Goker Barlas, Brook Andrew, Zhang Ranxin, Aasman Boudewijn, Wang Jichuan, Ferrena Alexander, Mirhaji Parsa, Yang Rui, Hoang Bang H, Geller David S
Department of Orthopedic Surgery, Montefiore Medical Center, Bronx, New York, USA.
Albert Einstein College of Medicine, Bronx, New York, USA.
J Surg Oncol. 2025 Jul;132(1):226-234. doi: 10.1002/jso.70001. Epub 2025 Jun 12.
Endoprosthetic reconstruction is the preferred approach for limb salvage surgery for many patients following malignant bone tumor resection. Implant failure is a common complication, however, there are no reliable means with which to offer patient-specific survival estimations. Implant survival predictions can set patient expectations and may guide treatment planning. This study aims to test and compare machine-learning models for the prediction of early tumor endoprosthetic implant survival.
A single-center retrospective series of 138 cases (mean age 41, 70 males, 68 females) was split into an 80:20 training and testing set. XGBoost, random forest, decision tree learning, and logistic regression were trained and assessed for model performance. After an initial review, age, sex, body mass index, diagnosis, location, resection length, and number of surgeries were selected as features. The output variables were 12-month, 24-month, and 36-month implant survival.
Random forest had the best performance at 12, 24, and 36 months with an area under the curve (AUC) of 0.96, 0.89, 0.88; accuracy of 0.92, 0.83, 0.75; and Brier score of 0.09, 0.11, 0.20, respectively. Overall, the models performed better at 12 months compared to the other time points. The most important feature at 12 months was resection length (0.17), whereas age was most important at 24 months (0.15) and 36 months (0.17). Online tools were created based on the random forest models.
Machine learning models can be leveraged for the accurate prediction of early tumor endoprosthetic survival. These represent the first ML models used to predict endoprosthetic implant survival beyond 1 year and the first to include upper extremity implants. This offers better patient-specific prognostication which can help manage patient expectations and may guide recommendations.
Level III.
对于许多恶性骨肿瘤切除术后的患者，内置假体重建是保肢手术的首选方法。然而，植入物失败是一种常见并发症，目前尚无可靠方法来提供针对患者的生存估计。植入物生存预测可以设定患者预期，并可能指导治疗计划。本研究旨在测试和比较用于预测早期肿瘤内置假体植入物生存的机器学习模型。
一项单中心回顾性系列研究，共138例患者（平均年龄41岁，男性70例，女性68例），分为80:20的训练集和测试集。对XGBoost、随机森林、决策树学习和逻辑回归进行训练，并评估模型性能。经过初步审查，选择年龄、性别、体重指数、诊断、位置、切除长度和手术次数作为特征。输出变量为12个月、24个月和36个月的植入物生存情况。
随机森林在12个月、24个月和36个月时表现最佳，曲线下面积（AUC）分别为0.96、0.89、0.88；准确率分别为0.92、0.83、0.75；布里尔评分分别为0.09、0.11、0.20。总体而言，模型在12个月时的表现优于其他时间点。12个月时最重要的特征是切除长度（0.17），而24个月（0.15）和36个月（0.17）时年龄最为重要。基于随机森林模型创建了在线工具。
机器学习模型可用于准确预测早期肿瘤内置假体的生存情况。这些是首批用于预测超过1年的内置假体植入物生存情况的机器学习模型，也是首批纳入上肢植入物的模型。这提供了更好的针对患者的预后评估，有助于管理患者预期，并可能指导建议。
三级。
