Comparison of Advanced Cardiac Life Information of Emergency Department Specialist with Artificial Intelligence: Multicenter Study

Background and aim: The delivery of cardiopulmonary resuscitation (CPR) after sudden cardiac death is a critical training component in emergency medicine. This study aims to investigate the performance of artificial intelligence applications in this area, particularly in relation to evidence-based medical systems and current CPR guidelines.
Patients and methods: This study was conducted as a multi-centre study involving emergency medicine specialists. A 20-question test based on the Advanced Life Support (ALS) guidelines published by the American Heart Association (AHA) was administered to LLM-2 and LLM-1. Correct answers were scored as 1 point each and the data collected was analysed.
Resutls: The study included 22 Emergency Medicine Specialists (EMS) with a mean age of 32.36±3.84 years. It was observed that the performance of EMS and LLM-1 was significantly higher than that of LLM-2, while there was no significant difference between EMS and LLM-1. Correlation analysis among the participants revealed a negative correlation between age, years of professional experience, years of working in the emergency department and the average score.
Conclution: Artificial intelligence systems still have many limiting factors. Although the responses provided by LLM-2 were found to be inadequate, it appears that LLM-1 can be used as a supporting system.

Artificial intelligence, Gemini, Chatgpt

1. Berg, K.M., et al., Adult Advanced Life Support: 2020 International Consensus on Cardiopulmonary Resuscitation and Emergency Cardiovascular Care Science With Treatment Recommendations. 2020. 142(16_suppl_1): p. S92-S139. [Google Scholar] [Crossref]

2. Soar, J., et al., European Resuscitation Council Guidelines 2021: Adult advanced life support. Resuscitation, 2021. 161: p. 115-151. [Google Scholar] [Crossref]

3. TUK. Emergency Medicine Specialist Education. 2021 [cited 2024; Available from: https://tuk.saglik.gov.tr/TR,50050/acil-tip.html. [Google Scholar] [Crossref]

4. Gunay, S., et al., Comparison of emergency medicine specialist, cardiologist, and chat-GPT in electrocardiography assessment. Am J Emerg Med, 2024. 80: p. 51-60. [Google Scholar] [Crossref]

5. OpenAI. Chat GPT. 2022; Available from: openai.com/chatgpt. [Google Scholar] [Crossref]

6. Google. Gemini. 2023; Available from: https://gemini.google.com. [Google Scholar] [Crossref]

7. Martinez-Selles, M. and M. Marina-Breysse, Current and Future Use of Artificial Intelligence in Electrocardiography. J Cardiovasc Dev Dis, 2023. 10(4). [Google Scholar] [Crossref]

8. Chang, K.C., et al., Usefulness of Machine Learning-Based Detection and Classification of Cardiac Arrhythmias With 12-Lead Electrocardiograms. Can J Cardiol, 2021. 37(1): p. 94-104. [Google Scholar] [Crossref]

9. Neri, E., et al., Artificial intelligence: Who is responsible for the diagnosis? Radiol Med, 2020. 125(6): p. 517-521. [Google Scholar] [Crossref]

10. Ramlakhan, S., et al., Understanding and interpreting artificial intelligence, machine learning and deep learning in Emergency Medicine. Emerg Med J, 2022. 39(5): p. 380-385. [Google Scholar] [Crossref]

11. Ehrlich, H., M. McKenney, and A. Elkbuli, The niche of artificial intelligence in trauma and emergency medicine. Am J Emerg Med, 2021. 45: p. 669-670. [Google Scholar] [Crossref]

12. Watari, T., et al., Performance Comparison of ChatGPT-4 and Japanese Medical Residents in the General Medicine In-Training Examination: Comparison Study. JMIR Med Educ, 2023. 9: p. e52202. [Google Scholar] [Crossref]

13. Meral, G., et al., Comparative analysis of ChatGPT, Gemini and emergency medicine specialist in ESI triage assessment. Am J Emerg Med, 2024. 81: p. 146-150. [Google Scholar] [Crossref]

14. Moor, J.J.A.M., The Dartmouth College artificial intelligence conference: The next fifty years. 2006. 27(4): p. 87-87. [Google Scholar] [Crossref]

15. Solomonoff, R.J.J.H.S.M., The time scale of artificial intelligence: Reflections on social effects. 1985. 5(2): p. 149-153. [Google Scholar] [Crossref]

16. Jumper, J., et al., Highly accurate protein structure prediction with AlphaFold. Nature, 2021. 596(7873): p. 583-589. [Google Scholar] [Crossref]

17. Semeraro, F., et al., Clinical questions on advanced life support answered by artificial intelligence. A comparison between ChatGPT, Google Bard and Microsoft Copilot. Resuscitation, 2024. 195: p. 110114. [Google Scholar] [Crossref]

• Treasure of 6th Edition of Organon of Medicine- Lm Potency
• Neurobehavioral and Immune-Histochemical Effects of Daucus Carota Ethanolic Leaf Extract in Cadmium-Induced Toxicity of the Hippocampus and Prefrontal Cortex of Adult Wistar Rats
• Unveiling the Antimicrobial Potential of Homoeopathic Sarcode and Bowel Nosode: A Study on Histaminum and Dysenteriae Co against Escherichia Coli And Klebsiella Bacteria
• Incidence of Cardiovascular Events in Patients Receiving Hematopoietic Stem Cell Transplant (HSCT) in HCTM – (A Retrospective Cohort Study)
• A Prospective Case Study Examining the Effectiveness of Homoeopathic Medicine in Treating Degenerative Changes in the Lumbar Spine-A Case Report