Gould Daniel J, Bailey James A, Spelman Tim, Bunzli Samantha, Dowsey Michelle M, Choong Peter F M
Department of Surgery, St Vincent's Hospital Melbourne, University of Melbourne, Level 2 Clinical Sciences Building, 29 Regent Street, Fitzroy, VIC, 3065, Australia.
School of Computing and Information Systems, University of Melbourne, Doug McDonell Building, Parkville, VIC, 3052, Australia.
Arthroplasty. 2023 Jun 1;5(1):30. doi: 10.1186/s42836-023-00186-3.
Thirty-day readmission is an increasingly important problem for total knee arthroplasty (TKA) patients. The aim of this study was to develop a risk prediction model using machine learning and clinical insight for 30-day readmission in primary TKA patients.
Data used to train and internally validate a multivariable predictive model were obtained from a single tertiary referral centre for TKA located in Victoria, Australia. Hospital administrative data and clinical registry data were utilised, and predictors were selected through systematic review and subsequent consultation with clinicians caring for TKA patients. Logistic regression and random forest models were compared to one another. Calibration was evaluated by visual inspection of calibration curves and calculation of the integrated calibration index (ICI). Discriminative performance was evaluated using the area under the receiver operating characteristic curve (AUC-ROC).
The models developed in this study demonstrated adequate calibration for use in the clinical setting, despite having poor discriminative performance. The best-calibrated readmission prediction model was a logistic regression model trained on administrative data using risk factors identified from systematic review and meta-analysis, which are available at the initial consultation (ICI = 0.012, AUC-ROC = 0.589). Models developed to predict complications associated with readmission also had reasonable calibration (ICI = 0.012, AUC-ROC = 0.658).
Discriminative performance of the prediction models was poor, although machine learning provided a slight improvement. The models were reasonably well calibrated, meaning they provide accurate patient-specific probabilities of these outcomes. This information can be used in shared clinical decision-making for discharge planning and post-discharge follow up.
对于全膝关节置换术（TKA）患者而言，30天再入院是一个日益重要的问题。本研究的目的是利用机器学习和临床见解，为初次TKA患者的30天再入院情况开发一种风险预测模型。
用于训练和内部验证多变量预测模型的数据来自澳大利亚维多利亚州一家单一的TKA三级转诊中心。利用医院管理数据和临床登记数据，并通过系统综述以及随后与护理TKA患者的临床医生协商来选择预测因素。对逻辑回归模型和随机森林模型进行了比较。通过校准曲线的目视检查和综合校准指数（ICI）的计算来评估校准情况。使用受试者操作特征曲线下面积（AUC-ROC）评估判别性能。
尽管判别性能较差，但本研究中开发的模型在临床环境中显示出足够的校准。校准最佳的再入院预测模型是一个逻辑回归模型，该模型基于系统综述和荟萃分析确定的风险因素，利用管理数据进行训练，这些因素在初次会诊时即可获得（ICI = 0.012，AUC-ROC = 0.589）。为预测与再入院相关的并发症而开发的模型也具有合理的校准（ICI = 0.012，AUC-ROC = 0.658）。
预测模型的判别性能较差，尽管机器学习略有改进。这些模型校准良好，这意味着它们能够提供针对这些结果的准确的患者特异性概率。此信息可用于出院计划和出院后随访的共同临床决策。
