Comparing ChatGPT and clinical nurses' performances on tracheostomy care: A cross-sectional study

Comparing ChatGPT and clinical nurses' performances on tracheostomy care: A cross-sectional study

2024 | Tongyao Wang, Juan Mu, Jialing Chen, Chia-Chin Lin
A cross-sectional study compared the performance of ChatGPT-3.5, ChatGPT-4.0, and clinical nurses in answering tracheostomy care questions. The study used 43 multiple-choice questions to evaluate accuracy, with responses graded on a 3-point scale (correct, partially correct, incorrect). ChatGPT-4.0 showed significantly higher accuracy (64.3% correct) compared to ChatGPT-3.5 (60.5%) and clinical nurses (36.7%). ChatGPT-4.0 performed well across all domains, including airway humidification, cuff management, tracheostomy tube care, suction techniques, and complication management. However, nurses performed poorly in five domains, with only the 'care for the tracheostomy stoma and surrounding skin' domain showing no significant difference. Prompt variations had no impact on ChatGPT accuracy. The study highlights ChatGPT-4.0's potential as a reliable tool for tracheostomy care information, offering accurate and efficient responses. It may serve as a complementary tool for patients and healthcare providers to enhance knowledge in tracheostomy care. The findings suggest that ChatGPT-4.0 could be a valuable resource for healthcare professionals and patients seeking information on tracheostomy care.A cross-sectional study compared the performance of ChatGPT-3.5, ChatGPT-4.0, and clinical nurses in answering tracheostomy care questions. The study used 43 multiple-choice questions to evaluate accuracy, with responses graded on a 3-point scale (correct, partially correct, incorrect). ChatGPT-4.0 showed significantly higher accuracy (64.3% correct) compared to ChatGPT-3.5 (60.5%) and clinical nurses (36.7%). ChatGPT-4.0 performed well across all domains, including airway humidification, cuff management, tracheostomy tube care, suction techniques, and complication management. However, nurses performed poorly in five domains, with only the 'care for the tracheostomy stoma and surrounding skin' domain showing no significant difference. Prompt variations had no impact on ChatGPT accuracy. The study highlights ChatGPT-4.0's potential as a reliable tool for tracheostomy care information, offering accurate and efficient responses. It may serve as a complementary tool for patients and healthcare providers to enhance knowledge in tracheostomy care. The findings suggest that ChatGPT-4.0 could be a valuable resource for healthcare professionals and patients seeking information on tracheostomy care.
Reach us at info@futurestudyspace.com
[slides and audio] Comparing ChatGPT and clinical nurses%E2%80%99 performances on tracheostomy care%3A A cross-sectional study