Multidisciplinary prediction of running-related injuries using machine learning - Takeaways - MDSpire

Multidisciplinary prediction of running-related injuries using machine learning

  • By

  • Han Wu

  • Katherine Brooke-Wavell

  • Michael R. Barnes

  • Zainab Awan

  • Sarabjit Mastana

  • Sam Allen

  • Richard C. Blagrove

  • February 6, 2026

  • 0 min

Share

  • 1

    The study presents a machine learning dataset for predicting running-related injuries using multidisciplinary risk factors.

  • 2

    Data was collected from 142 competitive endurance runners over 12 months, resulting in 6181 weekly samples.

  • 3

    Random forest models showed the best performance in predicting injuries, with an AUC of 0.784, significantly outperforming other algorithms.

  • 4

    Logistic regression improved performance when trained with a broader range of risk factors compared to high-quality risk factors.

  • 5

    The study provides a methodological framework for future machine learning research in sports injury prediction.

Original Source(s)

Multidisciplinary prediction of running-related injuries using machine learning

  • by Han Wu, Katherine Brooke-Wavell, Michael R. Barnes, Zainab Awan, Sarabjit Mastana, Sam Allen, Richard C. Blagrove

  • February 6, 2026

Related Content

Torsional Deformity Masquerading as Knee Instability

Persistent knee pain and gait disturbance exposed an overlooked lower extremity diagnosis.

APB Transfer Stabilizes Chronic Thumb RCL

Case report describes return to activity and improved stability after tendon reconstruction

AI Falls Short on Differential Dx

New PrIME-LLM benchmark shows strong diagnostic accuracy but persistent gaps in clinical reasoning across 21 large language models