Chat GPT for the management of obstructive sleep apnea: do we have a polar star?

PURPOSE

This study explores the potential of the Chat-Generative Pre-Trained Transformer (Chat-GPT), a Large Language Model (LLM), in assisting healthcare professionals in the diagnosis of obstructive sleep apnea (OSA). It aims to assess the agreement between Chat-GPT's responses and those of expert otolaryngologists, shedding light on the role of AI-generated content in medical decision-making.

METHODS

A prospective, cross-sectional study was conducted, involving 350 otolaryngologists from 25 countries who responded to a specialized OSA survey. Chat-GPT was tasked with providing answers to the same survey questions. Responses were assessed by both super-experts and statistically analyzed for agreement.

RESULTS

The study revealed that Chat-GPT and expert responses shared a common answer in over 75% of cases for individual questions. However, the overall consensus was achieved in only four questions. Super-expert assessments showed a moderate agreement level, with Chat-GPT scoring slightly lower than experts. Statistically, Chat-GPT's responses differed significantly from experts' opinions (p = 0.0009). Sub-analysis revealed areas of improvement for Chat-GPT, particularly in questions where super-experts rated its responses lower than expert consensus.

CONCLUSIONS

Chat-GPT demonstrates potential as a valuable resource for OSA diagnosis, especially where access to specialists is limited. The study emphasizes the importance of AI-human collaboration, with Chat-GPT serving as a complementary tool rather than a replacement for medical professionals. This research contributes to the discourse in otolaryngology and encourages further exploration of AI-driven healthcare applications. While Chat-GPT exhibits a commendable level of consensus with expert responses, ongoing refinements in AI-based healthcare tools hold significant promise for the future of medicine, addressing the underdiagnosis and undertreatment of OSA and improving patient outcomes.

Kangaroo mother method: randomised controlled trial of an alternative method of care for stabilised low-birthweight infants. Maternidad Isidro Ayora Study Team

Because resources for care of low-birthweight (LBW) infants in developing countries are scarce, the Kangaroo mother method (KMM) was developed. The infant is kept upright in skin-to-skin contact with the mother's breast. Previous studies reported several benefits with the KMM but interpretation of their findings is limited by small size and design weaknesses. We have done a longitudinal, randomised, controlled trial at the Isidro Ayora Maternity Hospital in Quito, Ecuador. Infants with LBW (< 2000 g) who satisfied out-of-risk criteria of tolerance of food and weight stabilisation were randomly assigned to KMM and control (standard incubator care) groups (n = 128 and 147, respectively). During 6 months of follow-up the KMM group had a significantly lower rate than the control group of serious illness (lower-respiratory-tract disorders, apnoea, aspiration, pneumonia, septicaemia, general infections; 7 [5%] vs 27 [18%], p < 0.002), although differences between the groups in less severe morbidity were not significant. There was no significant difference in growth or in the proportion of women breastfeeding, perhaps because the proportion breastfeeding was high in both groups owing to strong promotion. Mortality was the same in both groups; most deaths occurred during the stabilisation period before randomisation. KMM mothers made more unscheduled clinic visits than control mothers but their infants had fewer re-admissions and so the cost of care was lower with the KMM. Since the eligibility criteria excluded nearly 50% of LBW infants from the study, the KMM is not universally applicable to these infants. The benefits might be greater in populations where breastfeeding is not so common.