Artificial intelligence chatbots as sources of patient education material for obstructive sleep apnoea: ChatGPT versus Google Bard.

PURPOSE: To perform the first head-to-head comparative evaluation of patient education material for obstructive sleep apnoea generated by two artificial intelligence chatbots, ChatGPT and its primary rival Google Bard. METHODS: Fifty frequently asked questions on obstructive sleep apnoea in English were extracted from the patient information webpages of four major sleep organizations and categorized as input prompts. ChatGPT and Google Bard responses were selected and independently rated using the Patient Education Materials Assessment Tool-Printable (PEMAT-P) Auto-Scoring Form by two otolaryngologists, with a Fellowship of the Royal College of Surgeons (FRCS) and a special interest in sleep medicine and surgery. Responses were subjectively screened for any incorrect or dangerous information as a secondary outcome. The Flesch-Kincaid Calculator was used to evaluate the readability of responses for both ChatGPT and Google Bard. RESULTS: A total of 46 questions were curated and categorized into three domains: condition (n = 14), investigation (n = 9) and treatment (n = 23). Understandability scores for ChatGPT versus Google Bard on the various domains were as follows: condition 90.86% vs.76.32% (p < 0.001); investigation 89.94% vs. 71.67% (p < 0.001); treatment 90.78% vs.73.74% (p < 0.001). Actionability scores for ChatGPT versus Google Bard on the various domains were as follows: condition 77.14% vs. 51.43% (p < 0.001); investigation 72.22% vs. 54.44% (p = 0.05); treatment 73.04% vs. 54.78% (p = 0.002). The mean Flesch-Kincaid Grade Level for ChatGPT was 9.0 and Google Bard was 5.9. No incorrect or dangerous information was identified in any of the generated responses from both ChatGPT and Google Bard. CONCLUSION: Evaluation of ChatGPT and Google Bard patient education material for OSA indicates the former to offer superior information across several domains.

Performance of artificial intelligence chatbots in sleep medicine certification board exams: ChatGPT versus Google Bard.

PURPOSE: To conduct a comparative performance evaluation of GPT-3.5, GPT-4 and Google Bard in self-assessment questions at the level of the American Sleep Medicine Certification Board Exam. METHODS: A total of 301 text-based single-best-answer multiple choice questions with four answer options each, across 10 categories, were included in the study and transcribed as inputs for GPT-3.5, GPT-4 and Google Bard. The first output responses generated were selected and matched for answer accuracy against the gold-standard answer provided by the American Academy of Sleep Medicine for each question. A global score of 80% and above is required by human sleep medicine specialists to pass each exam category. RESULTS: GPT-4 successfully achieved the pass mark of 80% or above in five of the 10 exam categories, including the Normal Sleep and Variants Self-Assessment Exam (2021), Circadian Rhythm Sleep-Wake Disorders Self-Assessment Exam (2021), Insomnia Self-Assessment Exam (2022), Parasomnias Self-Assessment Exam (2022) and the Sleep-Related Movements Self-Assessment Exam (2023). GPT-4 demonstrated superior performance in all exam categories and achieved a higher overall score of 68.1% when compared against both GPT-3.5 (46.8%) and Google Bard (45.5%), which was statistically significant (p value < 0.001). There was no significant difference in the overall score performance between GPT-3.5 and Google Bard. CONCLUSIONS: Otolaryngologists and sleep medicine physicians have a crucial role through agile and robust research to ensure the next generation AI chatbots are built safely and responsibly.

Rare Disorders of Painful Erection: A Cohort Study of the Investigation and Management of Stuttering Priapism and Sleep-Related Painful Erection.

BACKGROUND: A chief complaint of men with stuttering priapism (SP) and sleep-related painful erections (SRPE) is bothersome nocturnal erections that wake them up and result in poor sleep and daytime tiredness. SP and SRPE are rare entities that have similarities in their clinical features, but that require different treatment approaches. AIM: The aim of this study was to describe the clinical features, investigations, and effective management options for men with SP and SRPE. METHODS: Retrospective cohort study of 133 men with bothersome nocturnal painful erections that attended a tertiary andrology unit between 2004 and 2018. These men were divided into 3 groups. Group 1 (n = 62) contains men with sickle cell SP; group 2 (n = 40) has men with non-sickle cell SP and group 3 (n = 31) contains men with SRPE. OUTCOME: To determine the effectiveness of medical and surgical treatments for men with SP and SRPE. RESULTS: Hydroxyurea and automated exchange transfusion were the most effective treatment options in the sickle cell SP group. Hormonal manipulation and α-agonist therapies were effective in both SP cohorts (groups 1 and 2). Baclofen was the most effective therapy in men with SRPE. For men who failed medical management, implantation of a penile prosthesis resulted in complete resolution of the symptoms in men with SP (groups 1 and 2). Surgical management (penile prosthesis implantation and embolization) did not improve the patients' symptoms in the SRPE group. CLINICAL IMPLICATIONS: This study differentiates between sickle cell SP, non-sickle cell SP, and SRPE and describes effective treatment options for each group. STRENGTHS & LIMITATIONS: This is the largest cohort study for both SP and SRPE, respectively. Limitations include its retrospective nature and single-center experience. CONCLUSION: Managing men in these 3 groups differently and in accordance with the proposed treatment pathway provides a more structured approach to the management of these rare conditions. Johnson M, McNeillis S, Chiriaco G, et al. Rare Disorders of Painful Erection: A Cohort Study of the Investigation and Management of Stuttering Priapism and Sleep-Related Painful Erection. J Sex Med 2021;18:376-384.

Differences in polysomnographic, nocturnal penile tumescence and penile doppler ultrasound findings in men with stuttering priapism and sleep-related painful erections.

Men with Stuttering Priapism (SP) and sleep-related painful erections (SRPE) experience bothersome nocturnal painful erections resulting in poor sleep. The aim of this study is to observe common features and differences between men with SP and SRPE based on polysomnography, nocturnal penile tumescence (NPT), and penile doppler ultrasound (PDU). This is a prospective cohort study of 20 participants divided into two groups (Group 1 = SP [n = 12]; Group 2 = SRPE [n = 8]) with bothersome painful nocturnal erections. All participants were referred to the sleep disorder clinic to be assessed and consented for overnight polysomnography with simultaneous NPT recording and to complete validated sleep, sexual dysfunction and health-related quality of life questionnaires. Unstimulated PDU was also performed. Abnormal Polysomnographic findings (reduced sleep efficiency, total sleep time, and awake after sleep onset) were identified in both groups suggesting poor sleep. Men with SP had significantly longer erections (60.0 vs 18.5; p = 0.002) and took longer to detumesce once awake (25.7 vs 5.4 min; p = 0.001) than men with SRPE. They also had significantly higher peak systolic and end diastolic velocities on unstimulated PDU with an abnormal low resistance waveform identified. No sleep pathology was identified in men with SP. This implies a local (penile) etiology in men with SP. Men with SRPE had a normal resting PDU and abnormal sleep architecture with REM awakenings and significantly more Periodic limb movements (p = 0.04) than men with SP suggesting a central (sleep-related) cause in men with SRPE. Sexual dysfunction and poor HR-QoL was identified on validated questionnaires in both groups. SP and SRPE are rare entities that share similar symptoms (painful nocturnal erections and poor sleep) but dissimilar features of nocturnal erection onset, duration and resolution with different polysomnographic features which may allude to a different pathophysiology.