Goswami, Umesh

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 Hypoglossal nerve stimulators (HGNS) are used in patients with moderate-to-severe obstructive sleep apnea (OSA) who are unable to tolerate or do not respond to continuous positive airway pressure (CPAP) therapy. However, a subgroup of patients fail to achieve resolution of OSA with HGNS alone. Previous studies have shown that lower BMI, lower nadir oxygenation, decreased sleep latency, and higher VOTE score on drug-induced sleep endoscopy (DISE) predict better treatment outcome. We hypothesize that baseline diagnostic polysomnography (PSG) may further predict which patients will achieve successful therapeutic outcome with HGNS therapy. Methods We conducted a retrospective analysis of all adult patients who underwent HGNS implantation at Mayo Clinic Arizona between 2019-2025 and had a pre-implantation diagnostic PSG available for review. Treatment success was defined by Sher Criteria: >50% reduction in post-treatment apnea hypopnea index (AHI) to a final AHI of < 20/hr. Responders met Sher criteria and non-responders did not meet Sher criteria. Demographics, sleep questionnaire results, PSG variables, and VOTE score on DISE were collected and analyzed using Spearman’s rank correlation of reduction in AHI. Results Twenty-three patients (11M/12F, median age: 69[IQR:64,75] years) met inclusion criteria. Median baseline AHI was 24[IQR:19,37]/hr. Median post-implant AHI was 8 [IQR:3, 14]/hr. Responders (n=15, 65%) and non-responders (n=8, 35%) demonstrated median post-implant AHI of 4.5[IQR:2.3,7.3]/hr and 15.7[IQR:12.3,28.5]/hr, respectively. Treatment response was associated with less time with SpO2 < 88% (T88%) (21min [IQR:3,64] vs. 73[IQR:36,105mins]; p=0.023) and higher central apnea index (CAI) (1[IQR:0.1,3] vs. 0[IQR:0,1], p=0.03) on pre-implantation PSG. Conclusion In this small cohort of OSA patients, less nocturnal hypoxemia as defined by T88% and higher baseline central apnea index were predictors of better treatment response to HGNS therapy as measured by Sher criteria. We hypothesize that greater nocturnal hypoxemia likely reflects more severe airway obstruction during sleep. Our analysis also showed that responders had higher baseline CAI than non-responders, however we believe this association is not clinically significant and likely driven by one outlier (CAI 13/hr). Further analysis in a larger HGNS cohort is needed to confirm these findings. Data enrichment efforts and more sophisticated analyses are underway. Support (if any)