Machine learning model with post-hoc SHAP interpretation based on perioperative clinical and imaging parameters for prediction of 1-year radiographic recurrence after hallux valgus surgery
- 1Department of Trauma Orthopedics, The First Affiliated Hospital of Xinjiang Medical University, Urumqi, Xinjiang, China
- 2Department of Orthopedics, Xinjiang Uygur Hospital, Urumqi, Xinjiang, China
Abstract
Objective: Radiographic recurrence after hallux valgus surgery is an important issue affecting long-term imaging outcomes. Previous studies have suggested that preoperative deformity, postoperative residual HVA/IMA, and sesamoid reduction are associated with recurrence, but nonlinear relationships may exist among multiple parameters. The aim of this study was to establish and temporally validate a machine learning prediction model based on conventional perioperative clinical and imaging parameters and to provide post-hoc model interpretation using SHAP.
Methods: 597 patients undergoing hallux valgus surgery in the Department of Trauma, First Affiliated Hospital of Xinjiang Medical University from 2021 to 2025 were retrospectively enrolled. Radiographic recurrence was defined as HVA >20° on the fixed 12-month postoperative weight-bearing anteroposterior radiograph. Patients operated from 2021 to 2023 formed the development cohort (n=389), and patients operated from 2024 to 2025 formed the independent temporal-validation cohort (n=208). Eighteen candidate predictors were screened in the development cohort using collinearity assessment, LASSO, RFE, and permutation importance. A unified eight-feature set was then locked and used for comparison of LR, RF, XGBoost, LightGBM, and SVM using 5-fold outer/3-fold inner nested cross-validation conditional on the fixed feature set. Models were evaluated using ROC-AUC, PR-AUC, Brier score, calibration, and DCA, with post-hoc SHAP-based interpretation of the final SVM.
Results: A total of 109 patients met the 1-year radiographic recurrence criterion (18.3%). Eight variables were retained: age, preoperative HVA, preoperative IMA, preoperative DMAA, 6-week postoperative HVA, 6-week postoperative IMA, 6-week postoperative DMAA, and 6-week postoperative sesamoid grade. The development-cohort ROC-AUCs of LR and SVM were 0.908 and 0.906, respectively, with corresponding PR-AUCs of 0.766 and 0.757. SVM was retained as the final model on the basis of its lower Brier score and overall performance profile, without claiming statistical superiority over LR. In the temporal-validation cohort, SVM ROC-AUC was 0.944 (95% CI 0.908–0.973), PR-AUC 0.805, Brier score 0.071, sensitivity 0.892, and specificity 0.842. SHAP showed the largest model contributions for 6-week IMA, HVA, and sesamoid grade.
Conclusion: The SVM model with post-hoc SHAP-based interpretation showed promising performance for prediction of fixed 1-year radiographic recurrence using routine clinical and perioperative imaging parameters. Residual IMA, HVA, and sesamoid grade at 6 weeks were leading predictive signals within the model rather than causal determinants of recurrence. The model may support early risk stratification and enhanced follow-up, but multicenter external validation, reproducibility assessment, and prospective impact studies remain necessary before clinical implementation.
Related
- Preoperative ovarian vascular parameters and perioperative factors associated with ovarian reserve marker decline after laparoscopic endometrioma cystectomy: a retrospective prediction study
- Protocol for an immunocompetent KPC mouse model of pancreatic cancer resection and recurrence for perioperative treatment studies.
- Perioperative parameters to consider for enhanced recovery in surgery (ERS) in gynecology (excluding breast surgery)
- Implausible 100-400 m Performance Times and Inadequate Testing Distances Compromise the Estimation and Interpretation of Critical Velocity. Comment on Amara et al. Relationships Between Dry-Land Load-Velocity Parameters and In-Water Bioenergetic Performance in Competitive Swimmers. Sports 2026, 14, 11.
