Kim Jun S, Arvind Varun, Oermann Eric K, Kaji Deepak, Ranson Will, Ukogu Chierika, Hussain Awais K, Caridi John, Cho Samuel K
Department of Orthopaedic Surgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA.
Department of Neurosurgery, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA.
Spine Deform. 2018 Nov-Dec;6(6):762-770. doi: 10.1016/j.jspd.2018.03.003.
Cross-sectional database study.
To train and validate machine learning models to identify risk factors for complications following surgery for adult spinal deformity (ASD).
Machine learning models such as logistic regression (LR) and artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex data sets. ANNs have yet to be used for risk factor analysis in orthopedic surgery.
The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent surgery for ASD. This query returned 4,073 patients, which data were used to train and evaluate our models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American Society of Anesthesiologists (ASA) class >3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating characteristic curves (AUC) was used to determine the accuracy of our machine learning models.
The mean age of patients was 59.5 years. Forty-one percent of patients were male whereas 59.0% of patients were female. ANN and LR outperformed ASA scoring in predicting every complication (p<.05). The ANN outperformed LR in predicting cardiac complication, wound complication, and mortality (p<.05).
Machine learning algorithms outperform ASA scoring for predicting individual risk prognosis. These algorithms also outperform LR in predicting individual risk for all complications except VTE. With the growing size of medical data, the training of machine learning on these large data sets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.
Level III.
横断面数据库研究。
训练并验证机器学习模型，以识别成人脊柱畸形（ASD）手术后并发症的风险因素。
逻辑回归（LR）和人工神经网络（ANNs）等机器学习模型是分析和解释大型复杂数据集的宝贵工具。ANNs尚未用于骨科手术的风险因素分析。
查询美国外科医师学会国家外科质量改进计划（ACS-NSQIP）数据库中接受ASD手术的患者。该查询返回了4073例患者，其数据用于训练和评估我们的模型。使用的预测变量包括性别、年龄、种族、糖尿病、吸烟、类固醇使用、凝血功能障碍、功能状态、美国麻醉医师协会（ASA）分级>3、体重指数（BMI）、肺部合并症和心脏合并症。这些模型用于预测心脏并发症、伤口并发症、静脉血栓栓塞（VTE）和死亡率。以ASA分级作为预测基准，使用受试者操作特征曲线下面积（AUC）来确定我们机器学习模型的准确性。
患者的平均年龄为59.5岁。41%的患者为男性，而59.0%的患者为女性。在预测每种并发症方面，ANN和LR的表现均优于ASA评分（p<0.05）。在预测心脏并发症、伤口并发症和死亡率方面，ANN的表现优于LR（p<0.05）。
机器学习算法在预测个体风险预后方面优于ASA评分。在预测除VTE之外的所有并发症的个体风险方面，这些算法也优于LR。随着医疗数据量的不断增加，在这些大型数据集上进行机器学习训练有望改善风险预测，其持续学习的能力使其成为复杂临床场景中的优秀工具。
三级。
