https://doi.org/10.55788/f056dcb9
âThe commonly used AHI is a tool for physicians to diagnose OSA and to evaluate the severity of this condition,â explained Dr Sajila Wickramaratne (Icahn School of Medicine at Mount Sinai, NY, USA). âHowever, the instrument, that uses a fixed combination of ventilatory, hypoxic, and arousal domains, fails to capture the depth and breadth of sleep apnea across the domains.â She outlined that ventilatory features, such as âevent durationâ and â% of small breathsâ and arousal features such as âarousal intensityâ can characterise the disease burden along each domain. The current study aimed to assess whether a machine learning model, trained with feature from ventilatory, hypoxic, and arousal domains, is better than the AHI at generating survival profiles of patients. Dr Wickramaratne and colleagues used data from individuals who participated in the Sleep Heart Health study and had valid polysomnographs (n=5,074). Ventilatory distribution, hypoxic distribution, and arousal distribution data were created and analysed to generate survival outcomes in the AI model.
The mean follow-up duration was 8.2 years. The AI-model appeared to be slightly better at predicting sleep apnea-related mortality with a C-index of 0.63 compared to a C-index of 0.55 of the AHI-model. When the authors corrected for demographic features, like age, sex, race, BMI, prior history of cardiovascular disease, and smoking status, the AI-model and AHI-model had C-indexes of 0.79 and 0.76, respectively. âLooking at the individual facets of the respective domains, âfull wakefulnessâ appeared to be the most influential factor in this population,â added Dr Wickramaratne.
- Wickramaratne SD, et al. Physiology guided AI to predict survival curves for mortality in obstructive sleep apnea. Sleep apnea uplugged: navigating a myriad of health outcomes.
Medical writing support was provided by Robert van den Heuvel.
Copyright ©2024 Medicom Medical Publishers
Posted on
Previous Article
« Does PAP therapy truly reduce mortality in OSA? Next Article
Structural and functional lung improvement with dupilumab in asthma »
« Does PAP therapy truly reduce mortality in OSA? Next Article
Structural and functional lung improvement with dupilumab in asthma »
Table of Contents: ATS 2024
Featured articles
NOTUS: Dupilumab safe and efficacious in COPD with type 2 inflammation
Sulthiame may be the next treatment for OSA
Miscellaneous Topics
Pirfenidone may alleviate disease burden in DRCB
Can mindfulness reduce depression and anxiety in ICU survivors?
Exercise and diet improve functional status in PAH
Idiopathic Pulmonary Fibrosis
STARSCAPE: Zinpentraxin alfa does not ameliorate health status in IPF
COPD
COURSE: Encouraging results for tezepelumab in COPD
Ensifentrine delays transition from GOLD B to GOLD E in COPD
NOTUS: Dupilumab safe and efficacious in COPD with type 2 inflammation
BOREAS: Blood eosinophil count and FeNO levels predictive of dupilumab response in COPD
Respiratory Infections
Two regimens deliver high sputum conversion rates in M. xenopi pulmonary infection
Patient-reported outcomes improve practice in MAC lung disease
Novel RSV vaccine to prevent serious respiratory illness
Asthma
UCAP: Identify and treat undiagnosed COPD or asthma
Structural and functional lung improvement with dupilumab in asthma
Obstructive Sleep Apnea
Is the Apnea Hypopnea Index ready to be replaced?
Does PAP therapy truly reduce mortality in OSA?
Sulthiame may be the next treatment for OSA
Related Articles
October 30, 2022
Digital asthma intervention improves health and reduces costsÂ
© 2024 Medicom Medical Publishers. All rights reserved. Terms and Conditions | Privacy Policy
HEAD OFFICE
Laarderhoogtweg 25
1101 EB Amsterdam
The Netherlands
T: +31 85 4012 560
E: publishers@medicom-publishers.com