiological, training, and lifestyle factors for better injury risk prediction in triathletes.

Findings

Machine learning models achieved up to 86% AUC in injury prediction.

Sleep disturbances, heart rate variability, and stress are key early indicators.

The approach enhances injury prediction accuracy by incorporating holistic athlete data.

Abstract

Triathlon training, which involves high-volume swimming, cycling, and running, places athletes at substantial risk for overuse injuries due to repetitive physiological stress. Current injury prediction approaches primarily rely on training load metrics, often neglecting critical factors such as sleep quality, stress, and individual lifestyle patterns that significantly influence recovery and injury susceptibility. We introduce a novel synthetic data generation framework tailored explicitly for triathlon. This framework generates physiologically plausible athlete profiles, simulates individualized training programs that incorporate periodization and load-management principles, and integrates daily-life factors such as sleep quality, stress levels, and recovery states. We evaluated machine learning models (LASSO, Random Forest, and XGBoost) showing high predictive performance (AUC up to 0.86), identifying sleep disturbances, heart rate variability, and stress as critical early indicators of injury risk. This wearable-driven approach not only enhances injury prediction accuracy but also provides a practical solution to overcoming real-world data limitations, offering a pathway toward a holistic, context-aware athlete monitoring.