The Utility of Nursing Notes Among Medicare Patients With Heart Failure to Predict 30-Day Rehospitalization: A Pilot Study.
The Utility of Nursing Notes Among Medicare Patients With Heart Failure to Predict 30-Day Rehospitalization: A Pilot Study.
复制标题
DOI：
10.1097/jcn.0000000000000871
复制
发表时间：
2022-11-01
影响因子：
2
通讯作者：
Hurdle, John
中科院分区：
文献类型：
--
作者：
Kang, Youjeong;Topaz, Maxim;Dunbar, Sandra B.;Stehlik, Josef;Hurdle, John
对于心力衰竭（HF）患者，已经努力降低30天再住院的风险，例如开发使用电子健康记录的预测模型。以前很少有研究使用临床记录来预测30天的再住院。评估护理记录与出院总结对预测心衰患者30天再住院的效用。本初步研究使用从一家三级医院收集的自由文本出院摘要和护理记录。我们随机选择了500名患有心衰的医保患者。我们遵循自然语言处理和机器学习管道进行数据分析。使用出院总结（n= 500）进行30天再住院风险预测的AUC为0.74 （BOW +神经网络）。使用护理笔记进行30天再住院风险预测（n = 2046）， AUC为0.85 （BOW +神经网络）。与出院总结相比，护理记录为HF患者30天再住院的风险模型提供了更好的输入。
For patients with heart failure (HF), there have been efforts to reduce risk of 30-day rehospitalization such as developing predictive models using electronic health records. Few previous studies used clinical notes to predict 30-day rehospitalization. To assess the utility of nursing notes versus discharge summaries to predict 30-day rehospitalization among patients with HF. This pilot study used free-text discharge summaries and nursing notes collected from a tertiary hospital. We randomly selected 500 Medicare patients with HF. We followed the natural language processing and machine learning pipeline for data analysis. 30-day rehospitalization risk prediction using discharge summaries (n= 500) produced an AUC of 0.74 (BOW + Neural Network). 30-day rehospitalization risk prediction using nursing notes (n = 2,046) resulted in AUC of 0.85 (BOW + Neural Network). Nursing notes provide a superior input to risk models for 30-day rehospitalization in Medicare patients with HF compared to discharge summaries.