Towards Generalizable Methods for Automating Risk Score Calculation

Jennifer J Liang, Eric Lehman, Ananya Iyengar, Diwakar Mahajan, Preethi Raghavan, Cindy Y. Chang, Peter Szolovits


Abstract
Clinical risk scores enable clinicians to tabulate a set of patient data into simple scores to stratify patients into risk categories. Although risk scores are widely used to inform decision-making at the point-of-care, collecting the information necessary to calculate such scores requires considerable time and effort. Previous studies have focused on specific risk scores and involved manual curation of relevant terms or codes and heuristics for each data element of a risk score. To support more generalizable methods for risk score calculation, we annotate 100 patients in MIMIC-III with elements of CHA2DS2-VASc and PERC scores, and explore using question answering (QA) and off-the-shelf tools. We show that QA models can achieve comparable or better performance for certain risk score elements as compared to heuristic-based methods, and demonstrate the potential for more scalable risk score automation without the need for expert-curated heuristics. Our annotated dataset will be released to the community to encourage efforts in generalizable methods for automating risk scores.
Anthology ID:
2022.bionlp-1.42
Volume:
Proceedings of the 21st Workshop on Biomedical Language Processing
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venues:
ACL | BioNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
426–431
Language:
URL:
https://aclanthology.org/2022.bionlp-1.42
DOI:
10.18653/v1/2022.bionlp-1.42
Bibkey:
Cite (ACL):
Jennifer J Liang, Eric Lehman, Ananya Iyengar, Diwakar Mahajan, Preethi Raghavan, Cindy Y. Chang, and Peter Szolovits. 2022. Towards Generalizable Methods for Automating Risk Score Calculation. In Proceedings of the 21st Workshop on Biomedical Language Processing, pages 426–431, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Towards Generalizable Methods for Automating Risk Score Calculation (Liang et al., BioNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.bionlp-1.42.pdf
Data
MIMIC-IIIemrQA