从医疗保险数据中使用LLM预测住院治疗
Everton F Baro1,2, Luiz S Oliveira3, Alceu de Souza Britto4
1Department of Informatics, Federal University of Parana, Rua Francisco H. dos Santos, 100, Curitiba, 81530-090, Parana, Brazil. efbaro@inf.ufpr.br.
大型语言模型 (LLM) 现在可以使用医疗保险数据预测住院,简化复杂的特征提取. 这一突破使得医疗保健中的应用范围更广泛,对于一般和中风相关的入院的高准确性.
科学领域:
- 医疗信息学 医疗信息学
- 机器学习 机器学习
- 自然语言处理自然语言处理.
背景情况:
- 医疗保险数据为预测住院预测提供了尚未开发的潜力.
- 从这些数据中提取用于机器学习的特征通常需要专门的专业知识.
- 大型语言模型 (LLM) 为利用这些数据提供了一条新的途径,降低了技术障碍.
研究的目的:
- 提出一种方法,利用医疗保险数据与LLMs预测住院治疗.
- 在葡萄牙语和英语中开发和评估预先训练的LLM用于住院预测.
主要方法:
- 组织和准备医疗保险数据用于LLM输入.
- 预培训医疗保险数据集的LLM.
- 评估模型在预测一般住院和中风相关住院的性能.
主要成果:
- 在葡萄牙语和英语中生成预先训练的LLM,能够预测住院治疗.
- 实现了高性能指标:F1-Score = 87.8和AUC = 0.955用于一般住院预测.
- 取得了与中风相关的住院预测的优秀结果:F1-Score = 88.7和AUC = 0.964.
结论:
- 通过使用医疗保险数据,LLM可以有效地预测住院情况,民主化对预测性健康应用程序的访问.
- 开发的预训练模型显示出显著的准确性和各种医疗保健应用的潜力.
- 模型是科学界公开提供的,以促进进一步的研究和开发.
更多相关视频
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
相关概念视频
Hospitals-I
Steps in Outbreak Investigation
Models of Health Promotion and Illness Prevention I
The health belief model (HBM) attempts to predict health-related behavior in specific belief patterns. According to the HBM, a person's...
Hospitals-II
Nurses that work in...
Models of Health Promotion and Illness Prevention II
The agent-host-environment model states that disease results...
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...
