文献速递新生儿

大语言模型在低收入和中等收入国家母婴保健中的应用评估

Large Language Models for Maternal and Neonatal Health Care in Low- and Middle-Income Countries.
PubMed 文献 · J Pediatr · 2026-02-13

本研究评估了GPT-4o在低收入和中等收入国家母婴保健领域的表现,覆盖6个WHO区域和204个国家。结果显示GPT-4o在生成病例时不能反映真实患病率、对高婴儿死亡率国家存在偏见、44%的妊娠统计数据在无数据区域被错误提供且46.7%的引用有误,但79%的妊娠相关医学考试题回答正确。结论指出通用大语言模型在指导母婴保健方面存在重要局限性。

要点

  • GPT-4o生成的医学病例未反映真实患病率,过度代表美洲区域。
  • GPT-4o对高婴儿死亡率国家的主观健康话题排名偏低,显示明确偏见。
  • GPT-4o在44%的情况下为无统计数据区域提供妊娠相关统计且未说明不确定性。

核心结论

  • GPT-4o在全球范围内提供准确答案面临挑战,通用大语言模型在指导低收入和中等收入国家母婴保健方面存在重要局限性。

研究设计与样本

  • 研究评估GPT-4o在4个母婴健康领域的表现:生成医学病例时的疾病患病率、无可靠国家患病率数据国家的患病率、标准化医学考试题、主观健康相关问题。
  • 研究使用GPT-4o应用程序编程接口(除领域2使用ChatGPT外),采用重复提示以保证答案的统计显著性,并利用6个WHO区域和204个国家的公开数据。

主要发现

  • GPT-4o生成的医学病例未反映真实结局患病率,过度代表美洲区域。
  • GPT-4o表现出明确偏见,对婴儿死亡率高的国家在主观健康相关话题上给出较低排名。
  • GPT-4o在44%的情况下为无统计数据的区域提供妊娠相关统计,且未承认不确定性;近一半(46.7%)的引用来源有误。
  • GPT-4o正确回答了大多数(79%)妊娠相关医学考试题,但在基于特定区域常见健康问题回答时出错并忽略了症状。

临床怎么用

  • 在低收入和中等收入国家使用通用大语言模型辅助母婴保健时需警惕其准确性、偏见和引用错误问题。
  • 可基于情境化数据对LLM进行微调以改善其在母婴保健中的应用。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To investigate whether large language models (LLMs) can assist with maternal and neonatal health care in low- and middle-income countries. STUDY DESIGN: We evaluated the ability of GPT-4o to generate accurate answers across countries in 4 domains related to maternal and neonatal health: (1) prevalence of conditions when generating medical case examples; (2) prevalence of conditions in countries without reliable national prevalence data; (3) standardized medical examination questions; and (4) subjective health-related questions. We used the GPT-4o Application Programming Interface except for domain 2, for which we used ChatGPT, and used repeated prompts to guarantee statistical significance of answers. We utilized publicly available data from 6 WHO regions and 204 countries. RESULTS: We observed challenges for LLMs to provide accurate answers on a global scale. Medical cases generated by GPT-4o did not reflect true prevalences of outcomes, over-representing the Americas. GPT-4o demonstrated explicit bias, giving lower rankings for subjective health-related topics to countries with high infant mortality rates. In 44% of cases, GPT-4o provided pregnancy-related statistics in regions where those statistics were not available, while not acknowledging the uncertainty, and nearly half (46.7%) of the source citations were erroneous. GPT-4o answered the majority (79%) of pregnancy-related medical examination questions correctly but made errors when answering based on prevalent health issues in specific regions while overlooking symptoms. CONCLUSIONS: Identified challenges in using GPT-4o highlight important limitations in applying general-purpose LLMs to guide maternal and neonatal healthcare in low- and middle-income countries. These findings can guide further studies and solutions in fine-tuning LLMs on contextualized data.

来源:J Pediatr,查看原文。版权归原作者所有。

引用

  1. Yu L, Darmstadt GL, Ward V, et al. Large Language Models for Maternal and Neonatal Health Care in Low- and Middle-Income Countries. J Pediatr. 2026. PMID: 41692226. doi:10.1016/j.jpeds.2026.115037

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。