Knowledge Graph Based Trustworthy Medical Code Recommendations

Mutahira Khalid, Asim Abbas, Hassan Sajjad, Hassan Khattak, Tahir Hameed, Syed Bukhari

2023

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-learning 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.

Paper Citation

in Harvard Style

Khalid M., Abbas A., Sajjad H., Khattak H., Hameed T. and Bukhari S. (2023). Knowledge Graph Based Trustworthy Medical Code Recommendations. In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: CCH, ISBN 978-989-758-631-6, pages 627-637. DOI: 10.5220/0011925700003414

in Bibtex Style

@conference{cch23,
author={Mutahira Khalid and Asim Abbas and Hassan Sajjad and Hassan Khattak and Tahir Hameed and Syed Bukhari},
title={Knowledge Graph Based Trustworthy Medical Code Recommendations},
booktitle={Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: CCH,},
year={2023},
pages={627-637},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011925700003414},
isbn={978-989-758-631-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: CCH,
TI - Knowledge Graph Based Trustworthy Medical Code Recommendations
SN - 978-989-758-631-6
AU - Khalid M.
AU - Abbas A.
AU - Sajjad H.
AU - Khattak H.
AU - Hameed T.
AU - Bukhari S.
PY - 2023
SP - 627
EP - 637
DO - 10.5220/0011925700003414