Deep learning methods, such as the proposed CNN model, can accurately predict persistent SAD based on MR images. Further replication of these findings will allow early initiation of adjunctive pharmacologic treatment in high-risk patients, along with CPAP, to improve quality of life and occupational fitness. Future augmentation of this approach with explainable artificial intelligence methods may elucidate the neuroanatomical areas underlying persistent SAD to provide mechanistic insights and novel therapeutic targets.
Keyphrases
- deep learning
- artificial intelligence
- convolutional neural network
- obstructive sleep apnea
- big data
- machine learning
- end stage renal disease
- newly diagnosed
- positive airway pressure
- chronic kidney disease
- ejection fraction
- contrast enhanced
- prognostic factors
- peritoneal dialysis
- body composition
- physical activity
- magnetic resonance
- white matter
- optical coherence tomography
- soft tissue
- patient reported
- subarachnoid hemorrhage
- smoking cessation