DRG-LLaMA:调整LLaMA模型以预测住院患者的诊断相关组
Hanyin Wang1, Chufan Gao2, Christopher Dantona3
1Division of Hospital Internal Medicine, Mayo Clinic Health System, Mankato, MN, USA.
NPJ digital medicine
|January 22, 2024
概括
一个新的大型语言模型 (LLM),DRG-LLaMA,提高了诊断相关组 (DRG) 赋值的准确性. 这种人工智能模型通过分析临床笔记来提高美国住院患者支付系统的效率.
科学领域:
- 医疗保健中的人工智能
- 临床信息学 临床信息学
- 自然语言处理自然语言处理.
背景情况:
- 美国住院支付系统严重依赖于准确的诊断相关组 (DRG) 分配.
- 当前的DRG分配流程往往是低效的,容易出现错误.
研究的目的:
- 引入DRG-LLaMA,一种新型的大型语言模型 (LLM),旨在提高DRG分配的准确性和效率.
- 评估DRG-LLaMA与现有模型相比在从临床笔记中预测DRG方面的性能.
主要方法:
- 在MIMIC-IV排放总结的大数据集 (236,192) 上使用低级调整 (LoRA) 微调LLaMA基础模型.
- 开发DRG-LLaMA-7B模型,其最大输入令牌长度为512.
- 使用诸如宏观平均F1得分,顶级-1预测准确度和宏观平均曲线下面面积 (AUC) 等指标评估模型性能.
主要成果:
- DRG-LLaMA -7B实现了宏观平均F1得分为0.327,最高-1准确度为52.0%,AUC为0.986.
- 该模型比临床BERT (40.3%相对F1得分增加) 和CAML (35.7%相对F1得分增加) 显著提高了性能.
- 对于基本的DRG (67.8%) 和并发症/并发症 (CC/MCC) 预测 (67.5%),DRG-LLaMA取得了很高的top-1准确度.
结论:
- DRG-LLaMA代表了人工智能驱动的DRG预测的重大进步,其性能优于以前的先进模型.
- 模型性能受到增加的模型参数和输入上下文长度的积极影响.
- 这些发现表明DRG-LLaMA可以通过提高DRG分配效率和准确性来简化住院患者支付系统.
相关概念视频
Receiver Operating Characteristic Plot
183
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
183
Documentation of Nursing Diagnosis
1.3K
The nurse documents nursing diagnoses and enters them into the patient record. The identified patient's nursing diagnosis is either written out with a plan of care or entered into the electronic health record.
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...
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...
1.3K
Sensitivity, Specificity, and Predicted Value
358
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
358
Classification of Illness
7.5K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
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...
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...
7.5K


