Heart failure & cardiomyopathies
Machine learning-based detection of sleep-disordered breathing in hypertrophic cardiomyopathy
Performance · High ODI (3% ODI >10) in the test setResult — go to the resultOdds ratio 20.9 95% CI 5.3–105.8Authors' conclusion
Our study serves as the first to develop a machine learning-based discriminant model for the concomitance of SDB in patients with HCM.
Study context
- Population
- Consecutive patients with hypertrophic cardiomyopathy undergoing nocturnal oximetry
- Participants
- 369 patients
- Comparison
- Random forest discriminant model vs previous logistic regression model
- Outcome
- High ODI (3% ODI >10), correlating with moderate or severe SDB
Methodological detailsmulticentre, machine learning (random forest), training set (80%) and test set (20%)
- Multicentre
- Machine learning (random forest)
- Training set (80%) and test set (20%)
Performance
High ODI (3% ODI >10) in the test set
Odds ratio
20.9
95% CI 5.3–105.8
P < 0.001
By group
High-probabilityvs Low-probability
OR 20.9 (95% CI 5.3–105.8); P < 0.001
As reported in the abstract
Original publication
Machine learning-based detection of sleep-disordered breathing in hypertrophic cardiomyopathy. Heart. Published 8 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →