A frame semantic overview of NLP-based information extraction for cancer-related EHR notes

Abstract

Objective:There is a lot of information about cancer in Electronic Health Record (EHR) notes that can be useful for biomedical research provided natural language processing (NLP) methods are available to extract and structure this information. In this paper, we present a scoping review of existing clinical NLP literature for cancer. Methods:We identified studies describing an NLP method to extract specific cancer-related information from EHR sources from PubMed, Google Scholar, ACL Anthology, and existing reviews. Two exclusion criteria were used in this study. We excluded articles where the extraction techniques used were too broad to be represented as frames (e.g., document classification) and also where very low-level extraction methods were used (e.g. simply identifying clinical concepts). 79 articles were included in the final review. We organized this information according to frame semantic principles to help identify common areas of overlap and potential gaps.Results: Frames were created from the reviewed articles pertaining to cancer information such as cancer diagnosis, tumor description, cancer procedure, breast cancer diagnosis, prostate cancer diagnosis and pain in prostate cancer patients. These frames included both a definition as well as specific frame elements (i.e. extractable attributes). We found that cancer diagnosis was the most common frame among the reviewed papers (36 out of 79), with recent work focusing on extracting information related to treatment and breast cancer diagnosis. Conclusion:The list of common frames described in this paper identifies important cancerrelated information extracted by existing NLP techniques and serves as a useful resource for future researchers requiring cancer information extracted from EHR notes. We also argue, due to the heavy duplication of cancer NLP systems, that a general purpose resource of annotated cancer frames and corresponding NLP tools would be valuable.

Medical Information Extraction in the Age of Deep Learning

“…Savova et al [42] reviewed the current state of clinical NLP with respect to oncology and cancer phenotyping from EHR. Datta et al [43] focused on an even more specialized use case-the lexical representation required for the extraction of cancer information from EHR notes in a frame-semantic format.…”

Deep phenotyping: Embracing complexity and temporality—Towards scalability, portability, and interoperability

“…Four articles in this special issue leveraged NLP on different data resources for phenotyping [14][15][16][17].…”

“…Datta et al provided a methodology review that provides a frame semantic overview of NLP-based information extraction from EHR notes [14]. Using cancer as an example, this article contributes a model for identifying important disease-specific information using NLP techniques and serves as a useful resource for future researchers requiring disease-specific information extracted from EHR notes.…”

“…First author NLP STND DL SRC SUB Disease Focus eMERGE OHDSI [14] Datta, S X [15] Liu, Q X X [16] Lyudovyk, O X X X Cancer X [17] Liu, C X X X [18] Hong, N X [19] Shang, N X X X [20] Hripcsak, G X X X [21] Ostropolets, A X X X [22] Reps, J X X X [23] Swerdel, J X X [24] Warner, J X Cancer X [25] Shen, F X X X X [26] Trace, JM X Parkinson's [27] Mate, S X [28] Meng, W Cancer [29] Zhao, J X X Cardiovascular X [30] Chen, X X X Rare disease [31] Xu, Z X X X Acute kidney injury [32] Zhang, L X X [33] Chen, P X TOTAL 6 12 6 6 3 5 6…”

Extraction of Lactation Frames from Drug Labels and LactMed

“…Several works have explicitly extended FrameNet for biomedical tasks. This includes frame for molecular biology information (Dolbey et al, 2006;Dolbey, 2009;Tan, 2014), cancer information from EHRs Datta et al, 2017), and general medical information for Swedish (Kokkinakis, 2013). Many other works have implicitly used representations that are similar to frames, including the TAC ADR task data on drug labels Demner-Fushman et al, 2018b).…”