The Feinstein Institutes for Medical Research, Manhasset, NY; Elmezzi Graduate School of Molecular Medicine, Manhasset, NY; Department of Surgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Manhasset, NY; Department of Cardiovascular and Thoracic Surgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Manhasset, NY.
School of Computing Science, Simon Fraser University, Burnaby, British Columbia, Canada.
J Thorac Cardiovasc Surg. 2021 Jun;161(6):1926-1939.e8. doi: 10.1016/j.jtcvs.2020.04.172. Epub 2020 May 29.
To establish a machine learning (ML)-based prediction model for readmission within 30 days (early readmission or early readmission) of patients based on their profile at index hospitalization for esophagectomy.
Using the National Readmission Database, 383 patients requiring early readmission out of a total of 2037 esophagectomy patients alive at discharge in 2016 were identified. Early readmission risk factors were identified using standard statistics and after the application of ML methodology, the models were interpreted.
Early readmission after esophagectomy connoted an increased severity score and risk of mortality. Chronic obstructive pulmonary disease and malnutrition as well as postoperative prolonged intubation, pneumonia, acute kidney failure, and length of stay were identified as factors most contributing to increased odds of early readmission. The reasons for early readmission were more likely to be cardiopulmonary complications, anastomotic leak, and sepsis/infection. Patients with upper esophageal neoplasms had significantly higher early readmission and patients who received pyloroplasty/pyloromyotomy had significantly lower early readmission. Two ML models to predict early readmission were generated: 1 with 71.7% sensitivity for clinical decision making and the other with 84.8% accuracy and 98.7% specificity for quality review.
We identified risk factors for early readmission after esophagectomy and introduced ML-based techniques to predict early readmission in 2 different settings: clinical decision making and quality review. ML techniques can be utilized to provide targeted support and standardize quality measures.
基于食管癌指数住院患者的特征，建立基于机器学习（ML）的 30 天内（早期再入院或早期再入院）再入院预测模型。
使用国家再入院数据库，从 2016 年出院时存活的 2037 例食管癌患者中确定了 383 例需要早期再入院的患者。使用标准统计学方法和 ML 方法学应用后，确定早期再入院的危险因素，并对模型进行解释。
食管癌手术后的早期再入院意味着严重程度评分增加和死亡率增加。慢性阻塞性肺疾病和营养不良以及术后长时间插管、肺炎、急性肾衰竭和住院时间延长被确定为增加早期再入院几率的主要因素。早期再入院的原因更可能是心肺并发症、吻合口漏和脓毒症/感染。上食管肿瘤患者的早期再入院率明显较高，接受幽门成形术/幽门肌切开术的患者的早期再入院率明显较低。生成了 2 个用于预测早期再入院的 ML 模型：1 个用于临床决策的模型，灵敏度为 71.7%；另一个用于质量审查的模型，准确性为 84.8%，特异性为 98.7%。
我们确定了食管癌手术后早期再入院的危险因素，并在临床决策和质量审查的 2 种不同情况下引入了基于 ML 的技术来预测早期再入院。ML 技术可用于提供针对性支持和标准化质量措施。
