Pritzker School of Medicine, University of Chicago, Chicago, IL, USA.
Department of Medicine, Section of Pulmonary/Critical Care, University of Chicago, Chicago, IL, USA.
Int J Chron Obstruct Pulmon Dis. 2022 Oct 20;17:2701-2709. doi: 10.2147/COPD.S379700. eCollection 2022.
Chronic obstructive pulmonary disease (COPD) is a leading cause of hospital readmissions. Few existing tools use electronic health record (EHR) data to forecast patients' readmission risk during index hospitalizations.
We used machine learning and in-hospital data to model 90-day risk for and cause of readmission among inpatients with acute exacerbations of COPD (AE-COPD).
Retrospective cohort study.
Adult patients admitted for AE-COPD at the University of Chicago Medicine between November 7, 2008 and December 31, 2018 meeting International Classification of Diseases (ICD)-9 or -10 criteria consistent with AE-COPD were included.
Random forest models were fit to predict readmission risk and respiratory-related readmission cause. Predictor variables included demographics, comorbidities, and EHR data from patients' index hospital stays. Models were derived on 70% of observations and validated on a 30% holdout set. Performance of the readmission risk model was compared to that of the HOSPITAL score.
Among 3238 patients admitted for AE-COPD, 1103 patients were readmitted within 90 days. Of the readmission causes, 61% (n = 672) were respiratory-related and COPD (n = 452) was the most common. Our readmission risk model had a significantly higher area under the receiver operating characteristic curve (AUROC) (0.69 [0.66, 0.73]) compared to the HOSPITAL score (0.63 [0.59, 0.67]; = 0.002). The respiratory-related readmission cause model had an AUROC of 0.73 [0.68, 0.79].
Our models improve on current tools by predicting 90-day readmission risk and cause at the time of discharge from index admissions for AE-COPD. These models could be used to identify patients at higher risk of readmission and direct tailored post-discharge transition of care interventions that lower readmission risk.
慢性阻塞性肺疾病（COPD）是导致医院再入院的主要原因。现有的少数工具利用电子健康记录（EHR）数据来预测患者在住院期间的再入院风险。
我们利用机器学习和住院数据，为因 COPD 急性加重（AE-COPD）住院的患者建立 90 天内再入院风险和再入院原因的模型。
回顾性队列研究。
2008 年 11 月 7 日至 2018 年 12 月 31 日期间，因符合 AE-COPD 的国际疾病分类（ICD）第 9 或 10 版标准而在芝加哥大学医学中心住院治疗的 AE-COPD 成年患者。
随机森林模型用于预测再入院风险和与呼吸系统相关的再入院原因。预测变量包括患者住院期间的人口统计学、合并症和 EHR 数据。模型在 70%的观察值上进行拟合，在 30%的保留集上进行验证。比较了再入院风险模型与 HOSPITAL 评分的性能。
在 3238 名因 AE-COPD 住院的患者中，有 1103 名在 90 天内再次入院。再入院原因中，61%（n=672）与呼吸系统相关，最常见的原因是 COPD（n=452）。我们的再入院风险模型的接收者操作特征曲线下面积（AUROC）显著高于 HOSPITAL 评分（0.69[0.66，0.73]与 0.63[0.59，0.67]；=0.002）。与呼吸系统相关的再入院原因模型的 AUROC 为 0.73[0.68，0.79]。
我们的模型通过预测 AE-COPD 指数住院患者出院时的 90 天再入院风险和原因，改进了现有的工具。这些模型可用于识别再入院风险较高的患者，并为其提供有针对性的出院后过渡护理干预措施，以降低再入院风险。
