Wang Haosheng, Fan Tingting, Yang Bo, Lin Qiang, Li Wenle, Yang Mingyu
Department of Orthopedics, Taizhou Central Hospital (Affiliated Hospital to Taizhou College), Taizhou, China.
Department of Orthopedics, Baoji City Hospital of Traditional Chinese Medicine, Baoji, China.
Front Med (Lausanne). 2021 Dec 20;8:771608. doi: 10.3389/fmed.2021.771608. eCollection 2021.
Machine Learning (ML) is rapidly growing in capability and is increasingly applied to model outcomes and complications in medicine. Surgical site infections (SSI) are a common post-operative complication in spinal surgery. This study aimed to develop and validate supervised ML algorithms for predicting the risk of SSI following minimally invasive transforaminal lumbar interbody fusion (MIS-TLIF). This single-central retrospective study included a total of 705 cases between May 2012 and October 2019. Data of patients who underwent MIS-TLIF was extracted by the electronic medical record system. The patient's clinical characteristics, surgery-related parameters, and routine laboratory tests were collected. Stepwise logistic regression analyses were used to screen and identify potential predictors for SSI. Then, these factors were imported into six ML algorithms, including k-Nearest Neighbor (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Multi-Layer Perceptron (MLP), and Naïve Bayes (NB), to develop a prediction model for predicting the risk of SSI following MIS-TLIF under Quadrant channel. During the training process, 10-fold cross-validation was used for validation. Indices like the area under the receiver operating characteristic (AUC), sensitivity, specificity, and accuracy (ACC) were reported to test the performance of ML models. Among the 705 patients, SSI occurred in 33 patients (4.68%). The stepwise logistic regression analyses showed that pre-operative glycated hemoglobin A1c (HbA1c), estimated blood loss (EBL), pre-operative albumin, body mass index (BMI), and age were potential predictors of SSI. In predicting SSI, six ML models posted an average AUC of 0.60-0.80 and an ACC of 0.80-0.95, with the NB model standing out, registering an average AUC and an ACC of 0.78 and 0.90. Then, the feature importance of the NB model was reported. ML algorithms are impressive tools in clinical decision-making, which can achieve satisfactory prediction of SSI with the NB model performing the best. The NB model may help access the risk of SSI following MIS-TLIF and facilitate clinical decision-making. However, future external validation is needed.
机器学习（ML）的能力正在迅速发展，并越来越多地应用于医学领域的结果和并发症建模。手术部位感染（SSI）是脊柱手术中常见的术后并发症。本研究旨在开发和验证用于预测微创经椎间孔腰椎椎间融合术（MIS-TLIF）后发生SSI风险的监督式ML算法。这项单中心回顾性研究共纳入了2012年5月至2019年10月期间的705例病例。通过电子病历系统提取接受MIS-TLIF手术患者的数据。收集患者的临床特征、手术相关参数和常规实验室检查结果。采用逐步逻辑回归分析筛选和识别SSI的潜在预测因素。然后，将这些因素输入六种ML算法，包括k近邻（KNN）、决策树（DT）、支持向量机（SVM）、随机森林（RF）、多层感知器（MLP）和朴素贝叶斯（NB），以建立一个预测模型，用于预测象限通道下MIS-TLIF后发生SSI的风险。在训练过程中，采用10折交叉验证进行验证。报告了受试者工作特征曲线下面积（AUC）、敏感性、特异性和准确性（ACC）等指标，以测试ML模型的性能。在705例患者中，33例（4.68%）发生了SSI。逐步逻辑回归分析表明，术前糖化血红蛋白A1c（HbA1c）、估计失血量（EBL）、术前白蛋白、体重指数（BMI）和年龄是SSI的潜在预测因素。在预测SSI方面，六个ML模型的平均AUC为0.60 - 0.80，ACC为0.80 - 0.95，其中NB模型表现突出，平均AUC和ACC分别为0.78和0.90。然后，报告了NB模型的特征重要性。ML算法是临床决策中令人印象深刻的工具，其中NB模型表现最佳，能够对SSI进行令人满意的预测。NB模型可能有助于评估MIS-TLIF后发生SSI的风险，并促进临床决策。然而，未来需要进行外部验证。
