文献速递白内障与屈光手术

利用自然语言处理在电子健康记录中识别不同的晶状体病理

Using Natural Language Processing to Identify Different Lens Pathology in Electronic Health Records.
PubMed 文献 · Am J Ophthalmol · 2024-02-01

该数据库研究开发了一种自然语言处理(NLP)算法,用于搜索电子健康记录中自由文本的晶状体检查数据,以识别白内障类型、密度、人工晶状体及其他晶状体病理。在4314条晶状体检查记录中,NLP算法正确识别了全部晶状体病理的占95.1%,识别晶状体病理的敏感度为0.98(0.96-0.99),高于计费代码的0.49(0.46-0.53)。

要点

  • NLP算法在4104/4314条记录中正确识别所有晶状体病理,占95.1%。
  • NLP识别晶状体病理的敏感度0.98(0.96-0.99),计费代码为0.49(0.46-0.53)。
  • 对少见晶状体病理,临床医生复核确认假性剥脱物质提及的100%及瞳孔闭锁、半脱位、粘连的99.7%。

核心结论

  • NLP算法能高准确度地识别和分类眼科专业人员常规记录的晶状体异常。
  • 此类算法有助于研究人员正确识别和分类眼部病理,拓宽使用真实世界数据的可行研究范围。

研究设计与样本

  • 数据库研究,比较NLP与ICD计费代码准确识别晶状体病理的能力。
  • 开发NLP算法搜索电子健康记录中自由文本的晶状体检查数据,以识别白内障类型、白内障密度、人工晶状体存在及其他晶状体病理。
  • 选取4314条唯一晶状体检查条目,由11名临床医生评估NLP算法输出是否已正确识别条目中存在的所有病理。
  • 比较算法准确识别晶状体病理的敏感度与ICD代码的敏感度。

主要发现

  • NLP算法在4314条晶状体检查条目中的4104条正确识别所有晶状体病理,占95.1%。
  • 对于较少见的晶状体病理,算法发现经复核临床医生确认:假性剥脱物质提及的100%被确认,瞳孔闭锁、半脱位和粘连的99.7%被确认。
  • 识别晶状体病理的敏感度NLP为0.98(0.96-0.99),计费代码为0.49(0.46-0.53)。

关键数值与推荐

  • NLP算法正确识别所有晶状体病理的条目为4104/4314条,占95.1%。
  • NLP识别晶状体病理的敏感度为0.98(95%CI 0.96-0.99)。
  • 计费代码识别晶状体病理的敏感度为0.49(95%CI 0.46-0.53)。
  • 临床医生复核确认假性剥脱物质提及的100%被算法发现佐证。
  • 临床医生复核确认瞳孔闭锁、半脱位和粘连提及的99.7%被算法发现佐证。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

PURPOSE: Nearly all published ophthalmology-related Big Data studies rely exclusively on International Classification of Diseases (ICD) billing codes to identify patients with particular ocular conditions. However, inaccurate or nonspecific codes may be used. We assessed whether natural language processing (NLP), as an alternative approach, could more accurately identify lens pathology. DESIGN: Database study comparing the accuracy of NLP versus ICD billing codes to properly identify lens pathology. METHODS: We developed an NLP algorithm capable of searching free-text lens exam data in the electronic health record (EHR) to identify the type(s) of cataract present, cataract density, presence of intraocular lenses, and other lens pathology. We applied our algorithm to 17.5 million lens exam records in the Sight Outcomes Research Collaborative (SOURCE) repository. We selected 4314 unique lens-exam entries and asked 11 clinicians to assess whether all pathology present in the entries had been correctly identified in the NLP algorithm output. The algorithm's sensitivity at accurately identifying lens pathology was compared with that of the ICD codes. RESULTS: The NLP algorithm correctly identified all lens pathology present in 4104 of the 4314 lens-exam entries (95.1%). For less common lens pathology, algorithm findings were corroborated by reviewing clinicians for 100% of mentions of pseudoexfoliation material and 99.7% for phimosis, subluxation, and synechia. Sensitivity at identifying lens pathology was better for NLP (0.98 [0.96-0.99] than for billing codes (0.49 [0.46-0.53]). CONCLUSIONS: Our NLP algorithm identifies and classifies lens abnormalities routinely documented by eye-care professionals with high accuracy. Such algorithms will help researchers to properly identify and classify ocular pathology, broadening the scope of feasible research using real-world data.

来源:Am J Ophthalmol,查看原文。版权归原作者所有。

引用

  1. Stein JD, Zhou Y, Andrews CA, et al. Using Natural Language Processing to Identify Different Lens Pathology in Electronic Health Records. Am J Ophthalmol. 2024. PMID: 38296152. doi:10.1016/j.ajo.2024.01.030

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。