Authors: Surjya Ray, Pratik Mehta, Hongen Zhang, Ada Chaman, Jian Wang, Chung-Jen Ho, Michael Chiou, Tashfeen Suleman
Title: Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models
The precipitous rise and adoption of Large Language Models (LLMs) have shattered expectations with the fastest adoption rate of any consumer-facing technology in history. Healthcare, a field that traditionally uses NLP techniques, was bound to be affected by this meteoric rise. In this paper, we gauge the extent of the impact by evaluating the performance of LLMs for the task of medical coding on real-life noisy data. We conducted several experiments on MIMIC III and IV datasets with encoder-based LLMs, such as BERT. Furthermore, we developed Segmented Harmonic Loss, a new loss function to address the extreme class imbalance that we found to prevail in most medical data in a multi-label scenario by segmenting and decoupling co-occurring classes of the dataset with a new segmentation algorithm. We also devised a technique based on embedding similarity to tackle noisy data. Our experimental results show that when trained with the proposed loss, the LLMs achieve significant performance gains even on noisy long-tailed datasets, outperforming the F1-score of the state-of-the-art by over ten percentage points.
Keywords: Large Language Models, LLM, BERT, Transformer, NLP, Medical Coding, Mult-label, Extreme Class Imbalance, Long Tailed Distribution
For full paper, please visit: https://arxiv.org/pdf/2310.04595.pdf