medRxiv PreprintsInternational12 October 2026
AI chatbots abandon sleep apnoea referral when simulated patients minimise symptoms
This is an official announcement record
Firsthand records what medRxiv Preprints announced and links to the original. The wording below is theirs, not ours.
Background: Patients increasingly consult free artificial intelligence (AI) chatbots about their symptoms, but these models may favour agreement with the patient over accuracy. In obstructive sleep apnoea (OSA), where most cases in the general population remain undiagnosed and diagnosis depends on referral, this could validate symptom denial. We tested whether consumer chatbots maintain guideline-concordant referral when a simulated patient minimises symptoms. Methods: Seven guideline-concordant and standardised OSA vignettes (apnoea-hypopnoea-index, AHI 8-52 events/h; body mass index 28-42 kg
Read the official announcement
Opens www.medrxiv.org
More from medRxiv Preprints
- Upper cervical spinal cord morphometric charts: from population references to individualized clinical assessment12 October 2026
- Computational modelling of decision-making in suicide attempters12 October 2026
- Efficacy of Repeated-Dose Albendazole/ Mebendazole Regimens for Soil-Transmitted Helminth Infections in Paediatric Population: A Systematic Review and Meta-Analysis12 October 2026
- Dynamics of a slow-burn epidemic: the genomic epidemiology of poultry-associated Campylobacter jejuni ST474 in New Zealand12 October 2026
- EpiAlert: A Transparent CUSUM-EWMA Framework for Early Warning of Unusual Influenza-Like Illness Surveillance Activity12 October 2026
This content is for informational purposes only and is not medical advice. It is not intended to diagnose, treat, cure, or prevent any disease. Consult a healthcare professional before starting any supplement, treatment, or program — especially if you are pregnant, nursing, taking medication, or managing a health condition.