- High lesion detection rates with preoperative ⁹⁹ᵐTc-PSMA-SPECT/CT prior to radioguided surgery in biochemical recurrence: a hypothesis-generating analysis of quantitative PSMA-PET/CT parameters.
BibTeX
@article{luo2026machine,
title = {{Machine learning model with post-hoc SHAP interpretation based on perioperative clinical and imaging parameters for prediction of 1-year radiographic recurrence after hallux valgus surgery}},
author = {Xuefeng Luo and Xieraili Alimu and Aikebaierjiang Aisaiti},
journal = {Frontiers in Surgery},
year = {2026},
month = oct,
doi = {10.3389/fsurg.2026.1987508},
url = {https://doi.org/10.3389/fsurg.2026.1987508},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning model with post-hoc SHAP interpretation based on perioperative clinical and imaging parameters for prediction of 1-year radiographic recurrence after hallux valgus surgery
AU - Xuefeng Luo
AU - Xieraili Alimu
AU - Aikebaierjiang Aisaiti
PY - 2026
DA - 2026/10/21
JO - Frontiers in Surgery
DO - 10.3389/fsurg.2026.1987508
UR - https://doi.org/10.3389/fsurg.2026.1987508
AB - Objective: Radiographic recurrence after hallux valgus surgery is an important issue affecting long-term imaging outcomes. Previous studies have suggested that preoperative deformity, postoperative residual HVA/IMA, and sesamoid reduction are associated with recurrence, but nonlinear relationships may exist among multiple parameters. The aim of this study was to establish and temporally validate a machine learning prediction model based on conventional perioperative clinical and imaging parameters and to provide post-hoc model interpretation using SHAP. Methods: 597 patients undergoing hallux valgus surgery in the Department of Trauma, First Affiliated Hospital of Xinjiang Medical University from 2021 to 2025 were retrospectively enrolled. Radiographic recurrence was defined as HVA >20° on the fixed 12-month postoperative weight-bearing anteroposterior radiograph. Patients operated from 2021 to 2023 formed the development cohort (n=389), and patients operated from 2024 to 2025 formed the independent temporal-validation cohort (n=208). Eighteen candidate predictors were screened in the development cohort using collinearity assessment, LASSO, RFE, and permutation importance. A unified eight-feature set was then locked and used for comparison of LR, RF, XGBoost, LightGBM, and SVM using 5-fold outer/3-fold inner nested cross-validation conditional on the fixed feature set. Models were evaluated using ROC-AUC, PR-AUC, Brier score, calibration, and DCA, with post-hoc SHAP-based interpretation of the final SVM. Results: A total of 109 patients met the 1-year radiographic recurrence criterion (18.3%). Eight variables were retained: age, preoperative HVA, preoperative IMA, preoperative DMAA, 6-week postoperative HVA, 6-week postoperative IMA, 6-week postoperative DMAA, and 6-week postoperative sesamoid grade. The development-cohort ROC-AUCs of LR and SVM were 0.908 and 0.906, respectively, with corresponding PR-AUCs of 0.766 and 0.757. SVM was retained as the final model on the basis of its lower Brier score and overall performance profile, without claiming statistical superiority over LR. In the temporal-validation cohort, SVM ROC-AUC was 0.944 (95% CI 0.908–0.973), PR-AUC 0.805, Brier score 0.071, sensitivity 0.892, and specificity 0.842. SHAP showed the largest model contributions for 6-week IMA, HVA, and sesamoid grade. Conclusion: The SVM model with post-hoc SHAP-based interpretation showed promising performance for prediction of fixed 1-year radiographic recurrence using routine clinical and perioperative imaging parameters. Residual IMA, HVA, and sesamoid grade at 6 weeks were leading predictive signals within the model rather than causal determinants of recurrence. The model may support early risk stratification and enhanced follow-up, but multicenter external validation, reproducibility assessment, and prospective impact studies remain necessary before clinical implementation.
SN - 2296-875X
ER -