机器学习算法在预测翻修全髋和全膝关节置换术后30天死亡率方面优于CARDE-B、5项和6项改良衰弱指数风险评分
本研究基于美国外科医师学会国家手术质量改进计划数据库2013至2020年接受翻修全关节置换术的成人患者,按80:20随机分为训练集和验证集,开发并评估3种机器学习模型(极端梯度提升、随机森林、弹性网惩罚逻辑回归),并与CARDE-B、5项改良衰弱指数(5MFI)和6MFI评分的判别能力进行比较。结果显示所有机器学习模型准确度相同(Brier评分=0.005)且判别能力出色(AUC:极端梯度提升=0.94,随机森林=弹性网惩罚逻辑回归=0.93);CARDE-B评分判别能力最高(AUC=0.89),其次为6MFI(AUC=0.80)和5MFI(AUC=0.68)。机器学习模型在预测翻修全关节置换术后30天死亡率方面优于传统风险评估指数。
要点
- 机器学习模型预测翻修全关节置换术后30天死亡率AUC达0.93至0.94,优于CARDE-B评分(AUC=0.89)、6MFI(AUC=0.80)和5MFI(AUC=0.68)。
- 白蛋白<3.5 mg/dL和BMI(<30.15)是翻修全关节置换术后30天死亡率最重要的预测因素。
- 弹性网惩罚逻辑回归模型整体校准最佳(斜率=0.54,截距=-0.004)。
核心结论
- 机器学习模型在预测翻修全关节置换术后30天死亡率方面优于传统风险评估指数。
- 研究结果突显机器学习在临床环境中用于风险分层的效用。
- 识别低白蛋白血症和BMI作为预后标志物可能有助于制定患者个体化围手术期优化策略以改善翻修全关节置换术后的结局。
研究设计与样本
- 从美国外科医师学会国家手术质量改进计划数据库选取2013年至2020年接受翻修全关节置换术的成人患者,随机按80:20分为训练集和验证集。
- 开发并评估3种机器学习模型:极端梯度提升、随机森林和弹性网惩罚逻辑回归,使用判别能力、校准指标和准确度进行评价。
- 单独评估CARDE-B、5MFI和6MFI评分的判别能力,并与机器学习模型进行比较。
主要发现
- 所有模型准确度相同(Brier评分=0.005),判别能力出色且受试者工作特征曲线下面积相似(极端梯度提升=0.94,随机森林=弹性网惩罚逻辑回归=0.93)。
- 弹性网惩罚逻辑回归模型整体校准最佳(斜率=0.54,截距=-0.004)。
- CARDE-B评分判别能力最高(AUC=0.89),其次为6MFI(AUC=0.80)和5MFI(AUC=0.68)。
- 白蛋白<3.5 mg/dL和BMI(<30.15)是翻修全关节置换术后30天死亡率最重要的预测因素。
关键数值与推荐
- CARDE-B评分组成:充血性心力衰竭、白蛋白(<3.5 mg/dL)、透析依赖的肾衰竭、日常生活依赖、高龄(>65岁)和体重指数(BMI)<25 kg/m2。
- 机器学习模型AUC:极端梯度提升=0.94,随机森林=0.93,弹性网惩罚逻辑回归=0.93。
- 传统评分AUC:CARDE-B=0.89,6MFI=0.80,5MFI=0.68。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Although risk calculators are used to prognosticate postoperative outcomes following revision total hip and knee arthroplasty (total joint arthroplasty [TJA]), machine learning (ML) based predictive tools have emerged as a promising alternative for improved risk stratification. This study aimed to compare the predictive ability of ML models for 30-day mortality following revision TJA to that of traditional risk-assessment indices such as the CARDE-B score (congestive heart failure, albumin (< 3.5 mg/dL), renal failure on dialysis, dependence for daily living, elderly (> 65 years of age), and body mass index (BMI) of < 25 kg/m2), 5-item modified frailty index (5MFI), and 6MFI. METHODS: Adult patients undergoing revision TJA between 2013 and 2020 were selected from the American College of Surgeons National Surgical Quality Improvement Program database and randomly split 80:20 to compose the training and validation cohorts. There were 3 ML models - extreme gradient boosting, random forest, and elastic-net penalized logistic regression (NEPLR) - that were developed and evaluated using discrimination, calibration metrics, and accuracy. The discrimination of CARDE-B, 5MFI, and 6MFI scores was assessed individually and compared to that of ML models. RESULTS: All models were equally accurate (Brier score = 0.005) and demonstrated outstanding discrimination with similar areas under the receiver operating characteristic curve (AUCs, extreme gradient boosting = 0.94, random forest = NEPLR = 0.93). The NEPLR was the best-calibrated model overall (slope = 0.54, intercept = -0.004). The CARDE-B had the highest discrimination among the scores (AUC = 0.89), followed by 6MFI (AUC = 0.80), and 5MFI (AUC = 0.68). Albumin < 3.5 mg/dL and BMI (< 30.15) were the most important predictors of 30-day mortality following revision TJA. CONCLUSIONS: The ML models outperform traditional risk-assessment indices in predicting postoperative 30-day mortality after revision TJA. Our findings highlight the utility of ML for risk stratification in a clinical setting. The identification of hypoalbuminemia and BMI as prognostic markers may allow patient-specific perioperative optimization strategies to improve outcomes following revision TJA.
引用
- Pean CA, Buddhiraju A, Shimizu MR, et al. Prediction of 30-Day Mortality Following Revision Total Hip and Knee Arthroplasty: Machine Learning Algorithms Outperform CARDE-B, 5-Item, and 6-Item Modified Frailty Index Risk Scores. J Arthroplasty. 2024. PMID: 38797444. doi:10.1016/j.arth.2024.05.056
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。