Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors
Background:. Accurate prediction of postoperative metastasis and mortality risks in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction is essential for guiding adjuvant therapies and managing patient expectations. Current prediction methods are limited by variabil...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer
2025-06-01
|
| Series: | JBJS Open Access |
| Online Access: | http://journals.lww.com/jbjsoa/fulltext/10.2106/JBJS.OA.24.00213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850142312533852160 |
|---|---|
| author | Jiawen Deng, BHSc Myron Moskalyk, BHSc, MSc Madhur Nayan, MD, PhD Ahmed Aoude, MEng, MD, FRCSC Michelle Ghert, MD, FRCSC Sahir Bhatnagar, PhD Anthony Bozzo, MSc, MD, FRCSC |
| author_facet | Jiawen Deng, BHSc Myron Moskalyk, BHSc, MSc Madhur Nayan, MD, PhD Ahmed Aoude, MEng, MD, FRCSC Michelle Ghert, MD, FRCSC Sahir Bhatnagar, PhD Anthony Bozzo, MSc, MD, FRCSC |
| author_sort | Jiawen Deng, BHSc |
| collection | DOAJ |
| description | Background:. Accurate prediction of postoperative metastasis and mortality risks in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction is essential for guiding adjuvant therapies and managing patient expectations. Current prediction methods are limited by variability in patient-specific factors. This study aims to develop and internally validate explainable machine learning (ML) models to predict the 1-year risk of new distant metastases and mortality in these patients.
Methods:. We performed a secondary analysis of data from the Prophylactic Antibiotic Regimens in Tumor Surgery trial, which included 604 patients. Candidate features were selected based on availability and clinical relevance and then narrowed using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Boruta algorithms. Six ML classification algorithms were tuned and calibrated: logistic regression, support vector machines, random forest, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), and neural networks. Models were developed with and without including percent tumor necrosis due to its high missing data rate (>30%). Hyperparameters were tuned using Bayesian optimization. Internal validation was conducted using a 30% hold-out set. Model explainability was assessed using permutation-based feature importance and SHapley Additive exPlanations.
Results:. LightGBM was identified as the best-performing algorithm for both outcomes. For 1-year mortality prediction without percent necrosis, LightGBM achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.78 (95% confidence interval [CI] 0.70-0.86) during cross-validation and 0.72 on internal validation. For distant metastasis prediction, the LightGBM model without percent necrosis achieved an AUC-ROC of 0.77 (95% CI 0.71-0.84) during cross-validation and 0.77 on internal validation. Including percent necrosis did not significantly improve model performance. The top predictors identified were patient age, largest tumor dimension, and tumor stage.
Conclusions:. Explainable ML models can effectively predict the 1-year risk of mortality and new distant metastases in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction. Further external validation and consideration of other data modalities are required before integrating these ML-driven risk assessments into routine clinical practice.
