临床表型的零射击学习:比较LLM和基于规则的方法
Bernardo Neves1, José Maria Moreira2, Simão Gonçalves2
1Hospital da Luz Learning Health, Luz Saúde, Lisboa, Portugal; Internal Medicine Department, Hospital da Luz Lisboa, Lisboa, Portugal; INESC-ID, Instituto Superior Técnico, Universidade de Lisboa, Portugal; Católica Medical School, Universidade Católica Portuguesa, Portugal.
Computers in biology and medicine
|April 24, 2025
概括
大型语言模型 (LLM) 能够从电子健康记录 (EHR) 中有效地实现慢性疾病的零射击表型. GPT-4o表现出卓越的性能,减少了数据科学应用程序的手动注释需求.
科学领域:
- 计算健康信息学 医疗信息学
- 人工智能在医学中的应用
- 数据科学用于医疗保健
背景情况:
- 表型,在临床数据中分类疾病,对于电子健康记录 (EHR) 数据科学至关重要.
- 传统的表型化方法是劳动密集型的,难以扩展.
- 自动化表型化对于利用大型EHR数据集至关重要.
研究的目的:
- 评估大型语言模型 (LLM) 用于慢性疾病的零射击表型化.
- 将LLM的绩效与传统的基于规则的方法进行比较.
- 在EHR数据中评估基于LLM的表型化的效率和准确性.
主要方法:
- 研究了20种慢性疾病的零射击表型,使用来自EHR的合成患者摘要.
- 评估了多种LLM (GPT-4o,GPT-3.5,LLaMA 3) 和基于规则的方法.
- 利用来自里斯本医院1000名患者的数据集进行分析.
主要成果:
- GPT-4o获得了最高的回忆率 (0.97) 和宏观F1得分 (0.92),优于其他LLM和基于规则的方法.
- 基于规则的方法显示高精度 (0.92),但回忆率较低 (0.36).
- 将基于规则的方法与LLM集成,通过集中人工努力,提高了整体表型精度.
结论:
- 使用LLM的零射击学习,特别是GPT-4o,为EHR表型化提供了一种高效和准确的方法.
- LLM显著减少了对广泛标记数据集的要求.
- 这种方法提高了慢性疾病表型的准确性和可解释性.
更多相关视频
相关概念视频
02:07Improving Translational Accuracy
2.5K
2.5K
01:22Language Development
280
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
280
01:26Pharmacokinetic Models: Comparison and Selection Criterion
20
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
20
01:26Classification of Systems-I
156
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
156
01:06Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
45
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
45
01:12Statistical Software for Data Analysis and Clinical Trials
314
Statistical software is pivotal in data analysis and clinical trials by providing tools to analyze data, draw conclusions, and make predictions. These software packages range from simple data management applications to complex analytical platforms, supporting various statistical tests, models, and simulation techniques. Their significance lies in their ability to handle vast amounts of data with precision and efficiency, enabling researchers to validate hypotheses, identify trends, and make...
314