RESUMO
INTRODUCTION: ChatGPT, developed by OpenAI, represents the cutting-edge in its field with its latest model, GPT-4. Extensive research is currently being conducted in various domains, including cardiovascular diseases, using ChatGPT. Nevertheless, there is a lack of studies addressing the proficiency of GPT-4 in diagnosing conditions based on Electrocardiography (ECG) data. The goal of this study is to evaluate the diagnostic accuracy of GPT-4 when provided with ECG data, and to compare its performance with that of emergency medicine specialists and cardiologists. METHODS: This study has received approval from the Clinical Research Ethics Committee of Hitit University Medical Faculty on August 21, 2023 (decision no: 2023-91). Drawing on cases from the "150 ECG Cases" book, a total of 40 ECG cases were crafted into multiple-choice questions (comprising 20 everyday and 20 more challenging ECG questions). The participant pool included 12 emergency medicine specialists and 12 cardiology specialists. GPT-4 was administered the questions in a total of 12 separate sessions. The responses from the cardiology physicians, emergency medicine physicians, and GPT-4 were evaluated separately for each of the three groups. RESULTS: In the everyday ECG questions, GPT-4 demonstrated superior performance compared to both the emergency medicine specialists and the cardiology specialists (p < 0.001, p = 0.001). In the more challenging ECG questions, while Chat-GPT outperformed the emergency medicine specialists (p < 0.001), no significant statistical difference was found between Chat-GPT and the cardiology specialists (p = 0.190). Upon examining the accuracy of the total ECG questions, Chat-GPT was found to be more successful compared to both the Emergency Medicine Specialists and the cardiologists (p < 0.001, p = 0.001). CONCLUSION: Our study has shown that GPT-4 is more successful than emergency medicine specialists in evaluating both everyday and more challenging ECG questions. It performed better compared to cardiologists on everyday questions, but its performance aligned closely with that of the cardiologists as the difficulty of the questions increased.
RESUMO
BACKGROUND: Selective lung intubation is a life-saving procedure in emergency departments. While various equipment can be used in selective lung intubation, most of this equipment is not readily available; therefore, single-lumen endotracheal intubations are performed for rapid interventions. MATERIALS AND METHODS: This study was designed as a randomized, prospective, cross-over study using the 90° rotation technique for selective intubation on a manikin model with and without endotracheal tube introducer (ETI) in difficult airway settings. Forty-six emergency physicians were included in the study. The primary outcome was evaluating time to selective intubations, and secondary outcomes were first and second attempt success rates and the self-perceived difficulty level of each method according to the participants. RESULTS: The mean time to the first successful endotracheal intubation was significantly longer for both right selective and left selective intubations with ETI utilization than without ([39.71 ± 9.83 vs. 21.86 ± 5.94 s], [P < 0.001]), ([42.2 ± 10.81 vs. 26.23 ± 7.97 s], [P < 0.001], respectively). The first-pass success rate did not differ for right selective intubation with or without an ETI (45/46 [97.8%] and 45/46 [97.8%], respectively). However, the first-pass success rate for left selective intubation was significantly higher with ETI as compared to without an ETI (30/46 [65.2%] and 13/46 [28.3%], respectively) (P < 0.001). CONCLUSIONS: While the success rates of right selective intubation were the same, the left selective intubation success rates with ETI are higher than the styletted endotracheal tube, which can be strong evidence for this method's applicability in practice. Expanding the use of ETI and increasing the experience of the practitioners can contribute to further success.
RESUMO
BACKGROUND: Airway management methods during out-of-hospital cardiac arrest remain controversial. OBJECTIVES: This study aimed to compare the impact of using an endotracheal tube introducer with a Macintosh laryngoscope on the first-pass success rates of final-year medical students on a manikin during continuous chest compressions with a mechanical compression device. METHODS: Fifty-two final-year students of the faculty of medicine performed endotracheal intubations on a manikin using the Macintosh laryngoscope with and without the endotracheal tube introducer during chest compressions. First-pass success rates, the times of endotracheal intubations, the second endotracheal intubation attempt success rates, and the difficulty level of each method according to the participants' perceptions were measured. RESULTS: First-pass success rates did not differ using an endotracheal tube introducer as an adjunct to a Macintosh laryngoscope. Second endotracheal intubation attempt success rates also did not differ by endotracheal tube introducer use. The usage of an endotracheal tube introducer required significantly longer endotracheal intubation time than using only a Macintosh laryngoscope. The perception of difficulty was significantly lower with endotracheal tube introducer use. CONCLUSION: The use of an endotracheal tube introducer as an adjunct to a Macintosh laryngoscope is not associated with higher first-pass success rates during mechanical chest compressions in adult simulations performed by final-year medical students. © 2020 Elsevier Inc.