Level of Evidence:. Level II, Prognostic Study. See Instructions for Authors for a complete description of levels of evidence. |
| format | Article |
| id | doaj-art-b990c954f2a44875becce41160093acd |
| institution | OA Journals |
| issn | 2472-7245 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | Wolters Kluwer |
| record_format | Article |
| series | JBJS Open Access |
| spelling | doaj-art-b990c954f2a44875becce41160093acd2025-08-20T02:29:07ZengWolters KluwerJBJS Open Access2472-72452025-06-0110210.2106/JBJS.OA.24.00213JBJSOA2400213Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone TumorsJiawen Deng, BHSc0Myron Moskalyk, BHSc, MSc1Madhur Nayan, MD, PhD2Ahmed Aoude, MEng, MD, FRCSC3Michelle Ghert, MD, FRCSC4Sahir Bhatnagar, PhD5Anthony Bozzo, MSc, MD, FRCSC61 Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada2 Biostatistics Division, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada4 Department of Population Health, NYU Grossman School of Medicine, New York, New York5 Division of Orthopaedic Surgery, McGill University, Montréal, Quebec, Canada6 Division of Orthopaedic Surgery, McMaster University, Hamilton, Ontario, Canada8 Department of Epidemiology and Biostatistics, McGill University, Montréal, Quebec, Canada5 Division of Orthopaedic Surgery, McGill University, Montréal, Quebec, CanadaBackground:. Accurate prediction of postoperative metastasis and mortality risks in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction is essential for guiding adjuvant therapies and managing patient expectations. Current prediction methods are limited by variability in patient-specific factors. This study aims to develop and internally validate explainable machine learning (ML) models to predict the 1-year risk of new distant metastases and mortality in these patients. Methods:. We performed a secondary analysis of data from the Prophylactic Antibiotic Regimens in Tumor Surgery trial, which included 604 patients. Candidate features were selected based on availability and clinical relevance and then narrowed using Least Absolute Shrinkage and Selection Operator (LASSO) regression and Boruta algorithms. Six ML classification algorithms were tuned and calibrated: logistic regression, support vector machines, random forest, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), and neural networks. Models were developed with and without including percent tumor necrosis due to its high missing data rate (>30%). Hyperparameters were tuned using Bayesian optimization. Internal validation was conducted using a 30% hold-out set. Model explainability was assessed using permutation-based feature importance and SHapley Additive exPlanations. Results:. LightGBM was identified as the best-performing algorithm for both outcomes. For 1-year mortality prediction without percent necrosis, LightGBM achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.78 (95% confidence interval [CI] 0.70-0.86) during cross-validation and 0.72 on internal validation. For distant metastasis prediction, the LightGBM model without percent necrosis achieved an AUC-ROC of 0.77 (95% CI 0.71-0.84) during cross-validation and 0.77 on internal validation. Including percent necrosis did not significantly improve model performance. The top predictors identified were patient age, largest tumor dimension, and tumor stage. Conclusions:. Explainable ML models can effectively predict the 1-year risk of mortality and new distant metastases in patients undergoing lower-limb oncological resection and endoprosthetic reconstruction. Further external validation and consideration of other data modalities are required before integrating these ML-driven risk assessments into routine clinical practice. Level of Evidence:. Level II, Prognostic Study. See Instructions for Authors for a complete description of levels of evidence.http://journals.lww.com/jbjsoa/fulltext/10.2106/JBJS.OA.24.00213 |
| spellingShingle | Jiawen Deng, BHSc Myron Moskalyk, BHSc, MSc Madhur Nayan, MD, PhD Ahmed Aoude, MEng, MD, FRCSC Michelle Ghert, MD, FRCSC Sahir Bhatnagar, PhD Anthony Bozzo, MSc, MD, FRCSC Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors JBJS Open Access |
| title | Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors |
| title_full | Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors |
| title_fullStr | Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors |
| title_full_unstemmed | Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors |
| title_short | Development of Explainable Machine Learning Models to Identify Patients at Risk for 1-Year Mortality and New Distant Metastases Postendoprosthetic Reconstruction for Lower Extremity Bone Tumors |
| title_sort | development of explainable machine learning models to identify patients at risk for 1 year mortality and new distant metastases postendoprosthetic reconstruction for lower extremity bone tumors |
| url | http://journals.lww.com/jbjsoa/fulltext/10.2106/JBJS.OA.24.00213 |
| work_keys_str_mv | AT jiawendengbhsc developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors AT myronmoskalykbhscmsc developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors AT madhurnayanmdphd developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors AT ahmedaoudemengmdfrcsc developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors AT michelleghertmdfrcsc developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors AT sahirbhatnagarphd developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors AT anthonybozzomscmdfrcsc developmentofexplainablemachinelearningmodelstoidentifypatientsatriskfor1yearmortalityandnewdistantmetastasespostendoprostheticreconstructionforlowerextremitybonetumors |