Authors:
Mutahira Khalid
1
;
Asim Abbas
2
;
Hassan Sajjad
3
;
Hassan Khattak
1
;
Tahir Hameed
4
and
Syed Bukhari
2
Affiliations:
1
School of Electrical Engineering and Computer Science, NUST, H-12, Islamabad, Pakistan
;
2
Division of Computer Science, Mathematics and Science, St. John’s University, Queens, NY 11439, U.S.A.
;
3
Faculty of Computer Science, Dalhousie University, Halifax, Canada
;
4
Girard School of Business, Merrimack College, North Andover, Massachusetts, U.S.A.
Keyword(s):
Medical Coding, Computer Assisted Coding (CAC), Deep Learning, Attention Mechanism, Symbolic AI, Knowledge Graphs, Ontologies, Explainability.
Abstract:
Medical coding is about assigning standardized alphanumeric codes to diagnoses, procedures, and interventions recorded in patients’ clinical notes. These codes are essential for correct medical claims and billing processes, which are critical in maintaining efficient revenue cycles. Computer-Assisted-Coding (CAC) employs AI models to automate medical coding hence cutting down human effort and errors. Despite their unrivalled performance, these models lack ‘explainability’. Explainability opens up the inner workings and results of black-box deep learning models. Attention mechanisms are the most common approach for ‘explainability’, but they leave some questions unanswered, for instance, the relationship between highlighted words and predictions. Where black-box models fail to answer such questions, ‘Symbolic AI’ such as ‘Knowledge Graphs’ provide a superior alternate approach. We consolidated the attention mechanism with Symbolic AI to help users understand the results of a deep-lear
ning model for CAC. We evaluated its performance on the basis of strong and weak relationships on word-to-word and word-to-code levels by employing a semantically-enriched Knowledge Graph. We achieved 64% word-to-word and 53% word-to-code level accuracy. This paper is among the earliest ones on knowledge graphs for explainability in medical coding. It is also the deepest in applying attention-based mechanisms and knowledge graphs to any medical domain.
(More)