Department of Orthopaedic Surgery, Mayo Clinic, Rochester, MN, USA.
Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA.
Knee Surg Sports Traumatol Arthrosc. 2021 Sep;29(9):2958-2966. doi: 10.1007/s00167-020-06321-w. Epub 2020 Oct 12.
Overnight admission following anterior cruciate ligament reconstruction has implications on clinical outcomes as well as cost benefit, yet there are few validated risk calculators for reliable identification of appropriate candidates. The purpose of this study is to develop and validate a machine learning algorithm that can effectively identify patients requiring admission following elective anterior cruciate ligament (ACL) reconstruction.
A retrospective review of a national surgical outcomes database was performed to identify patients who underwent elective ACL reconstruction from 2006 to 2018. Patients admitted overnight postoperatively were identified as those with length of stay of 1 or more days. Models were generated using random forest (RF), extreme gradient boosting (XGBoost), linear discriminant classifier (LDA), and adaptive boosting algorithms (AdaBoost), and an additional model was produced as a weighted ensemble of the four final algorithms.
Overall, of the 4,709 patients included, 531 patients (11.3%) required at least one overnight stay following ACL reconstruction. The factors determined most important for identification of candidates for inpatient admission were operative time, anesthesia type, age, gender, and BMI. Smoking history, history of COPD, and history of coagulopathy were identified as less important variables. The following factors supported overnight admission: operative time > 200 min, age < 35.8 or > 53.5 years, male gender, BMI < 25 or > 31.2 kg/m, positive smoking history, history of COPD and the presence of preoperative coagulopathy. The ensemble model achieved the best performance based on discrimination assessed via internal validation (AUC = 0.76), calibration, and decision curve analysis. The model was integrated into a web-based open-access application able to provide both predictions and explanations.
Modifiable risk factors identified by the model such as increased BMI, operative time, anesthesia type, and comorbidities can help clinicians optimize preoperative status to prevent costs associated with unnecessary admissions. If externally validated in independent populations, this algorithm could use these inputs to guide preoperative screening and risk stratification to identify patients requiring overnight admission for observation following ACL reconstruction.
IV.
前交叉韧带重建术后的住院过夜与临床结果和成本效益都有关，但是目前还没有经过验证的风险计算器可以可靠地识别合适的患者。本研究旨在开发和验证一种机器学习算法，以便有效地识别需要接受择期前交叉韧带（ACL）重建术后住院治疗的患者。
对全国手术结果数据库进行回顾性分析，以确定 2006 年至 2018 年间接受择期 ACL 重建的患者。术后住院过夜的患者定义为住院时间超过 1 天的患者。使用随机森林（RF）、极端梯度增强（XGBoost）、线性判别分类器（LDA）和自适应提升算法（AdaBoost）生成模型，并将另外一个模型作为四个最终算法的加权集成模型。
共有 4709 例患者纳入研究，其中 531 例（11.3%）患者在 ACL 重建后需要至少住院过夜 1 天。确定最适合识别住院患者的候选因素是手术时间、麻醉类型、年龄、性别和 BMI。吸烟史、COPD 病史和凝血障碍史被确定为不太重要的变量。以下因素支持患者住院过夜：手术时间>200 分钟，年龄<35.8 岁或>53.5 岁，男性，BMI<25 或>31.2kg/m，有吸烟史、COPD 病史和术前凝血障碍。基于内部验证评估的判别力（AUC=0.76）、校准和决策曲线分析，集成模型的性能最佳。该模型集成到一个基于网络的开放访问应用程序中，能够提供预测和解释。
该模型确定的可改变的风险因素，如 BMI 增加、手术时间、麻醉类型和合并症，可帮助临床医生优化术前状态，以避免不必要的住院治疗相关费用。如果在独立人群中进行外部验证，该算法可以使用这些输入来指导 ACL 重建术后的术前筛查和风险分层，以识别需要住院过夜观察的患者。
IV。
