Dang Pragya A, Kalra Mannudeep K, Blake Michael A, Schultz Thomas J, Stout Markus, Lemay Paul R, Freshman David J, Halpern Elkan F, Dreyer Keith J
Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, Massachusetts 02114, USA.
J Am Coll Radiol. 2008 Mar;5(3):197-204. doi: 10.1016/j.jacr.2007.09.003.
The study purpose was to describe the use of natural language processing (NLP) and online analytic processing (OLAP) for assessing patterns in recommendations in unstructured radiology reports on the basis of patient and imaging characteristics, such as age, gender, referring physicians, radiology subspecialty, modality, indications, diseases, and patient status (inpatient vs outpatient).
A database of 4,279,179 radiology reports from a single tertiary health care center during a 10-year period (1995-2004) was created. The database includes reports of computed tomography, magnetic resonance imaging, fluoroscopy, nuclear medicine, ultrasound, radiography, mammography, angiography, special procedures, and unclassified imaging tests with patient demographics. A clinical data mining and analysis NLP program (Leximer, Nuance Inc, Burlington, Massachusetts) in conjunction with OLAP was used for classifying reports into those with recommendations (I(REC)) and without recommendations (N(REC)) for imaging and determining I(REC) rates for different patient age groups, gender, imaging modalities, indications, diseases, subspecialties, and referring physicians. In addition, temporal trends for I(REC) were also determined.
There was a significant difference in the I(REC) rates in different age groups, varying between 4.8% (10-19 years) and 9.5% (>70 years) (P <.0001). Significant variations in I(REC) rates were observed for different imaging modalities, with the highest rates for computed tomography (17.3%, 100,493/581,032). The I(REC) rates varied significantly for different subspecialties and among radiologists within a subspecialty (P < .0001). For most modalities, outpatients had a higher rate of recommendations when compared with inpatients.
The radiology reports database analyzed with NLP in conjunction with OLAP revealed considerable differences between recommendation trends for different imaging modalities and other patient and imaging characteristics.
本研究旨在描述如何使用自然语言处理（NLP）和在线分析处理（OLAP），基于患者和影像特征（如年龄、性别、转诊医生、放射科亚专业、检查方式、检查指征、疾病及患者状态（住院患者与门诊患者）），评估非结构化放射学报告中的建议模式。
创建了一个包含某单一三级医疗中心在10年期间（1995 - 2004年）的4,279,179份放射学报告的数据库。该数据库包括计算机断层扫描、磁共振成像、荧光透视检查、核医学、超声、放射摄影、乳腺摄影、血管造影、特殊检查以及带有患者人口统计学信息的未分类影像检查报告。使用一个临床数据挖掘与分析NLP程序（Leximer，Nuance公司，马萨诸塞州伯灵顿）结合OLAP，将报告分类为有影像检查建议的报告（I(REC)）和无影像检查建议的报告（N(REC)），并确定不同患者年龄组、性别、影像检查方式、检查指征、疾病、亚专业及转诊医生的I(REC)率。此外，还确定了I(REC)的时间趋势。
不同年龄组的I(REC)率存在显著差异，范围在4.8%（10 - 19岁）至9.5%（>70岁）之间（P <.（此处原文可能有误，推测应为P <.0001））。不同影像检查方式的I(REC)率存在显著差异，计算机断层扫描的I(REC)率最高（17.3%，100,493/581,032）。不同亚专业以及同一亚专业内不同放射科医生的I(REC)率差异显著（P <.0001）。对于大多数检查方式，门诊患者的建议率高于住院患者。
结合NLP与OLAP分析的放射学报告数据库显示，不同影像检查方式以及其他患者和影像特征的建议趋势之间存在显著差异。
