利用自然语言处理识别失代偿期肝硬化患者严肃疾病沟通记录
NLP在4个SIC领域的F1分数为0.91至1.0,每例患者耗时6.8分钟,而人工回顾需41.5分钟。NLP高效且准确,可用于质量改进和临床试验。
要点
- NLP识别SIC记录的F1分数为0.91至1.0,与人工回顾相当。
- NLP每例患者耗时6.8分钟,显著少于人工回顾的41.5分钟。
核心结论
- NLP在识别失代偿期肝硬化患者电子健康记录中的SIC记录方面,与人工病历回顾一样准确且更高效。
主要发现
- NLP在4个SIC领域(治疗目标对话、代码状态限制、专科姑息治疗参与、临终关怀评估)的F1分数为0.91至1.0。
- NLP识别SIC记录每例患者需6.8分钟,人工病历回顾需41.5分钟。
临床怎么用
- NLP可高效准确地识别SIC记录,适用于大规模质量改进项目和临床试验。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
INTRODUCTION: Given the high mortality of patients with decompensated cirrhosis (DC), there is increasing focus on improving serious illness communication (SIC) for this population. However, SIC documentation in the electronic health record (EHR) is often unstructured and difficult to find. We aimed to evaluate the ability to use natural language processing (NLP) to identify SIC documentation in clinical notes from patients with DC. METHODS: In a single-center cohort of adult patients with DC who were evaluated for liver transplantation between January 1, 2010 and December 31, 2017 and died by June 30, 2018, we developed a semiautomated NLP approach to identify SIC documentation in clinical notes. All inpatient and outpatient notes from 1 year until 3 days before death were extracted from the EHR. NLP software with semiautomated chart review was applied to identify SIC documentation across 4 domains: goals of care conversations, code status limitations, specialist palliative care involvement, and hospice assessment. The performance of NLP was compared with gold standard manual chart review. RESULTS: One hundred ninety-six unique patients with 14,062 notes were included in the study. In the gold standard data set, NLP achieved F1 scores ranging from 0.91 to 1.0 across all 4 SIC domains. Identification of SIC documentation required 6.8 minutes per patient using NLP, compared with 41.5 minutes per patient using manual chart review. Forty-eight percent of patients had no SIC documentation. DISCUSSION: NLP is more efficient and as accurate as manual chart review for identifying SIC documentation in the EHR for patients with DC and can be used at scale for quality improvement initiatives and clinical trials.
引用
- Smith L, Sciacca K, Durieux BN, et al. Harnessing Natural Language Processing to Identify Documentation of Serious Illness Communication for Patients With Decompensated Cirrhosis. Am J Gastroenterol. 2025. PMID: 41235801. doi:10.14309/ajg.0000000000003830
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。