Columbia University School of Nursing, New York, NY, USA.
University of Iowa College of Nursing, Iowa City, IA, USA.
AMIA Annu Symp Proc. 2023 Apr 29;2022:552-559. eCollection 2022.
Home healthcare (HHC) agencies provide care to more than 3.4 million adults per year. There is value in studying HHC narrative notes to identify patients at risk for deterioration. This study aimed to build machine learning algorithms to identify "concerning" narrative notes of HHC patients and identify emerging themes. Six algorithms were applied to narrative notes (n = 4,000) from a HHC agency to classify notes as either "concerning" or "not concerning." Topic modeling using Latent Dirichlet Allocation bag of words was conducted to identify emerging themes from the concerning notes. Gradient Boosted Trees demonstrated the best performance with a F-score = 0.74 and AUC = 0.96. Emerging themes were related to patient-clinician communication, HHC services provided, gait challenges, mobility concerns, wounds, and caregivers. Most themes have been cited by previous literature as increasing risk for adverse events. In the future, such algorithms can support early identification of patients at risk for deterioration.
家庭保健（HHC）机构每年为超过 340 万成年人提供护理。研究 HHC 叙述性记录以识别有恶化风险的患者具有重要价值。本研究旨在构建机器学习算法，以识别 HHC 患者的“有关”叙述性记录，并确定新出现的主题。六种算法应用于 HHC 机构的叙述性记录（n=4000），以将记录分类为“有关”或“无关”。使用潜在狄利克雷分配词袋的主题建模用于从有关记录中识别新出现的主题。梯度提升树的表现最佳，F 分数=0.74，AUC=0.96。新兴主题与患者-临床医生沟通、HHC 服务提供、步态挑战、移动性问题、伤口和护理人员有关。大多数主题都被先前的文献引用为增加不良事件风险的因素。在未来，此类算法可以支持对有恶化风险的患者进行早期识别。
