分段谐波损失：面向大语言模型医疗编码任务的类别不平衡多标签临床数据处理
Segmented Harmonic Loss: Handling Class-Imbalanced Multi-Label Clinical Data for Medical Coding with Large Language Models
AI总结：
针对医疗编码任务中多标签临床数据极端类别不平衡与含噪问题，提出分段谐波损失及嵌入相似度降噪技术，在MIMIC数据集上实现F1分数较SOTA提升超10个百分点。
摘要：
大语言模型（LLM）的迅猛发展与普及创下了历史上所有消费级技术中最快的采用率，远超预期。医疗健康作为传统上应用自然语言处理（NLP）技术的领域，势必会受到这一快速发展浪潮的影响。本文通过评估大语言模型在真实含噪数据上完成医疗编码任务的表现，衡量了这一影响的程度。我们基于BERT等编码器型大语言模型，在MIMIC III和IV数据集上开展了多项实验。此外，我们提出了一种新型损失函数——分段谐波损失（Segmented Harmonic Loss），通过一种全新的分割算法对数据集中共现的类别进行分割与解耦，用于解决多标签场景下绝大多数医疗数据中普遍存在的极端类别不平衡问题。我们还设计了一种基于嵌入相似度的技术来处理含噪数据。实验结果表明，采用所提损失函数训练后，大语言模型即使在含噪的长尾数据集上也能实现显著的性能提升，其F1分数较当前最优水平高出超过10个百分点。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
