Rationale: Excessive daytime sleepiness, an important symptom of obstructive sleep apnea (OSA), is commonly quantified using the Epworth Sleepiness Scale score (ESS). Baseline OSA severity measures (ventilatory burden, flow limitation, and hypoxemia) provide insights into OSA pathophysiology and could predict changes in sleepiness (i.e. change-in-ESS) following continuous positive airway pressure (CPAP) treatment. Objectives: We hypothesized that change-in-ESS following CPAP treatment can be predicted from baseline polysomnography. Methods: Associations between OSA severity measures and ESS were evaluated in 2332 participants, adjusting for age, sex, BMI, and total sleep time. Change-in-ESS prediction was evaluated using 213 CPAP treatment studies (HomePAP, BestAIR, and ABC) in three steps: severity measures were compared (adjusted regression, n=64), a prediction model was developed using baseline ventilatory burden and baseline ESS (n=139), and then evaluated in holdout participants (n=74). Measurements and Main Results: In cross-sectional analysis, ESS was associated with ventilatory burden (0.45 points/SD; 95% CI 0.23-0.67), hypoxic burden (0.39; 0.17-0.62), the apnea-hypopnea index (AHI) (0.36; 0.14-0.59), and flow limitation severity (0.22; 0.01-0.43). Comparison analysis revealed that change-in-ESS was most strongly associated with baseline ventilatory burden (-1.08 points/SD; -2.13 to -0.05) and baseline ESS (-2.75; -3.83 to -1.69); the AHI association was weaker (-0.97; -2.01-0.05). Predicted change-in-ESS and actual change-in-ESS were correlated in holdout participants (adjusted R^2=0.313); median [IQR] actual change-in-ESS of predicted responders (>=2-point ESS improvement, n=54, 73.0%) was -5.0 [-10.0 to -2.0] and non-responders was 0.0 [-1.0-1.0] (P<0.001). Conclusions: Baseline ventilatory burden and baseline ESS were independently associated with change-in-ESS and could be used together to inform clinicians whether CPAP treatment will likely improve a patient's sleepiness.

ES was supported by the National Health and Medical Research Council (NHMRC) of Australia (grant 2001729). TL was supported by The State Research Funding for university-level health research, Kuopio University Hospital, Wellbeing Service County of North Savo (project 5041794). JT was supported by the NHMRC (grants 2001729 and 2007001), NordForsk (NordSleep project 90458) via Business Finland (5133/31/2018), and Sigrid Juselius Foundation (decision number 230216), and has received royalties related to Bittium BrainStatus EEG electrode (unrelated to the submitted work). SAS has received funding from the American Academy of Sleep Medicine Foundation (228-SR-20) and the National Institute of Health NHLBI (grants R01HL146697 and R01HL168067). SAS has received grant support from Apnimed, Prosomnus, and Dynaflex for unrelated studies, and has received personal fees as a consultant for LinguaFlex, Nox Medical, Merck, Apnimed, Inspire Medical Systems, Eli Lilly, Respicardia, and Forepont (unrelated to the submitted work). SAS has patents on sleep apnea pharmacotherapy and phenotyping from wearable technology and his industry interactions are managed by Brigham and Women's Hospital and Mass General Brigham in accordance with their conflict of interest policies. SK has received research funding from The State Research Funding for university-level health research, Kuopio University Hospital, Wellbeing Service County of North Savo (project 5041804), the Finnish Cultural Foundation (Central Fund), and the Research Council of Finland (project 360119). PIT was supported by The University of Queensland, Queensland Health Metro North, and NHMRC (grants 2001729 and 2007001). PIT has received honoraria from the University of Adelaide, University of Sydney, and Flinders University (unrelated to the submitted work). DLM was supported by the NHMRC (grants 2001729 and 2007001). AA has received research funding from the American Academy of Sleep Medicine, American Heart Association, and National Institute of Health. AA has received a grant from Somnifix; consulting fees from Respicardia, Apnimed, LinguaFlex, Eli Lilly, and Inspire; honoraria from University of Alberta for a grant review; honoraria from the American Academy of Orofacial Pain for a lecture; equipment loaned from Philips Respironics; and has a patent pending for phenotyping sleep apnea using wearables (all unrelated to the submitted work).

ES was supported by the National Health and Medical Research Council (NHMRC) of Australia (grant 2001729). TL was supported by The State Research Funding for university-level health research, Kuopio University Hospital, Wellbeing Service County of North Savo (project 5041794). JT was supported by the NHMRC (grants 2001729 and 2007001), NordForsk (NordSleep project 90458) via Business Finland (5133/31/2018), and Sigrid Juselius Foundation (decision number 230216), and has received royalties related to Bittium BrainStatus EEG electrode (unrelated to the submitted work). SAS has received funding from the American Academy of Sleep Medicine Foundation (228-SR-20) and the National Institute of Health NHLBI (grants R01HL146697 and R01HL168067). SAS has received grant support from Apnimed, Prosomnus, and Dynaflex for unrelated studies, and has received personal fees as a consultant for LinguaFlex, Nox Medical, Merck, Apnimed, Inspire Medical Systems, Eli Lilly, Respicardia, and Forepont (unrelated to the submitted work). SAS has patents on sleep apnea pharmacotherapy and phenotyping from wearable technology and his industry interactions are managed by Brigham and Women's Hospital and Mass General Brigham in accordance with their conflict of interest policies. SK has received research funding from The State Research Funding for university-level health research, Kuopio University Hospital, Wellbeing Service County of North Savo (project 5041804), the Finnish Cultural Foundation (Central Fund), and the Research Council of Finland (project 360119). PIT was supported by The University of Queensland, Queensland Health Metro North, and NHMRC (grants 2001729 and 2007001). PIT has received honoraria from the University of Adelaide, University of Sydney, and Flinders University (unrelated to the submitted work). DLM was supported by the NHMRC (grants 2001729 and 2007001). AA has received research funding from the American Academy of Sleep Medicine, American Heart Association, and National Institute of Health. AA has received a grant from Somnifix; consulting fees from Respicardia, Apnimed, LinguaFlex, Eli Lilly, and Inspire; honoraria from University of Alberta for a grant review; honoraria from the American Academy of Orofacial Pain for a lecture; equipment loaned from Philips Respironics; and has a patent pending for phenotyping sleep apnea using wearables (all unrelated to the submitted work).

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Analyses were approved by The University of Queensland Research Ethics and Integrity unit (2023/HE000064, 2023/HE001953, and 2021/HE002256).

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

This study used data from five published studies that are publicly available from the National Sleep Research Resource website: Apnea, Bariatric surgery, and CPAP study (ABC): https://sleepdata.org/datasets/abc Best Apnea Interventions in Research (BestAIR): https://sleepdata.org/datasets/bestair Home Positive Airway Pressure (HomePAP): https://sleepdata.org/datasets/homepap Stanford Technology Analytics and Genomics in Sleep (STAGES): https://sleepdata.org/datasets/stages Multi-Ethnic Study of Atherosclerosis (MESA): https://sleepdata.org/datasets/mesa Requests for code and processed data should be directed to the corresponding author.