Predicting the Healing of Lower Extremity Fractures Using Wearable Ground Reaction Force Sensors and Machine Learning

Sensors (Basel). 2024 Aug 17;24(16):5321. doi: 10.3390/s24165321.

Abstract

Lower extremity fractures pose challenges due to prolonged healing times and limited assessment methods. Integrating wearable sensors with machine learning can help overcome these challenges by providing objective assessment and predicting fracture healing. In this retrospective study, data from a gait monitoring insole on 25 patients with closed lower extremity fractures were analyzed. Continuous underfoot loading data were processed to isolate steps, extract metrics, and feed them into three white-box machine learning models. Decision tree and Lasso regression aided feature selection, while a logistic regression classifier predicted days until fracture healing within a 30-day range. Evaluations via 10-fold cross-validation and leave-one-out validation yielded stable metrics, with the model achieving a mean accuracy, precision, recall, and F1-score of approximately 76%. Feature selection revealed the importance of underfoot loading distribution patterns, particularly on the medial surface. Our research facilitates data-driven decisions, enabling early complication detection, potentially shortening recovery times, and offering accurate rehabilitation timeline predictions.

Keywords: ankle fracture; lower limb rehabilitation; machine learning; tibial fracture; wearable sensors.

MeSH terms

  • Adult
  • Aged
  • Female
  • Fracture Healing / physiology
  • Fractures, Bone
  • Gait / physiology
  • Humans
  • Lower Extremity* / physiopathology
  • Machine Learning*
  • Male
  • Middle Aged
  • Retrospective Studies
  • Wearable Electronic Devices*

Grants and funding

This original clinical trial was funded by the U.S. Department of Defense CDMRP Award No. W81XWH1220089. The study presented in this paper was funded by a University of Utah Graduate Research Fellowship and a grant from the U.S. Department of Defense CDMRP Award No. W81XWH2010266.