Yu, Tsung-Yen

Abstract Introduction Adherence to continuous positive airway pressure (CPAP) therapy is difficult for many patients with obstructive sleep apnea. Clinical outcomes are improved with CPAP adherence ≥6 hr/night, yet scalable approaches to personalized support are limited. We developed a theory-based, clinic experience–driven conceptual dynamical model for optimizing CPAP use and applied it to a ‘just-in-time’ adaptive version of SleepWell24, a smartphone application integrating near–real-time wearable data, CPAP use, and patient-reported symptoms and CPAP-related problems with evidence-based behavior change interventions. In this feasibility optimization trial, we examined patient acceptability and initial outcomes of the adaptive SleepWell24 platform, and guided by the conceptual model, evaluated a control systems engineering approach to demonstrate, in simulation, improved CPAP adherence. Methods Aim 1: Naïve CPAP users (N=10; M age=61.7, 60% female) participated in this 60-day ongoing trial. Patients were encouraged to interact daily with SleepWell24 to report symptoms, receive personalized troubleshooting recommendations, set goals, and receive feedback on CPAP use (via Wi-Fi-enabled smart plug assessing CPAP ‘on/off state’) and sleep/activity (Fitbit). We assessed SleepWell24 use, post-intervention acceptability, and consistent CPAP use defined as ≥6hr, for ≥6nights/week for ≥2 consecutive weeks. Aim 2: The conceptual model of CPAP adherence produced a dynamical system, informed by Model Predictive Control (MPC) as a decision-making algorithm to optimize CPAP use to ≥6hr/night by tailoring actionable behavioral recommendations using patient data integrated in real-time. Results Aim 1: Across the 60-day trial, average daily SleepWell24 engagement was 72.7%. Median CPAP adherence of ≥6hr/night was 65.8%. All participants (100%) rated SleepWell24 as moderately-to-totally acceptable and would recommend it; perceived helpfulness averaged 7.0 (of 10). Eighty percent achieved consistent CPAP use. Aim 2: In simulation, the MPC framework managed CPAP-associated symptoms (e.g., nasal, anxiety, leak) and adjusted CPAP use goals, improving predicted CPAP adherence and sleep duration and quality. Conclusion SleepWell24 was engaging, acceptable, and helpful, with most users reaching optimal CPAP use. We will next estimate dynamical models using data from trial patients, a necessary step towards full automation of SleepWell24. Support (if any) AASMF #285-SR-22

Abstract Introduction We aimed to test the feasibility and acceptability of SleepWell24, a multicomponent, smartphone-delivered intervention to increase positive airway pressure (PAP) adherence among newly diagnosed OSA patients. Methods SleepWell24 targets PAP adherence along with other health behaviors through education, trouble-shooting, goal-setting, and near real-time biofeedback of PAP machine use, and sleep and physical activity levels (via Fitbit integration), and other chronic disease self-management components. Patients with a first-time diagnosis of OSA (AHI≥5) and prescribed PAP therapy were enrolled from the Centers for Sleep Medicine at Mayo Clinic in Rochester, MN and Phoenix, AZ. Patients were randomized to SleepWell24 or usual care (UC) and assessed for PAP use over 60 consecutive nights. UC patients received a Fitbit monitor to control for non-specific intervention effects related to the introduction of a new personal technology. Feasibility was assessed with recruitment and retention rates and acceptability was assessed post-intervention with the validated, 8-item Treatment Evaluation Questionnaire (TEQ; range:0-4). ANCOVA models, adjusting for age, sex, and AHI severity, compared intervention arms on acceptability ratings. Results OSA patients were consented and randomized (N=111). Before the intervention began 4 participants withdrew, 12 were lost to follow-up, and 5 could not start the trial due to durable medical equipment (DME) vendor barriers. Ninety OSA patients (n=41 SleepWell24, n=49 UC; age M±SD=57.2±12.2; 44.4% female, 61.1% AHI≥15) started the intervention, with 2 participants withdrawing, 1 becoming deceased (unrelated to treatment) and 7 with missing PAP data due to DME vendor barriers. There was no significant between-groups differences on post-treatment acceptability (SleepWell24 M±SD=2.7±1.1 vs. UC M±SD=3.1±0.9, F[1,73]=2.3, p=0.11), and 77% of SleepWell24 participants found the app to be moderately to totally acceptable. Conclusion Overall, SleepWell24 was found to be feasible for delivery in two large clinical sleep medicine centers, and patients found the app to be acceptable. A number of challenges in trial delivery were encountered that have implications for scaled-up efficacy testing: (a) partnerships with DME vendors for near real-time PAP data integration; (b) alignment with clinical practice (i.e., referral, medical record integration); and (c) patient engagement. Support National Institute of Nursing Research / National Institutes of Health: R21NR016046