人工神经网络预测初次全膝关节置换术后当日出院
本研究基于2018年NSQIP数据库,纳入28,742例因原发性骨关节炎行初次择期单侧全膝关节置换术的患者,利用人工神经网络模型分析术前和术中变量以预测当日出院,并与逻辑回归模型比较。ANN模型AUC为0.801,与逻辑回归模型(AUC=0.796)相似,识别出预测当日出院的重要因素。
要点
- ANN模型预测当日出院的AUC为0.801,与逻辑回归模型(AUC=0.796)相似。
- ANN模型中最重要的预测因素包括术前钠、INR、BMI、年龄、麻醉类型等。
- 逻辑回归分析中,ANN识别的前10个因素中有6个也具有统计学显著性。
核心结论
- ANN建模和逻辑回归分析均揭示了预测患者可安全进行门诊TKA当日出院的重要临床因素。
研究设计与样本
- 回顾性分析2018年NSQIP数据库,纳入28,742例因原发性骨关节炎行初次择期单侧TKA的患者,使用ANN模型与逻辑回归模型比较预测当日出院。
主要发现
- ANN模型AUC=0.801,逻辑回归模型AUC=0.796,两者预测能力相似。
- ANN模型中最重要的10个预测因素包括术前钠、术前INR、BMI、年龄、麻醉类型、手术时间、呼吸困难状态、功能状态、种族、贫血状态和COPD。
- 上述10个因素中有6个在逻辑回归分析中也具有显著性。
关键数值与推荐
- ANN模型AUC=0.801,逻辑回归模型AUC=0.796。
- ANN模型识别的10个最重要因素:术前钠、术前INR、BMI、年龄、麻醉类型、手术时间、呼吸困难状态、功能状态、种族、贫血状态、COPD。
临床怎么用
- ANN模型可作为辅助工具,帮助识别适合当日出院的TKA患者。
- 术前钠、INR、BMI、年龄、麻醉类型等变量可用于评估当日出院可能性。
局限性
- 研究基于2018年NSQIP数据库,结论可能受当时围手术期康复方案限制。
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
AIMS: This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA). METHODS: Data for this study were collected from the National Surgery Quality Improvement Program (NSQIP) database from the year 2018. Patients who received a primary, elective, unilateral TKA with a diagnosis of primary osteoarthritis were included. Demographic, preoperative, and intraoperative variables were analyzed. The ANN model was compared to a logistic regression model, which is a conventional machine-learning algorithm. Variables collected from 28,742 patients were analyzed based on their contribution to hospital length of stay. RESULTS: The predictability of the ANN model, area under the curve (AUC) = 0.801, was similar to the logistic regression model (AUC = 0.796) and identified certain variables as important factors to predict same-day discharge. The ten most important factors favouring same-day discharge in the ANN model include preoperative sodium, preoperative international normalized ratio, BMI, age, anaesthesia type, operating time, dyspnoea status, functional status, race, anaemia status, and chronic obstructive pulmonary disease (COPD). Six of these variables were also found to be significant on logistic regression analysis. CONCLUSION: Both ANN modelling and logistic regression analysis revealed clinically important factors in predicting patients who can undergo safely undergo same-day discharge from an outpatient TKA. The ANN model provides a beneficial approach to help determine which perioperative factors can predict same-day discharge as of 2018 perioperative recovery protocols. Cite this article: Bone Joint J 2021;103-B(8):1358-1366.
引用
- Wei C, Quan T, Wang KY, et al. Artificial neural network prediction of same-day discharge following primary total knee arthroplasty based on preoperative and intraoperative variables. Bone Joint J. 2021. PMID: 34334050. doi:10.1302/0301-620X.103B8.BJJ-2020-1013.R2
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。