EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-assisted decision-making in mild traumatic brain injury

Yavuz Yigit, Mahmut Firat Kaynak, Baha Alkahlout, Shabbir Ahmed, Serkan Günay, Asim Enes Ozbek

BMC Emergency Medicine · 12.03.2025 · 25 (1)

DOI: 10.1186/s12873-024-01159-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BMC Emergency Medicine, online erschienen am 12.03.2025. Verfasst von Yavuz Yigit und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, Hamad Medical Corporation, Hamad General Hospital, Doha, 3050, Qatar. yyigit@hamad.qa. Hauptthemen laut MEDLINE: Clinical Decision-Making, Brain Concussion. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Qatar National Library.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study evaluates the potential use of ChatGPT in aiding clinical decision-making for patients with mild traumatic brain injury (TBI) by assessing the quality of responses it generates for clinical care.

Methods

Seventeen mild TBI case scenarios were selected from PubMed Central, and each case was analyzed by GPT-4 (March 21, 2024, version) between April 11 and April 20, 2024. Responses were evaluated by four emergency medicine specialists, who rated the ease of understanding, scientific adequacy, and satisfaction with each response using a 7-point Likert scale. Evaluators were also asked to identify critical errors, defined as mistakes in clinical care or interpretation that could lead to morbidity or mortality. The readability of GPT-4’s responses was also assessed using the Flesch Reading Ease and Flesch-Kincaid Grade Level tools.

Results

There was no significant difference in the ease of understanding between responses with and without critical errors ( p = 0.133). However, responses with critical errors significantly reduced satisfaction and scientific adequacy ( p < 0.001). GPT-4 responses were significantly more difficult to read than the case descriptions ( p < 0.001).

Conclusion

GPT-4 demonstrates potential utility in clinical decision-making for mild TBI management, offering scientifically appropriate and comprehensible responses. However, critical errors and readability issues limit its immediate implementation in emergency settings without oversight by experienced medical professionals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Clinical Decision-MakingBrain ConcussionHumansMaleFemaleAdult

Stichwörter der Autor:innen

Artificial IntelligenceChatGPTClinical Decision SupportEmergency MedicineReadabilityTraumatic Brain Injury

Autor:innen und Institutionen

  • Department of Emergency Medicine, Hamad Medical Corporation, Hamad General Hospital, Doha, 3050, Qatar. yyigit@hamad.qa.
  • Blizard Institute, Queen Mary University, London, UK. yyigit@hamad.qa.
  • Primary Health Care Corporation, Doha, Qatar.
  • Department of Emergency Medicine, Hamad Medical Corporation, Hamad General Hospital, Doha, 3050, Qatar.
  • Çorum Erol Olçok Education and Research Hospital, Department of Emergency Medicine, Hitit University, Çorum, Turkey.
  • Department of Emergency Medicine, Kocaeli City Hospital, Kocaeli, Turkey.

Förderung

  • Qatar National Library

Zitieren

APA

Yigit, Y., Kaynak, M. F., Alkahlout, B., Ahmed, S., Günay, S., & Ozbek, A. E. (2025). AI-assisted decision-making in mild traumatic brain injury. BMC Emergency Medicine, 25(1). https://doi.org/10.1186/s12873-024-01159-8

Vancouver

Yigit Y, Kaynak MF, Alkahlout B, Ahmed S, Günay S, Ozbek AE. AI-assisted decision-making in mild traumatic brain injury. BMC Emergency Medicine. 2025;25(1). doi:10.1186/s12873-024-01159-8

BibTeX
@article{Yigit2025,
  author = {Yigit, Yavuz and Kaynak, Mahmut Firat and Alkahlout, Baha and Ahmed, Shabbir and Günay, Serkan and Ozbek, Asim Enes},
  title = {AI-assisted decision-making in mild traumatic brain injury},
  journal = {BMC Emergency Medicine},
  year = {2025},
  volume = {25},
  number = {1},
  doi = {10.1186/s12873-024-01159-8}
}
Kostenlos starten →