Melton Genevieve B, Parsons Simon, Morrison Frances P, Rothschild Adam S, Markatou Marianthi, Hripcsak George
Department of Surgery, The Johns Hopkins Medical Institutions, Baltimore, MD, USA.
J Biomed Inform. 2006 Dec;39(6):697-705. doi: 10.1016/j.jbi.2006.01.004. Epub 2006 Feb 24.
Patient-based similarity metrics are important case-based reasoning tools which may assist with research and patient care applications. Ontology and information content principles may be potentially helpful tools for similarity metric development.
Patient cases from 1989 through 2003 from the Columbia University Medical Center data repository were converted to SNOMED CT concepts. Five metrics were implemented: (1) percent disagreement with data as an unstructured "bag of findings," (2) average links between concepts, (3) links weighted by information content with descendants, (4) links weighted by information content with term prevalence, and (5) path distance using descendants weighted by information content with descendants. Three physicians served as gold standard for 30 cases.
Expert inter-rater reliability was 0.91, with rank correlations between 0.61 and 0.81, representing upper-bound performance. Expert performance compared to metrics resulted in correlations of 0.27, 0.29, 0.30, 0.30, and 0.30, respectively. Using SNOMED axis Clinical Findings alone increased correlation to 0.37.
Ontology principles and information content provide useful information for similarity metrics but currently fall short of expert performance.
基于患者的相似性度量是重要的基于案例的推理工具，可辅助研究和患者护理应用。本体论和信息内容原则可能是相似性度量开发的潜在有用工具。
将1989年至2003年来自哥伦比亚大学医学中心数据存储库的患者病例转换为SNOMED CT概念。实施了五种度量：（1）与作为非结构化“发现集”的数据的不一致百分比，（2）概念之间的平均链接数，（3）由具有后代的信息内容加权的链接，（4）由具有术语流行率的信息内容加权的链接，以及（5）使用由具有后代的信息内容加权的后代的路径距离。三位医生作为30个病例的金标准。
专家评分者间信度为0.91，等级相关性在0.61至0.81之间，代表上限性能。与度量相比，专家性能的相关性分别为0.27、0.29、0.30、0.30和0.30。仅使用SNOMED轴临床发现可将相关性提高到0.37。
本体论原则和信息内容为相似性度量提供了有用信息，但目前仍未达到专家性能。
