Perceptions of large language models in medical education and clinical practice among pediatric emergency physicians in Saudi Arabia: a multiregional cross-sectional study
- Yara AlGoraini 1, Mashhour Alsayyali 2, Ola Alotaibi 1, Ibtihal Almeshawi 1, Fahad Alaifan 1, Rawan Alrashed 1
- 1Pediatric Emergency Department, King Fahad Medical City, Riyadh, Saudi Arabia.
- 2Pediatric Emergency Department, Armed Forced Hospital Alhada, Taif, Saudi Arabia.
- 0Pediatric Emergency Department, King Fahad Medical City, Riyadh, Saudi Arabia.
Related Experiment Videos
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Pediatric emergency medicine physicians in Saudi Arabia are optimistic about artificial intelligence (AI) and ChatGPT for clinical practice and education. However, concerns regarding accuracy and patient safety necessitate careful implementation strategies.
Area Of Science
- Medical Informatics
- Artificial Intelligence in Healthcare
- Pediatric Emergency Medicine
Background
- Artificial intelligence (AI) is transforming healthcare, yet its value perception among pediatric emergency medicine (PEM) physicians in Saudi Arabia remains understudied.
- This research investigates PEM physicians' views on AI, specifically ChatGPT, in clinical settings and medical education.
Purpose Of The Study
- To assess the perceptions and experiences of Saudi Arabian PEM physicians regarding AI and ChatGPT.
- To evaluate the perceived benefits, limitations, and utility of AI tools in PEM clinical practice and education.
Main Methods
- A cross-sectional, web-based survey was administered to 100 PEM physicians across Saudi Arabia.
- The survey collected data on demographics, AI experience, perceived AI benefits/limitations, and evaluations of ChatGPT-generated content for clinical scenarios and education.
Main Results
- 96% of PEM physicians anticipate a significant role for AI (e.g., ChatGPT) in future PEM.
- High agreement exists on AI's utility in medical education (91%) and clinical practice, including differential diagnosis (77%) and documentation (78%).
- While ChatGPT responses were rated highly for validity and educational value, concerns persist regarding accuracy (83%), patient safety (56%), and regulatory guidance (52%).
Conclusions
- Saudi PEM physicians express strong interest in integrating AI tools like ChatGPT into their workflows.
- Despite optimism, significant concerns about accuracy, safety, and ethics underscore the need for robust regulatory frameworks and structured implementation strategies for AI in PEM.
Related Experiment Videos
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.

