Explainable machine learning-based prediction of early and mid-term postoperative complications in adolescent tibial fractures
Authors:
Open Access
- 21 October 2025
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Surgery
- Vol. 12, 1688702
Abstract
Background: Adolescent tibial fractures commonly lead to postoperative complications. Conventional coagulation markers (PT/APTT/FIB) lack combinatorial risk assessment. We developed an explainable ML model integrating coagulation and clinical features to predict adverse events.Methods: A retrospective cohort of 624 surgical patients (13–18 years) was analyzed. AutoML with Improved Harmony Search Optimization (IHSO) processed features: age, fracture classification, surgery duration, blood loss, and 24 h-postoperative labs (coagulation triad/D-dimer/CRP). Primary outcome: 90-day composite adverse events (DVT/infection/early callus formation disorder/reoperation). SHAP explained predictions.Results: Baseline characteristics were balanced between training and test sets (P > 0.05). The IHSO-optimized algorithm outperformed controls in 91.67% of CEC2022 benchmark functions. AutoML model performance significantly surpassed conventional methods: training set ROC-AUC: 0.9667, test set ROC-AUC: 0.9247 (PR-AUC: 0.8350). Decision curves demonstrated clinical net benefit across 6%–99% risk thresholds. Key feature importance ranked as: age > operative duration > fibrinogen > fracture classification > APTT > CRP > BMI > D-dimer. SHAP analysis revealed: 1) Increasing age significantly attenuates the risk contribution of surgery duration; 2) FIB >4.0 g/L + elevated CRP indicated coagulation-inflammation cascade; 3) AO-C type fractures carried highest risk.Conclusion: This AutoML model, validated through explainability techniques, confirms the core predictive value of age, operative duration, and coagulation-inflammation networks for adolescent tibial fracture risk management. Though requiring prospective validation, the three-tier warning system establishes a stepped framework for individualized intervention. Future studies should advance multicenter collaborations integrating dynamic monitoring indicators to optimize clinical applicability.Keywords
This publication has 30 references indexed in Scilit:
- Holistic swarm optimization: A novel metaphor-less algorithm guided by whole population information for addressing exploration-exploitation dilemmaComputer Methods in Applied Mechanics and Engineering, 2025
- Bivariate genome-wide association study of circulating fibrinogen and C-reactive protein levelsJournal of Thrombosis and Haemostasis, 2024
- Revisiting CEC 2022 ranking: A new ranking method and influence of parameter tuningSwarm and Evolutionary Computation, 2024
- Preoperative fibrinogen/CRP score predicts survival in upper urothelial tract carcinoma patients undergoing radical curative surgeryWorld Journal of Urology, 2023
- Tibial tubercle fractures are sports injuries in male adolescents with a considerable risk of complications and reoperations: a systematic reviewKnee Surgery, Sports Traumatology, Arthroscopy, 2023
- Epidemiology and treatment of pediatric tibial fractures in Sweden: a nationwide population-based study on 5828 fractures from the Swedish Fracture RegisterEuropean Journal of Trauma and Emergency Surgery, 2022
- Explainable artificial intelligence (XAI) in deep learning-based medical image analysisMedical Image Analysis, 2022
- Fracture nonunion in long bones: A literature review of risk factors and surgical managementInjury, 2021
- Harris hawks optimization: Algorithm and applicationsFuture Generation Computer Systems, 2019
- The Whale Optimization AlgorithmAdvances in Engineering Software, 2016