临床语言模型的多模式微调用于预测COVID-19结果
Aron Henriksson1, Yash Pawar1, Pontus Hedberg2
1Department of Computer and Systems Sciences (DSV), Stockholm University, Kista, Sweden.
综合结构化和非结构化临床数据的多模式模型显著改善了COVID-19结果预测,优于仅使用一种数据类型的模型. 这种方法提高了医疗保健中的患者管理和资源配置.
科学领域:
- 人工智能在医学中的应用
- 临床信息学 临床信息学
- 健康 数据科学 数据科学
背景情况:
- 传统的临床预测模型往往忽略了自由文本临床笔记中的有价值信息.
- 整合各种数据模式对于全面的患者评估至关重要.
研究的目的:
- 开发和评估用于预测COVID-19结果的多式联络模型.
- 用结构化和非结构化数据评估多式模式模型与单式模式模型的性能.
主要方法:
- 利用多式联络微调来训练使用结构化和非结构化医疗保健数据的模型.
- 在六家医院的COVID-19患者的多中心队列上训练和评估模型.
- 预计30天死亡率,安全出院,并重新入院.
主要成果:
- 多模式模型在预测所有三种COVID-19结果方面始终优于单模式模型.
- 敏感性分析探讨了不同患者子组的表现.
- 一项废除研究确定了各种临床笔记类型对模型准确性的影响.
结论:
- 多模式模型有效地利用例行收集的医疗保健数据,以优化COVID-19结果预测.
- 这些模型可以增强患者管理,并优化医疗保健资源的使用.
- 多种数据源的整合代表了临床预测的重大进步.
更多相关视频
05:56Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
相关概念视频
Improving Translational Accuracy
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...
Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
Statistical Methods for Analyzing Epidemiological Data
Statistical Software for Data Analysis and Clinical Trials
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
