Maxim Topaz, PhD, RN, is Associate Professor, Columbia University School of Nursing, New York City, New York. Kyungmi Woo, PhD, RN, CCM, is Postdoctoral Scientist, Columbia University School of Nursing, New York City, New York. Miriam Ryvicker, PhD, is Senior Researcher, Center for Home Care Policy & Research, Visiting Nurse Service of New York, New York City. Maryam Zolnoori, PhD, is Postdoctoral Scientist, Columbia University School of Nursing, New York City, New York. Kenrick Cato, PhD, RN, FAAN, is Assistant Professor, Columbia University School of Nursing, New York City, New York.
Nurs Res. 2020 Nov/Dec;69(6):448-454. doi: 10.1097/NNR.0000000000000470.
About 30% of home healthcare patients are hospitalized or visit an emergency department (ED) during a home healthcare (HHC) episode. Novel data science methods are increasingly used to improve identification of patients at risk for negative outcomes.
The aim of the study was to identify patients at heightened risk hospitalization or ED visits using HHC narrative data (clinical notes).
This study used a large database of HHC visit notes (n = 727,676) documented for 112,237 HHC episodes (89,459 unique patients) by clinicians of the largest nonprofit HHC agency in the United States. Text mining and machine learning algorithms (Naïve Bayes, decision tree, random forest) were implemented to predict patient hospitalization or ED visits using the content of clinical notes. Risk factors associated with hospitalization or ED visits were identified using a feature selection technique (gain ratio attribute evaluation).
Best performing text mining method (random forest) achieved good predictive performance. Seven risk factors categories were identified, with clinical factors, coordination/communication, and service use being the most frequent categories.
This study was the first to explore the potential contribution of HHC clinical notes to identifying patients at risk for hospitalization or an ED visit. Our results suggest that HHC visit notes are highly informative and can contribute significantly to identification of patients at risk. Further studies are needed to explore ways to improve risk prediction by adding more data elements from additional data sources.
大约 30%的家庭保健患者在家庭保健（HHC）期间住院或前往急诊部（ED）。新颖的数据科学方法越来越多地用于改善对负面结果风险患者的识别。
本研究旨在使用 HHC 叙述数据（临床记录）识别有住院或 ED 就诊风险的患者。
本研究使用了美国最大的非营利性 HHC 机构的临床医生记录的大量 HHC 就诊记录数据库（n=727676），这些记录与 112237 个 HHC 病例（89459 个独特患者）相关。文本挖掘和机器学习算法（朴素贝叶斯、决策树、随机森林）被用于使用临床记录的内容预测患者的住院或 ED 就诊。使用特征选择技术（增益比属性评估）确定与住院或 ED 就诊相关的风险因素。
表现最佳的文本挖掘方法（随机森林）实现了良好的预测性能。确定了七个风险因素类别，其中临床因素、协调/沟通和服务使用是最常见的类别。
本研究首次探索了 HHC 临床记录对识别有住院或 ED 就诊风险的患者的潜在贡献。我们的结果表明，HHC 就诊记录非常有信息量，可以为识别风险患者做出重大贡献。需要进一步研究以探索通过添加来自其他数据源的更多数据元素来改善风险预测的方法。
