Byrd Roy J, Steinhubl Steven R, Sun Jimeng, Ebadollahi Shahram, Stewart Walter F
IBM T. J. Watson Research Center, Yorktown Heights, NY, United States.
Geisinger Medical Center, Center for Health Research, Danville, PA, United States.
Int J Med Inform. 2014 Dec;83(12):983-92. doi: 10.1016/j.ijmedinf.2012.12.005. Epub 2013 Jan 11.
Early detection of Heart Failure (HF) could mitigate the enormous individual and societal burden from this disease. Clinical detection is based, in part, on recognition of the multiple signs and symptoms comprising the Framingham HF diagnostic criteria that are typically documented, but not necessarily synthesized, by primary care physicians well before more specific diagnostic studies are done. We developed a natural language processing (NLP) procedure to identify Framingham HF signs and symptoms among primary care patients, using electronic health record (EHR) clinical notes, as a prelude to pattern analysis and clinical decision support for early detection of HF.
We developed a hybrid NLP pipeline that performs two levels of analysis: (1) At the criteria mention level, a rule-based NLP system is constructed to annotate all affirmative and negative mentions of Framingham criteria. (2) At the encounter level, we construct a system to label encounters according to whether any Framingham criterion is asserted, denied, or unknown.
Precision, recall, and F-score are used as performance metrics for criteria mention extraction and for encounter labeling.
Our criteria mention extractions achieve a precision of 0.925, a recall of 0.896, and an F-score of 0.910. Encounter labeling achieves an F-score of 0.932.
Our system accurately identifies and labels affirmations and denials of Framingham diagnostic criteria in primary care clinical notes and may help in the attempt to improve the early detection of HF. With adaptation and tooling, our development methodology can be repeated in new problem settings.
早期发现心力衰竭（HF）可减轻这种疾病给个人和社会带来的巨大负担。临床检测部分基于对构成弗明汉姆心力衰竭诊断标准的多种体征和症状的识别，这些体征和症状通常由初级保健医生在进行更具体的诊断研究之前记录下来，但不一定进行综合分析。我们开发了一种自然语言处理（NLP）程序，以利用电子健康记录（EHR）临床笔记在初级保健患者中识别弗明汉姆心力衰竭的体征和症状，作为早期检测心力衰竭的模式分析和临床决策支持的前奏。
我们开发了一个混合NLP管道，该管道执行两个层次的分析：（1）在标准提及层次，构建一个基于规则的NLP系统，对弗明汉姆标准的所有肯定和否定提及进行注释。（2）在就诊层次，我们构建一个系统，根据是否有任何弗明汉姆标准被断言、否认或未知来标记就诊情况。
精确率、召回率和F分数用作标准提及提取和就诊标记的性能指标。
我们的标准提及提取的精确率为0.925，召回率为0.896，F分数为0.910。就诊标记的F分数为0.932。
我们的系统能够准确识别和标记初级保健临床笔记中弗明汉姆诊断标准的肯定和否定情况，并可能有助于提高心力衰竭的早期检测水平。通过调整和工具开发，我们的开发方法可以在新的问题环境中重复使用。
