Ritaban Dutta1, Benjamin K Tong2,3, Danny J Eckert2,3,4. 1. Data61, Commonwealth Scientific and Industrial Research Organisation, Hobart, Tasmania, Australia. 2. Neuroscience Research Australia, Randwick Sydney, New South Wales, Australia. 3. School of Medical Sciences, University of New South Wales, Kensington Sydney, New South Wales, Australia. 4. Adelaide Institute for Sleep Health and Flinders Health and Medical Research Institute, Flinders University, Bedford Park Adelaide, South Australia, Australia.
Abstract
STUDY OBJECTIVES: Oral appliance (OA) therapy is a well-tolerated alternative to continuous positive airway pressure. However, it is less efficacious. A major unresolved clinical challenge is the inability to accurately predict who will respond to OA therapy. We recently developed a model to estimate obstructive sleep apnea pathophysiological endotypes. This study aimed to apply this physiological-based model to predict OA treatment responses. METHODS: Sixty-two men and women with obstructive sleep apnea (aged 29-71 years) were studied to investigate the efficacy of a novel OA device. An in-laboratory diagnostic followed by an OA treatment efficacy polysomnography were performed. Seven polysomnography variables from the diagnostic study plus age and body mass index were included in our machine-learning-based model to predict OA therapy response according to standard apnea-hypopnea index (AHI) definitions. Initially, the model was trained on data from the first 45 participants using 10-fold cross-validation. A blinded independent validation was then performed for the remaining 17 participants. RESULTS: Mean accuracy of the trained model to predict OA therapy responders vs nonresponders (AHI < 5 events/h) using 10-fold cross-validation was 91% ± 8%. In the independent blinded validation, 100% (AHI < 5 events/h); 59% (AHI < 10 events/h); 71% (50% reduction in AHI); and 82% (50% reduction in AHI to < 20 events/h) of the 17 participants were correctly classified for each of the treatment outcome definitions respectively. CONCLUSIONS: While further evaluation in larger clinical data sets is required, these findings highlight the potential to use routinely collected sleep study and clinical data with machine learning-based approaches underpinned by obstructive sleep apnea endotype concepts to help predict treatment outcomes to OA therapy for people with obstructive sleep apnea. CITATION: Dutta R, Tong BK, Eckert DJ. Development of a physiological-based model that uses standard polysomnography and clinical data to predict oral appliance treatment outcomes in obstructive sleep apnea. J Clin Sleep Med. 2022;18(3):861-870.
STUDY OBJECTIVES: Oral appliance (OA) therapy is a well-tolerated alternative to continuous positive airway pressure. However, it is less efficacious. A major unresolved clinical challenge is the inability to accurately predict who will respond to OA therapy. We recently developed a model to estimate obstructive sleep apnea pathophysiological endotypes. This study aimed to apply this physiological-based model to predict OA treatment responses. METHODS: Sixty-two men and women with obstructive sleep apnea (aged 29-71 years) were studied to investigate the efficacy of a novel OA device. An in-laboratory diagnostic followed by an OA treatment efficacy polysomnography were performed. Seven polysomnography variables from the diagnostic study plus age and body mass index were included in our machine-learning-based model to predict OA therapy response according to standard apnea-hypopnea index (AHI) definitions. Initially, the model was trained on data from the first 45 participants using 10-fold cross-validation. A blinded independent validation was then performed for the remaining 17 participants. RESULTS: Mean accuracy of the trained model to predict OA therapy responders vs nonresponders (AHI < 5 events/h) using 10-fold cross-validation was 91% ± 8%. In the independent blinded validation, 100% (AHI < 5 events/h); 59% (AHI < 10 events/h); 71% (50% reduction in AHI); and 82% (50% reduction in AHI to < 20 events/h) of the 17 participants were correctly classified for each of the treatment outcome definitions respectively. CONCLUSIONS: While further evaluation in larger clinical data sets is required, these findings highlight the potential to use routinely collected sleep study and clinical data with machine learning-based approaches underpinned by obstructive sleep apnea endotype concepts to help predict treatment outcomes to OA therapy for people with obstructive sleep apnea. CITATION: Dutta R, Tong BK, Eckert DJ. Development of a physiological-based model that uses standard polysomnography and clinical data to predict oral appliance treatment outcomes in obstructive sleep apnea. J Clin Sleep Med. 2022;18(3):861-870.
Authors: Craig L Phillips; Ronald R Grunstein; M Ali Darendeliler; Anastasia S Mihailidou; Vasantha K Srinivasan; Brendon J Yee; Guy B Marks; Peter A Cistulli Journal: Am J Respir Crit Care Med Date: 2013-04-15 Impact factor: 21.405
Authors: Lauriane Jugé; Jade Yeung; Fiona L Knapman; Peter G R Burke; Aimee B Lowth; Ken Z C Gan; Elizabeth C Brown; Jane E Butler; Danny J Eckert; Joachim Ngiam; Kate Sutherland; Peter A Cistulli; Lynne E Bilston Journal: Sleep Date: 2021-03-12 Impact factor: 5.849
Authors: Hui Chen; Danny J Eckert; Paul F van der Stelt; Jing Guo; Shaohua Ge; Elham Emami; Fernanda R Almeida; Nelly T Huynh Journal: Sleep Med Rev Date: 2019-11-06 Impact factor: 11.609
Authors: Danny J Eckert; David P White; Amy S Jordan; Atul Malhotra; Andrew Wellman Journal: Am J Respir Crit Care Med Date: 2013-10-15 Impact factor: 21.405
Authors: Sara Op de Beeck; Andrew Wellman; Marijke Dieltjens; Kingman P Strohl; Marc Willemen; Paul H Van de Heyning; Johan A Verbraecken; Olivier M Vanderveken; Scott A Sands Journal: Am J Respir Crit Care Med Date: 2021-03-15 Impact factor: 21.405