Seifen Christopher, Huppertz Tilman, Gouveris Haralampos, Bahr-Hamm Katharina, Pordzik Johannes, Eckrich Jonas, Smith Harry, Kelsey Tom, Blaikie Andrew, Matthias Christoph, Kuhn Sebastian, Buhr Christoph Raphael
Sleep Medicine Center & Department of Otolaryngology, Head and Neck Surgery, University Medical Center Mainz, Mainz, Germany.
School of Computer Science, University of St Andrews, St Andrews, UK.
Eur Arch Otorhinolaryngol. 2025 Mar;282(3):1631-1639. doi: 10.1007/s00405-024-08985-3. Epub 2024 Oct 20.
From a healthcare professional's perspective, the use of ChatGPT (Open AI), a large language model (LLM), offers huge potential as a practical and economic digital assistant. However, ChatGPT has not yet been evaluated for the interpretation of polysomnographic results in patients with suspected obstructive sleep apnea (OSA).
AIMS/OBJECTIVES: To evaluate the agreement of polysomnographic result interpretation between ChatGPT-4o and a board-certified sleep physician and to shed light into the role of ChatGPT-4o in the field of medical decision-making in sleep medicine.
For this proof-of-concept study, 40 comprehensive patient profiles were designed, which represent a broad and typical spectrum of cases, ensuring a balanced distribution of demographics and clinical characteristics. After various prompts were tested, one prompt was used for initial diagnosis of OSA and a further for patients with positive airway pressure (PAP) therapy intolerance. Each polysomnographic result was independently evaluated by ChatGPT-4o and a board-certified sleep physician. Diagnosis and therapy suggestions were analyzed for agreement.
ChatGPT-4o and the sleep physician showed 97% (29/30) concordance in the diagnosis of the simple cases. For the same cases the two assessment instances unveiled 100% (30/30) concordance regarding therapy suggestions. For cases with intolerance of treatment with positive airway pressure (PAP) ChatGPT-4o and the sleep physician revealed 70% (7/10) concordance in the diagnosis and 44% (22/50) concordance for therapy suggestions.
Precise prompting improves the output of ChatGPT-4o and provides sleep physician-like polysomnographic result interpretation. Although ChatGPT shows some shortcomings in offering treatment advice, our results provide evidence for AI assisted automation and economization of polysomnographic interpretation by LLMs. Further research should explore data protection issues and demonstrate reproducibility with real patient data on a larger scale.
从医疗保健专业人员的角度来看，使用大型语言模型（LLM）ChatGPT（OpenAI）作为实用且经济的数字助手具有巨大潜力。然而，ChatGPT尚未针对疑似阻塞性睡眠呼吸暂停（OSA）患者的多导睡眠图结果解读进行评估。
评估ChatGPT-4o与经过委员会认证的睡眠医生在多导睡眠图结果解读方面的一致性，并阐明ChatGPT-4o在睡眠医学医疗决策领域的作用。
对于这项概念验证研究，设计了40份全面的患者资料，代表广泛且典型的病例谱，确保人口统计学和临床特征的均衡分布。在测试了各种提示后，一个提示用于OSA的初步诊断，另一个用于气道正压通气（PAP）治疗不耐受的患者。每个多导睡眠图结果由ChatGPT-4o和经过委员会认证的睡眠医生独立评估。分析诊断和治疗建议的一致性。
在简单病例的诊断中，ChatGPT-4o与睡眠医生的一致性为97%（29/30）。对于相同病例，两个评估实例在治疗建议方面的一致性为100%（30/30）。对于气道正压通气（PAP）治疗不耐受的病例，ChatGPT-4o与睡眠医生在诊断方面的一致性为70%（7/10），在治疗建议方面的一致性为44%（22/50）。
精确的提示可改善ChatGPT-4o的输出，并提供类似睡眠医生的多导睡眠图结果解读。尽管ChatGPT在提供治疗建议方面存在一些不足，但我们的结果为大型语言模型辅助多导睡眠图解读的自动化和经济化提供了证据。进一步的研究应探讨数据保护问题，并在更大规模上用真实患者数据证明可重复性。
