EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitSystematische ÜbersichtMetaanalyseOpen Access

Diagnostic Accuracy of ChatGPT for Patients' Triage; a Systematic Review and Meta-Analysis.

Navid Kaboudi, Saeedeh Firouzbakht, Mohammad Shahir Eftekhar, Fatemeh Fayazbakhsh, Niloufar Joharivarnoosfaderani, Salar Ghaderi, Mohammadreza Dehdashti, Yasmin Mohtasham Kia, Maryam Afshari, Maryam Vasaghi-Gharamaleki, Leila Haghani, Zahra Moradzadeh und 4 weitere

Archives of Academic Emergency Medicine · 01.01.2024 · 12 (1) · e60-e60

DOI: 10.22037/aaem.v12i1.2384 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Archives of Academic Emergency Medicine, erschienen am 01.01.2024. Verfasst von Navid Kaboudi und 15 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Pharmacy, Tabriz University of Medical Sciences, Tabriz, Iran. Die Arbeit wurde bisher 34-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Artificial intelligence (AI), particularly ChatGPT developed by OpenAI, has shown the potential to improve diagnostic accuracy and efficiency in emergency department (ED) triage. This study aims to evaluate the diagnostic performance and safety of ChatGPT in prioritizing patients based on urgency in ED settings.

Methods

A systematic review and meta-analysis were conducted following PRISMA guidelines. Comprehensive literature searches were performed in Scopus, Web of Science, PubMed, and Embase. Studies evaluating ChatGPT's diagnostic performance in ED triage were included. Quality assessment was conducted using the QUADAS-2 tool. Pooled accuracy estimates were calculated using a random-effects model, and heterogeneity was assessed with the I² statistic.

Results

Fourteen studies with a total of 1,412 patients or scenarios were included. ChatGPT 4.0 demonstrated a pooled accuracy of 0.86 (95% CI: 0.64-0.98) with substantial heterogeneity (I² = 93%). ChatGPT 3.5 showed a pooled accuracy of 0.63 (95% CI: 0.43-0.81) with significant heterogeneity (I² = 84%). Funnel plots indicated potential publication bias, particularly for ChatGPT 3.5. Quality assessments revealed varying levels of risk of bias and applicability concerns.

Conclusion

ChatGPT, especially version 4.0, shows promise in improving ED triage accuracy. However, significant variability and potential biases highlight the need for further evaluation and enhancement.

Schlagwörter

Stichwörter der Autor:innen

ChatGPTdiagnostic performanceemergency departmenttriage

Autor:innen und Institutionen

  • Faculty of Pharmacy, Tabriz University of Medical Sciences, Tabriz, Iran.
  • Department of Pediatrics, School of Medicine, Bushehr University of Medical Sciences, Bushehr, Iran.
  • Department of Surgery, School of Medicine, Qom University of Medical Sciences, Qom, Iran.
  • School of Medicine, Birjand University of Medical Sciences, Birjand, iran.
  • Faculty of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
  • Research Center for Evidence-based Medicine, Faculty of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran.

Förderung

  • NCI NIH HHS

Zitieren

APA

Kaboudi, N., Firouzbakht, S., Shahir Eftekhar, M., Fayazbakhsh, F., Joharivarnoosfaderani, N., Ghaderi, S., Dehdashti, M., Mohtasham Kia, Y., Afshari, M., Vasaghi-Gharamaleki, M., Haghani, L., Moradzadeh, Z., Khalaj, F., Mohammadi, Z., Hasanabadi, Z., & Shahidi, R. (2024). Diagnostic Accuracy of ChatGPT for Patients' Triage; a Systematic Review and Meta-Analysis. Archives of Academic Emergency Medicine, 12(1), e60-e60. https://doi.org/10.22037/aaem.v12i1.2384

Vancouver

Kaboudi N, Firouzbakht S, Shahir Eftekhar M, Fayazbakhsh F, Joharivarnoosfaderani N, Ghaderi S, et al. Diagnostic Accuracy of ChatGPT for Patients' Triage; a Systematic Review and Meta-Analysis. Archives of Academic Emergency Medicine. 2024;12(1):e60-e60. doi:10.22037/aaem.v12i1.2384

BibTeX
@article{Kaboudi2024,
  author = {Kaboudi, Navid and Firouzbakht, Saeedeh and Shahir Eftekhar, Mohammad and Fayazbakhsh, Fatemeh and Joharivarnoosfaderani, Niloufar and Ghaderi, Salar and Dehdashti, Mohammadreza and Mohtasham Kia, Yasmin and Afshari, Maryam and Vasaghi-Gharamaleki, Maryam and Haghani, Leila and Moradzadeh, Zahra and Khalaj, Fattaneh and Mohammadi, Zahra and Hasanabadi, Zahra and Shahidi, Ramin},
  title = {Diagnostic Accuracy of ChatGPT for Patients' Triage; a Systematic Review and Meta-Analysis},
  journal = {Archives of Academic Emergency Medicine},
  year = {2024},
  volume = {12},
  number = {1},
  pages = {e60--e60},
  doi = {10.22037/aaem.v12i1.2384}
}
Kostenlos starten →