Beyond Equality Matching: Custom Loss Functions for Semantics-Aware ICD-10 Coding

Monah Bou Hatoum, Jean Claude Charr, Alia Ghaddar, Alia Ghaddar, Christophe Guyeux, David Laiymani

2025

Abstract

Background: Accurate ICD-10 coding is vital for healthcare operations, yet manual processes are inefficient and error-prone. Machine learning offers automation potential but struggles with complex relationships between codes and clinical text. Objective: We propose a semantics-aware approach using custom loss functions to improve accuracy and clinical relevance in multi-label ICD-10 coding by leveraging cosine similarity to measure semantic relatedness between predicted and actual codes. Methods: Four custom loss functions (True Label Cardinality Loss (TLCL), Predicted Label Cardinality Loss (PLCL), Balanced Harmonic Mean Loss (BHML), and Weighted Harmonic Mean Loss (WHML)) were designed to capture hierarchical and semantic relationships. These were validated on a dataset of 9.57 million clinical notes from 24 medical specialties, using binary cross-entropy (BCE) loss as a baseline. Results: Our approach achieved a test micro-F1 score of 88.54%, surpassing the 74.64% baseline, with faster convergence and improved performance across specialties. Conclusion: Incorporating semantic similarity into the loss functions enhances ICD-10 code prediction, addressing clinical nuances and advancing machine learning in medical coding.

Paper Citation

in Harvard Style

Bou Hatoum M., Charr J., Ghaddar A., Guyeux C. and Laiymani D. (2025). Beyond Equality Matching: Custom Loss Functions for Semantics-Aware ICD-10 Coding. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 166-174. DOI: 10.5220/0013101000003890

in Bibtex Style

@conference{icaart25,
author={Monah Bou Hatoum and Jean Claude Charr and Alia Ghaddar and Christophe Guyeux and David Laiymani},
title={Beyond Equality Matching: Custom Loss Functions for Semantics-Aware ICD-10 Coding},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={166-174},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013101000003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Beyond Equality Matching: Custom Loss Functions for Semantics-Aware ICD-10 Coding
SN - 978-989-758-737-5
AU - Bou Hatoum M.
AU - Charr J.
AU - Ghaddar A.
AU - Guyeux C.
AU - Laiymani D.
PY - 2025
SP - 166
EP - 174
DO - 10.5220/0013101000003890
PB - SciTePress