Bioengineering Laboratory, Department of Orthopaedic Surgery, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts.
J Arthroplasty. 2023 Jun;38(6S):S253-S258. doi: 10.1016/j.arth.2023.02.054. Epub 2023 Feb 25.
Postoperative discharge to facilities account for over 33% of the $ 2.7 billion revision total knee arthroplasty (TKA)-associated annual expenditures and are associated with increased complications when compared to home discharges. Prior studies predicting discharge disposition using advanced machine learning (ML) have been limited due to a lack of generalizability and validation. This study aimed to establish ML model generalizability by externally validating its prediction for nonhome discharge following revision TKA using national and institutional databases.
The national and institutional cohorts comprised 52,533 and 1,628 patients, respectively, with 20.6 and 19.4% nonhome discharge rates. Five ML models were trained and internally validated (five-fold cross-validation) on a large national dataset. Subsequently, external validation was performed on our institutional dataset. Model performance was assessed using discrimination, calibration, and clinical utility. Global predictor importance plots and local surrogate models were used for interpretation.
The strongest predictors of nonhome discharge were patient age, body mass index, and surgical indication. The area under the receiver operating characteristic curve increased from internal to external validation and ranged between 0.77 and 0.79. Artificial neural network was the best predictive model for identifying patients at risk for nonhome discharge (area under the receiver operating characteristic curve = 0.78), and also the most accurate (calibration slope = 0.93, intercept = 0.02, and Brier score = 0.12).
All five ML models demonstrated good-to-excellent discrimination, calibration, and clinical utility on external validation, with artificial neural network being the best model for predicting discharge disposition following revision TKA. Our findings establish the generalizability of ML models developed using data from a national database. The integration of these predictive models into clinical workflow may assist in optimizing discharge planning, bed management, and cost containment associated with revision TKA.
在 2.7 亿美元的全膝关节翻修术（TKA）相关年度支出中，术后至医疗机构的出院占比超过 33%，与家庭出院相比，这种出院方式与并发症的增加有关。先前使用先进的机器学习（ML）预测出院去向的研究由于缺乏通用性和验证而受到限制。本研究旨在通过使用国家和机构数据库对外科翻修 TKA 后非家庭出院的预测结果进行验证，从而建立 ML 模型的通用性。
国家和机构队列分别包含 52533 例和 1628 例患者，非家庭出院率分别为 20.6%和 19.4%。在一个大型的国家数据库上，我们训练和内部验证了 5 个 ML 模型（五分交叉验证）。随后，在我们的机构数据集上进行了外部验证。使用判别能力、校准和临床实用性来评估模型性能。全局预测因子重要性图和局部替代模型用于解释。
非家庭出院的最强预测因子是患者年龄、体重指数和手术指征。从内部验证到外部验证，受试者工作特征曲线下面积增加，范围在 0.77 到 0.79 之间。人工神经网络是识别非家庭出院风险患者的最佳预测模型（受试者工作特征曲线下面积为 0.78），也是最准确的模型（校准斜率为 0.93，截距为 0.02，Brier 评分 0.12）。
所有 5 个 ML 模型在外部验证中均表现出良好到优秀的判别能力、校准能力和临床实用性，其中人工神经网络是预测 TKA 翻修后出院去向的最佳模型。我们的研究结果证实了使用来自国家数据库的数据开发的 ML 模型的通用性。将这些预测模型整合到临床工作流程中，可能有助于优化与 TKA 翻修相关的出院计划、床位管理和成本控制。
