A Machine Learning Approach to Predicting Radiographic Outcomes of Nonsurgically Treated Distal Radius Fractures
Eric R Taleghani1, Ruihong Lyu, Taylor Shackleford
1From the Department of Orthopaedic Surgery, University of Cincinnati (Taleghani, Shackleford, Rex, Hale, and Florczynski), and University of Cincinnati College of Engineering and Applied Science, Cincinnati, OH (Lyu and Talavage).
Introduction:
Several statistical models have been developed to predict the stability of distal radius fractures after closed reduction, but their findings have not been consistently reproduced. We aimed to develop a machine learning (ML) model to predict radiographic outcomes of nonsurgically treated distal radius fractures based on pre-reduction and postreduction radiographic parameters and demographic variables.
Methods:
Adults with displaced distal radius fractures at a single institution between 2012 and 2024 were identified through retrospective chart review. Inclusion criteria required closed reduction in the emergency department, with radiographs obtained before reduction, immediately after reduction, and 6 weeks after reduction. At 6 weeks, treatment outcomes were classified as "success" or "failure" based on American Academy of Orthopaedic Surgeons acceptable reduction parameters. Five ML models were trained to predict 6-week outcomes using demographic data and pre-reduction and postreduction radiographic measurements. The 10 parameters with highest Shapley values for predictive ability were used to create an interpretable composite model.
Results:
Among 1,227 patients, 152 met the inclusion criteria (mean age: 61.4 ± 20.2 years; 75.7% female). The composite model correctly predicted outcomes in 25 of 31 patients, achieving an accuracy, precision, and recall of 81%; area under the curve of 0.84; and F1 score of 0.81. Restoration of postreduction palmar tilt, radial height, and excellent reduction based on the Lindstrom score were most predictive of 6-week radiographic outcomes. The best performing decision tree showed the following cutoffs predictive of treatment failure: +4.7 mm of pre-reduction ulnar variance, 8° of postreduction dorsal tilt, and <18.8° of postreduction radial inclination.
Conclusion:
This study developed an ML model that accurately predicts 6-week radiographic outcomes in nonsurgically treated distal radius fractures. Postreduction parameters were the strongest predictors, underscoring the importance of a high-quality closed reduction. This study validates the potential of ML as a predictive tool in this setting.
