Answers are grounded in this paper and cite their sources.
Cross-sectional study compares AI-generated sleep quality tool with PSQI in undergraduate medical students, indicating potential differences in assessment outcomes.
Objectives: Recently, artificial intelligence (AI) has been increasingly utilized in sleep medicine for various tasks, including scoring respiratory events and staging sleep. Regardless of these AI developments in the field of sleep, sleep assessment devices require stringent validation to enhance the reliability and accuracy of their reports. The present study aims to analyze the performance of an AI-generated assessment tool of sleep quality in comparison with the Pittsburgh Sleep Quality Index (PSQI) among undergraduate medical students. By evaluating this agreement and comparing these two assessment tools, we aim to explore the potential of AI in expanding personalized sleep medicine. Material and Methods: This was a cross-sectional study conducted among 300 undergraduate medical students using two sleep assessment tools. The first is the traditional PSQI tool, and the second is an AI-generated sleep quality assessment tool for undergraduate medical students, structured and designed by Chat-GPT, which utilizes the same seven domains as the PSQI. Results: The current study found out that the mean score of the AI-generated assessment (10.65 ± 2.30) was lower than the mean PSQI score (11.94 ± 2.45). In addition, a slight agreement was found between these two scores, which was shown by Cohen’s weighted kappa coefficient of 0.133. This suggests that the AI tool may underestimate the sleep quality assessment compared to PSQI scoring. Conclusion: While the AI-generated questionnaire for sleep quality assessment has the potential benefit of scalability and automation in research, the present study highlights the crucial necessity for careful training and validation of AI tools.
No takes yet. Share an insight, caveat, or question.
Dharani et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: