计算机辅助口语尸检:将大型语言模型与医生进行比较,以确定塞拉利昂2019-2022年6939例死亡的原因
Richard Wen1, Anteneh Tesfaye Assalif2,3, Andy Sze-Heng Lee2
1Centre for Global Health Research, St. Michael's Hospital, Unity Health Toronto and University of Toronto, 30 Bond St, Toronto, Ontario, M5B 1W8, Canada. rwen@torontomu.ca.
BMC medicine
|December 24, 2025
概括
与传统方法相比,GPT-5等大型语言模型 (LLM) 在从口头尸检 (VA) 确定死亡原因 (COD) 方面表现优异. 这项研究提供了将LLM与医生编码集成的证据,以提高VA数据质量.
科学领域:
- 公共卫生 公共卫生
- 流行病学 流行病学
- 医疗信息学 医疗信息学
背景情况:
- 口语解剖 (VAs) 对于估计低收入和中等收入国家死亡原因 (CODs) 至关重要,因为这些国家的设施死亡登记有限.
- 医生对VA的叙事编码是当前的标准,但大型语言模型 (LLM) 为分析VA数据提供了潜在的替代方案.
- 在LLM表现和VA的医生编码之间进行可靠的比较很少.
研究的目的:
- 将三个LLM (GPT-3.5,GPT-4,GPT-5) 的性能与两个基于症状的算法 (InterVA-5,InSilicoVA) 和医生编码进行比较,用于从VA叙述中分配COD.
- 为了评估不同模型与医生分配的个人级别 (PCCC) 和人口级别 (CSMF准确性) 协议.
- 由于CODs的变化,根据年龄组 (新生儿,儿童,成年人) 分层化性能分析.
主要方法:
- 分析了来自塞拉利昂的6939份VA记录 (2019-2022年).
- 将GPT模型 (使用叙述) 与InterVA-5和InSilicoVA (使用问卷) 与医生分配的COD进行比较.
- 评估使用因特定死亡率分数 (CSMF) 准确度和部分机会校正一致性 (PCCC),按年龄分层.
主要成果:
- GPT-5显示了最高的整体性能 (PCCC = 0.71),超过了GPT-4 (0.61),GPT-3.5 (0.56),InSilicoVA (0.44) 和InterVA-5 (0.44) 的表现.
- 此外,GPT-5在成人 (0.68),儿童 (0.71) 和新生儿 (0.65) 死亡中表现最好.
- 在人口层面上,GPT-5实现了最高的CSMF精度 (0.9),明显超过其他模型.
结论:
- 从VA中分配COD的传统算法模型来看,LLM,特别是GPT-5显示出了显著的改进.
- 在个人层面上,LLM和InSilicoVA都在特定的COD方面表现强.
- 这些发现支持将LLM和算法方法与医生编码相结合,以提高VA数据在公共卫生方面的准确性和实用性.
相关概念视频
Actuarial Approach
276
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
276
Classification of Illness
8.5K
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...
8.5K
Comparing the Survival Analysis of Two or More Groups
531
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
531
Statistical Methods for Analyzing Epidemiological Data
864
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
864
Causality in Epidemiology
1.4K
Causality or causation is a fundamental concept in epidemiology, vital for understanding the relationships between various factors and health outcomes. Despite its importance, there's no single, universally accepted definition of causality within the discipline. Drawing from a systematic review, causality in epidemiology encompasses several definitions, including production, necessary and sufficient, sufficient-component, counterfactual, and probabilistic models. Each has its strengths and...
1.4K

