A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Abstract

Clinical case reports (CCRs) are a valuable means of sharing observations and insights in medicine. The form of these documents varies, and their content includes descriptions of numerous, novel disease presentations and treatments. Thus far, the text data within CCRs is largely unstructured, requiring significant human and computational effort to render these data useful for in-depth analysis. In this protocol, we describe methods for identifying metadata corresponding to specific biomedical concepts frequently observed within CCRs. We provide a metadata template as a guide for document annotation, recognizing that imposing structure on CCRs may be pursued by combinations of manual and automated effort. The approach presented here is appropriate for organization of concept-related text from a large literature corpus (e.g., thousands of CCRs) but may be easily adapted to facilitate more focused tasks or small sets of reports. The resulting structured text data includes sufficient semantic context to support a variety of subsequent text analysis workflows: meta-analyses to determine how to maximize CCR detail, epidemiological studies of rare diseases, and the development of models of medical language may all be made more realizable and manageable through the use of structured text data.

Decline of case reports in pathology and their renewal in the digital age: an analysis of publication trends over four decades

“…Moreover, BDA tools would allow for a qualitative/quantitative evaluation of SMCRs based on the quality of information, quality of images, the presence of citations from the literature, the degree of involvement in the discussion and other parameters. Some authors have already proposed a particular type of automated annotation analysis for clinical CRs, defined as ‘metadata extraction approach’; it consists in extracting text and numerical values from a large collection of published CRs to standardise the description of the discussed specific biomedical concepts 15 16. The BDA tools and metadata extraction approach would allow the development of SMCR databases which may be published in special online sections of Pathology journals or dedicated websites.…”

A manual corpus of annotated main findings of clinical case reports

“…Manual annotation of clinical case reports has been pursued in previous studies that have extracted potential adverse drug event relations (4) and biomedical concepts (5). Corpora consisting of clinical case reports have been employed for training machine reading comprehension (6) and automated recognition of rare disease phenotypes (7).…”

Examining the Educational Depth of Medical Case Reports and Radiology with Text Mining

“…Researchers can extract data from the whole case report or from the abstract section of the article. In an effort to provide more insight and help educate others on extracting metadata from case reports,Caufield et al (2018) published a video article on the topic in the Journal of Visualized Experiments. In their video and corresponding article, the team provides the steps needed to successfully apply text mining to large sets of unstructured data to extract data in order to provide standardized ways to annotate biomedical concepts Luo et al (2020).…”