大型语言模型提高了基于电子健康记录的预测在不同国家和编码系统的可转移性
Matthias Kirchler1,2,3, Matteo Ferro3, Veronica Lorenzini4
1Hasso Plattner Institute, University of Potsdam, Digital Engineering Faculty, Potsdam, Germany.
NPJ digital medicine
|January 22, 2026
概括
本研究介绍了GRASP,一种使用大型语言模型嵌入的新方法,以提高电子健康记录预测模型在各种医疗保健系统中的普遍性. GRASP提高了疾病预测的准确性和稳定性,克服了当前方法的局限性.
科学领域:
- 计算生物学是一种计算生物学.
- 医疗信息学医学信息学
- 机器学习在医疗保健中的应用
背景情况:
- 医疗保健系统在医疗实践和报告标准上存在差异,这阻碍了预测模型的可转移性.
- 将医疗代码嵌入到共享的语义空间可以减轻差异,但现实世界的应用是有限的.
研究的目的:
- 开发和验证一种可扩展的方法,GRASP,利用大型语言模型嵌入来提高使用电子健康记录数据的预测模型的概括性.
- 改善跨多种国际医疗保健数据集的疾病发病和全因死亡率的预测.
主要方法:
- 开发了GRASP,将大型语言模型嵌入式与基于变压器的预测模型集成在一起.
- 应用GRASP来预测超过一百万个人的21种疾病和全因死亡率.
- 在英国生物库数据上进行培训,并在芬兰的FinnGen (芬兰) 和西奈山 (美国) 的数据集中进行评估.
主要成果:
- 与语言无意识模型相比,GRASP在概括性方面表现出显著的改进,平均DC指数的改善为88% (FinnGen) 和47% (西奈山).
- 在62%的疾病中,GRASP与多基因风险得分的相关性更高.
- 该模型即使在非协调的数据集中也保持了强大的性能.
结论:
- 利用大型语言模型嵌入提供了一个有效和可扩展的解决方案,以提高基于电子健康记录的预测模型的通用性.
- GRASP代表了跨医疗保健系统模型可转移性的重大进展,解决了当前预测建模中的关键局限性.
- 这种方法显示出更可靠,更广泛应用的临床预测工具的前景.
相关概念视频
Ionic Bonding and Electron Transfer
48.9K
Ions are atoms or molecules bearing an electrical charge. A cation (a positive ion) forms when a neutral atom loses one or more electrons from its valence shell, and an anion (a negative ion) forms when a neutral atom gains one or more electrons in its valence shell. Compounds composed of ions are called ionic compounds (or salts), and their constituent ions are held together by ionic bonds: electrostatic forces of attraction between oppositely charged cations and anions.
48.9K
Purpose of Health Records I
1.8K
The vital purpose of health records is to provide a complete and accurate account of a patient's medical history, including communication, diagnostic and therapeutic orders, care planning, research, and quality review.
Here's a breakdown of how health records serve these purposes:
Here's a breakdown of how health records serve these purposes:
1.8K
Purpose of Health Records II
1.4K
Health records serve various essential purposes in the healthcare system. Here are some key purposes:
1.4K
Transfer Function in Control Systems
1.5K
The transfer function is a fundamental concept in the analysis and design of linear time-invariant (LTI) systems. It offers a concise way to understand how a system responds to different inputs in the frequency domain. It serves as a bridge between the time-domain differential equations that describe system dynamics and the frequency-domain representation that facilitates easier manipulation and analysis.
To derive the transfer function, consider a general nth-order linear time-invariant...
To derive the transfer function, consider a general nth-order linear time-invariant...
1.5K
Electron Orbital Model
71.9K
Orbitals are the areas outside of the atomic nucleus where electrons are most likely to reside. They are characterized by different energy levels, shapes, and three-dimensional orientations. The location of electrons is described most generally by a shell or principal energy level, then by a subshell within each shell, and finally, by individual orbitals found within the subshells.
The first shell is closest to the nucleus, and it has only one subshell with a single spherical orbital called the...
The first shell is closest to the nucleus, and it has only one subshell with a single spherical orbital called the...
71.9K
Predicting Molecular Geometry
45.5K
VSEPR Theory for Determination of Electron Pair Geometries
45.5K


