Development of a Machine Learning Model for Screening Sleep Apnea in Heart Failure Patients Using Sleep Sensor Data

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Development of a Machine Learning Model for Screening Sleep Apnea in Heart Failure Patients Using Sleep Sensor Data
Συγγραφείς: Gunasegarama, Mathushan, Dinesen, Birthe, Müller Larsen, Nikolaj, Ghamari Gilavai, Ghazal, Røge, Kristine, Kirk Østergaard, Mathias, Rovsing Jochumsen, Mads
Πηγή: Gunasegarama, M, Dinesen, B, Müller Larsen, N, Ghamari Gilavai, G, Røge, K, Kirk Østergaard, M & Rovsing Jochumsen, M 2025, Development of a Machine Learning Model for Screening Sleep Apnea in Heart Failure Patients Using Sleep Sensor Data. in Good Evaluation-Better Digital Health. IOS Press, Studies in Health Technology and Informatics, vol. 332, pp. 62-66, EFMI Special Topic Conference 2025, Osnabrück, Germany, 20/10/2025. https://doi.org/10.3233/SHTI251496
Στοιχεία εκδότη: IOS Press, 2025.
Έτος έκδοσης: 2025
Θεματικοί όροι: Machine Learning, Male, Sleep Apnea Syndromes/diagnosis, Diagnosis, Computer-Assisted/methods, Heart Failure/complications, Mass Screening/methods, Humans, Reproducibility of Results, Polysomnography/methods, Female, Sensitivity and Specificity
Περιγραφή: Sleep apnea (SA) is a prevalent disorder among individuals with heart failure (HF), often leading to complications. Early identification is essential for timely interventions and better outcomes. This study explores the feasibility of developing a screening tool for SA in patients with HF using data from the Future Patient Telerehabilitation program. A random forest classifier was used to develop a predictive model, achieving a promising receiver operating characteristic area under the curve (ROC-AUC) of 0.85, suggesting that the random forest classifier has the potential as a SA screening tool for HF patients. However, the study lacked key variables, such as oxygen saturation, that are strong predictors for SA assessment according to current literature; this limits the model’s generalizability. Despite this, the findings indicate that the ML model shows promise for screening SA in HF patients, highlighting the need for high-quality, standardized data from future clinical trials to enhance its accuracy and clinical utility.
Τύπος εγγράφου: Part of book or chapter of book
Περιγραφή αρχείου: application/pdf
ISSN: 1879-8365
0926-9630
DOI: 10.3233/shti251496
Σύνδεσμος πρόσβασης: https://vbn.aau.dk/da/publications/d6c0a653-d6c5-4b54-b6ba-c1ca86fcc710
https://vbn.aau.dk/ws/files/798726352/SHTI-332-SHTI251496.pdf
https://doi.org/10.3233/SHTI251496
Αριθμός Καταχώρησης: edsair.dedup.wf.002..8c6edb253ca1d15c2583c7124bbafa43
Βάση Δεδομένων: OpenAIRE
Περιγραφή
ISSN:18798365
09269630
DOI:10.3233/shti251496