The Use of Machine Learning to Estimate Ground Reaction Forces During Running: A Scoping Review of the Current...

Ground reaction forces (GRFs) are essential for assessing running biomechanics, and the combination of wearable sensors and machine learning offers an accessible alternative for estimating GRFs outside controlled environments. This scoping review summarized current methods used to predict GRFs during running. A structured search (2019-2025) identified 36 studies, from which 37% did not report participant's training status, and 59% of all participants were males. Treadmill running was assessed in 58% of studies, which included larger samples (median N = 28) and more steps/participant (median = 65) than overground studies (median N = 14; median = 32). Deep learning models, particularly LSTM and Bi-LSTM networks, were the most applied techniques, though presenting similar accuracies compared to classical regression methods. Vertical GRF predictions were the most accurate, while mediolateral GRF predictions remain challenging. GRF-derived variables such as peak forces, impact peaks, and impulses were predicted more accurately than region-dependent metrics like loading rates. Notably, no study validated treadmill-trained models on overground running, limiting real-world generalizability. Future work should prioritize larger, sex-balanced cohorts, improving prediction of mediolateral GRFs and loading rates, and explore validating treadmill-based models in overground conditions. In conclusion, although machine learning shows promise for GRF predictions, key methodological gaps must be addressed to enable robust, real-world applications.