MIMICause: Representation and automatic extraction of causal relation types from clinical notes

Findings of the Association for Computational Linguistics: ACL 2022, pages 764 - 773 May 22-27, 2022 c⃝2022 Association for Computational Linguistics MIMICause: Representation and automatic extraction of causal relation types from clinical notes Vivek Khetan∗†♠ Md Imbesat Hassan Rizvi† ♣ Jessica Huber‡ ♥ Paige Bartusiak‡ ♦ Bogdan Sacaleanu♠ Andrew Fano ♠ ♠Accenture Labs, SF, ♣Indian Institute of Science ♥Arizona State University, ♦Duke University vivek.a.khetan@accenture.com, mdrizvi@iisc.ac.in jhuber12@asu.edu, paige.bartusiak@cs.duke.edu {bogdan.e.sacaleanu, andrew.e.fano}@accenture.com Abstract Understanding causal narratives communi- cated in clinical notes can help make strides towards personalized healthcare. Extracted causal information from clinical notes can be combined with structured EHR data such as pa- tients’ demographics, diagnoses, and medica- tions. This will enhance healthcare providers’ ability to identify aspects of a patient’s story communicated in the clinical notes and help make more informed decisions. In this work, we propose annotation guide- lines, develop an annotated corpus1 and pro- vide baseline scores to identify types and di- rection of causal relations between a pair of biomedical concepts in clinical notes; commu- nicated implicitly or explicitly, identified ei- ther in a single sentence or across multiple sen- tences. We annotate a total of 2714 de-identified exam- ples sampled from the 2018 n2c2 shared task dataset and train four different language model based architectures. Annotation based on our guidelines achieved a high inter-annotator agreement i.e. Fleiss’ kappa (κ) score of 0.72, and our model for identification of causal re- lations achieved a macro F1 score of 0.56 on the test data. The high inter-annotator agree- ment for clinical text shows the quality of our annotation guidelines while the provided baseline F1 score sets the direction for future research towards understanding narratives in clinical texts. 1 Introduction Electronic Health Records (EHRs) have significant amounts of unstructured clinical notes containing a rich description of patients’ states as observed by ∗Corresponding Author †Equal contribution ‡Contributed during an internship at Accenture labs, SF 1MIMICause dataset will be available un- der the “Community Annotations Downloads” at https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/ healthcare professionals over time. Our ability to effectively parse and understand clinical narratives depends upon the quality of extracted biomedical concepts and semantic relations. The contempo- rary advancements in natural language processing (NLP) have led to an increased interest in tasks such as extraction of biomedical concepts, patients’ data de-identification, medical question answering and relation extraction. While these tasks have improved our ability for clinical narrative under- standing, identification of semantic causal relations between biomedical entities will further enhance it. Identification of novel and interesting causal ob- servations from clinical notes can be instrumental to a better understanding of patients’ health. It can also help us identify potential causes of diseases and determine their prevention and treatment. De- spite the usefulness of identification and extraction of causal relation types, our capability to do so is limited and remains a challenge for specialized domains like healthcare. The NLP community has been actively working on causality understanding from text and has pro- posed various methodologies to represent (Talmy, 1988; Wolff, 2007; Swartz, 2014; Hassanzadeh et al., …

Content truncated to 500 words