Machine learning-based prediction of the necessity for the surgical treatment of distal radius fractures

Abstract

Background: Treatments for distal radius fractures (DRFs) are determined by various factors. Therefore, quantitative or qualitative tools have been introduced to assist in deciding the treatment approach. This study aimed to develop a machine learning (ML) model that determines the need for surgical treatment in patients with DRFs using a ML model that incorporates various clinical data concatenated with plain radiographs in the anteroposterior and lateral views.

Methods: Radiographic and clinical data from 1,139 patients were collected and used to train the ML models. To analyze and integrate data effectively, the proposed ML model was mainly composed of a U-Net-based image feature extractor for radiographs, a multilayer perceptron based clinical feature extractor for clinical data, and a final classifier that combined the extracted features to predict the necessity of surgical treatment. To promote interpretability and support clinical adoption, Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to provide visual insights into the radiographic data. SHapley Additive exPlanations (SHAP) were utilized to elucidate the contributions of each clinical feature to the predictions of the model.

Results: The model integrating image and clinical data achieved accuracy, sensitivity, and specificity of 92.98%, 93.28%, and 92.55%, respectively, in predicting the need for surgical treatment in patients with DRFs. These findings demonstrate the enhanced performance of the integrated model compared to the image-only model. In the Grad-CAM heatmaps, key regions such as the radiocarpal joint, volar, and dorsal cortex of the radial metaphysis were highlighted, indicating critical areas for model training. The SHAP results indicated that being female and having subsequent or concomitant fractures were strongly associated with the need for surgical treatment.

Conclusions: The proposed ML models may assist in assessing the need for surgical treatment in patients with DRFs. By improving the accuracy of treatment decisions, this model may enhance the success rate of fracture treatments, guiding clinical decisions and improving efficiency in clinical settings.

Keywords: Clinical data integration; Fracture management; Grad-CAM; SHAP; Surgical decision-making; U-Net.

Fig. 1

U-net based image feature extractor for plain radiograph images

Fig. 2

Overview of the prediction models. A. Model utilizing only radiographic image data as input. Image features are extracted through an image feature extractor and fed into a classifier to generate predictions. B. Model integrating both radiographic images and clinical data (e.g., age and BMI). Clinical features were extracted using a clinical feature extractor and concatenated with image features before being passed to the classifier. Integrating image and clinical data leverages complementary information, potentially improving predictive performance

Fig. 3

A. Confusion matrix of the image-only model. B. Confusion matrix of the image and clinical data integrating model

Fig. 4

Receiver operating characteristic (ROC) curve of the models (image-only model and image and clinical data integrating model). A. Comparison of ROC curves between the two models. B. ROC curve for the image-only model, including the 95% confidence interval (CI). C. ROC curve for the image and clinical data integrating model, including the 95% CI

Fig. 5

A. Gradient-weighted Class Activation Mapping (Grad-CAM) visualization on anteroposterior wrist radiograph images. The heatmap indicates that the congruency of the radiocarpal joint (white arrow) was a critical region for model training. B. Grad-CAM visualization on lateral wrist radiograph images. The heatmap shows that the volar cortical disruption of the radial metaphysis (white arrow) and dorsal metaphyseal comminution (red arrow) were critical regions for model training

Fig. 6

A. SHapley Additive exPlanations (SHAP) values for clinical features in predicting the need for surgery (surgery required). Each dot represents a SHAP value for a single patient’s feature, with its position indicating the degree of influence on the model’s decision and its color representing the feature’s value (red = high, blue = low). B. SHAP values for clinical features in predicting the need for surgery (surgery not required), following the same format as Fig. 6A, illustrating how these features influenced cases where surgery was not required. C. Mean absolute SHAP values across both classes, offering a global perspective on feature importance in the model’s decision-making