Evaluating ChatGPT and DeepSeek in postdural puncture headache management: a comparative study with international consensus guidelines
All four AI models demonstrate clinical validity, with ChatGPT-4o and DeepSeek-R1 showing stronger guideline alignment. Though largely accurate, their responses achieve only 60-80% completeness relative to medical guidelines. Healthcare professionals must exercise caution when using AI tools and should critically evaluate outputs before clinical application. While promising, their partial guideline coverage requires careful human oversight. Further validation research is essential before these models can reliably support clinical decision-making for complex conditions like PDPH.
Authors
- Jie Deng (ORCID: https://orcid.org/0000-0002-4040-1402)
- Shangfeng Yang (ORCID: https://orcid.org/0000-0002-6931-9613)
- Yali Wu
- Xiaoming Dong (ORCID: https://orcid.org/0000-0003-2413-8541)
- Qinghua Li (ORCID: https://orcid.org/0000-0002-4547-8513)
- Chuanhui Dong (ORCID: https://orcid.org/0000-0001-7165-355X)
- Xinyun Qiu (ORCID: https://orcid.org/0000-0001-6409-2408)
- Shi Chen (ORCID: https://orcid.org/0000-0003-2205-5371)
- Jianliang Sun (ORCID: https://orcid.org/0000-0001-9796-7370)
- Feifang He
- Tao Mei
- Li Xu (ORCID: https://orcid.org/0000-0003-2432-6104)
- Hanbin Wang (ORCID: https://orcid.org/0000-0002-9607-8114)
- Liang Yu (ORCID: https://orcid.org/0009-0007-3922-3454)
Institutions
- Hospital for Sick Children (CA)
- Ruijin Hospital (CN)
- Soochow University (CN)
- First Affiliated Hospital of Soochow University (CN)
Publication Details
- Journal
- BMC Neurology
- Published
- 2025-07-01
- DOI
- https://doi.org/10.1186/s12883-025-04280-8
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62