Department of Surgery, University of Florida, Gainesville, FL.
Department of Medicine, University of Florida, Gainesville, FL; Precision and Intelligent Systems in Medicine (PrismaP), University of Florida, Gainesville FL.
Surgery. 2021 Jul;170(1):298-303. doi: 10.1016/j.surg.2021.01.030. Epub 2021 Feb 27.
Postoperative acute kidney injury is common after major vascular surgery and is associated with increased morbidity, mortality, and cost. High-performance risk stratification using a machine learning model can inform strategies that mitigate harm and optimize resource use. It is hypothesized that incorporating intraoperative data would improve machine learning model accuracy, discrimination, and precision in predicting acute kidney injury among patients undergoing major vascular surgery.
A single-center retrospective cohort of 1,531 adult patients who underwent nonemergency major vascular surgery, including open aortic, endovascular aortic, and lower extremity bypass procedures, was evaluated. The validated, automated MySurgeryRisk analytics platform used electronic health record data to forecast patient-level probabilistic risk scores for postoperative acute kidney injury using random forest models with preoperative data alone and perioperative data (preoperative plus intraoperative). The MySurgeryRisk predictions were compared with each other as well as with the American Society of Anesthesiologists physical status classification.
Machine learning models using perioperative data had greater accuracy, discrimination, and precision than models using either preoperative data alone or the American Society of Anesthesiologists physical status classification (accuracy: 0.70 vs 0.64 vs 0.62, area under the receiver operating characteristics curve: 0.77 vs 0.68 vs 0.61, area under the precision-recall curve: 0.70 vs 0.58 vs 0.48).
In predicting acute kidney injury after major vascular surgery, machine learning approaches that incorporate dynamic intraoperative data had greater accuracy, discrimination, and precision than models using either preoperative data alone or the American Society of Anesthesiologists physical status classification. Machine learning methods have the potential for real-time identification of high-risk patients who may benefit from personalized risk-reduction strategies.
大血管手术后常发生术后急性肾损伤，与发病率、死亡率和医疗费用增加有关。使用机器学习模型进行高性能风险分层可以为减轻伤害和优化资源利用提供策略。研究假设，术中数据的纳入可以提高机器学习模型预测大血管手术后急性肾损伤的准确性、区分度和精度。
对 1531 例接受非紧急大血管手术（包括开放主动脉、血管内主动脉和下肢旁路手术）的成年患者进行了单中心回顾性队列研究。验证后的自动化 MySurgeryRisk 分析平台使用电子病历数据，使用随机森林模型仅使用术前数据和围手术期数据（术前加术中）预测患者术后急性肾损伤的概率风险评分。将 MySurgeryRisk 预测结果与其他预测结果（如美国麻醉医师协会身体状况分类）进行了比较。
使用围手术期数据的机器学习模型比仅使用术前数据或美国麻醉医师协会身体状况分类的模型具有更高的准确性、区分度和精度（准确性：0.70 比 0.64 比 0.62，受试者工作特征曲线下面积：0.77 比 0.68 比 0.61，精度-召回曲线下面积：0.70 比 0.58 比 0.48）。
在预测大血管手术后急性肾损伤方面，纳入动态术中数据的机器学习方法比仅使用术前数据或美国麻醉医师协会身体状况分类的模型具有更高的准确性、区分度和精度。机器学习方法有可能实时识别高危患者，这些患者可能受益于个性化的降低风险策略。
