用人工智能生成的医学诊断微调Llama-2-13B:优化ICD编码在妇科瘤学中的新策略
Yu-Ling Liang1, Chiu-Fan Chen2, Meng-Hsing Wu3
1Department of Obstetrics and Gynecology, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan; Graduate Institute of Clinical Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan.
将Llama-2模型与人工智能生成的医学诊断进行微调,大大提高了它在为妇科瘤学分配ICD-10代码的准确性. 这种人工智能驱动的方法提高了诊断编码的效率和准确性.
科学领域:
- 人工智能在医学中的应用
- 自然语言处理自然语言处理.
- 医疗信息学 医疗信息学
背景情况:
- 大型语言模型 (LLM) 显示出医疗应用的前景.
- 准确的国际疾病分类 (ICD) 编码对医疗保健至关重要.
- 妇科瘤学编码提出了独特的挑战.
研究的目的:
- 评估人工智能生成的诊断文本在微调Llama-2模型中的有效性.
- 使用人工智能优化ICD-10编码过程用于妇科瘤学.
- 为了提高拉玛-2-13B模型的诊断准确度.
主要方法:
- 基于ICD-10描述符的AI生成的诊断文本被创建.
- 拉玛-2-13B模型使用不同数量的AI生成数据进行了微调.
- 四个模型进行了比较:本地Llama-2,与基本ICD-10代码微调,并微调每代码10或20个AI生成的语句.
- 对83份妇科瘤学出院记录进行了验证.
主要成果:
- 精细调整人工智能生成的数据显著提高了准确性和卡帕分数.
- 模型3 (10个AI语句/代码) 实现了0.90准确度和0.89卡帕.
- 模型4 (20个AI语句/代码) 实现了0.95准确度和0.94卡帕.
- 原生拉玛-2 (模型1) 显示了最小的精度 (0.06) 和卡帕 (0.04).
结论:
- 用于微调的人工智能生成的数据大大提高了ICD-10编码中的LLM性能.
- 这种方法提供了一种具有成本效益的策略,以优化诊断代码的准确性.
- 该方法显示了在医学编码和LLM利用中更广泛应用的潜力.
更多相关视频
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Formulating and Validating Nursing Diagnosis II
Risk nursing diagnoses represent clinical judgments of an individual, family, or community more vulnerable to developing the health problem than others...
Formulating and Validating Nursing Diagnosis I
There are thirteen domains...
Standards of Care II
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
Improving Translational Accuracy
