Are Semantic Annotators Able to Extract Relevant Complexity-Related Concepts from Clinical Notes?

Abstract

Clinical decision support systems (CDSSs) implementing cancer clinical practice guidelines (CPGs) have the potential to improve the compliance of decisions made by multidisciplinary tumor boards (MTB) with CPGs. However, guideline-based CDSSs do not cover complex cases and need time for discussion. We propose to learn how to predict complex cancer cases prior to MTBs from breast cancer patient summaries (BCPSs) resuming clinical notes. BCPSs being unstructured natural language textual documents, we implemented four semantic annotators (ECMT, SIFR, cTAKES, and MetaMap) to assess whether complexity-related concepts could be extracted from clinical notes. On a sample of 24 BCPSs covering 35 complexity reasons, ECMT and MetaMap were the most efficient systems with a performance rate of 60% (21/35) and 49% (17/35), respectively. When using the four annotators in sequence, 69% of complexity reasons were extracted (24/35 reasons).

Using Machine Learning and Deep Learning Methods to Predict the Complexity of Breast Cancer Cases

“…We previously used semantic annotators to extract structured data from textual BCPSs [3]. ECMT and SIFR [4] are two annotators that work for the French language.…”

“…As a result, all BCPSs were available in both French and English. As a previous work [3] concluded that the application of all four annotators gave the best set of annotations, including complexity-related concepts, we executed the four annotators, and processed the output of each annotator to generate a semantic representation of a BCPS as two vectors, a vector of UMLS concepts (CUI) extracted by SIFR, cTAKES, and MetaMap. And a second vector containing the labels of the concepts extracted by ECMT (ECMT does not extract UMLS CUIs).…”