Khayat, Rami

Abstract Introduction Adherence with mask-based therapies remains a significant challenge for optimal treatment of patients with sleep disordered breathing. Transvenous phrenic nerve stimulation (TPNS) to treat central sleep apnea offers a novel, automated approach to enhance nightly adherence by initiating therapy based on patient-specific programmed conditions such as sleep schedule, activity, and body position. Therapy automatically pauses when the patient sits up or changes position, facilitating re-initiation of sleep. This research aimed to determine the degree of adherence achieved with TPNS’s automated activation approach. Methods Device data from 128 remedē® System Pivotal Trial participants were analyzed to calculate hours of therapy activation. Daily use from device data within the 14 days prior to scheduled visits were used to calculate median daily hours of therapy per patient, and subsequently the overall median daily use for all patients. Therapy duration was defined as the sum of time of delivered therapy when all conditions to activate therapy were met between the first time therapy came on to the last time off during the night, excluding time when activity or body position did not meet the programmed criteria for therapy activation. Results The median [Q1-Q3] nightly therapy duration at 6, 12, 18, and 24 months was 5.9 [4.9-6.6], 5.7 [5.0-6.8], 6.0 [5.3-6.8], and 5.9 [4.9-6.5] hours, respectively. Using a definition for adequate therapy as the percentage of patients with usage ≥4 hours/night for at least 70% of nights, 86%, 82%, 83%, and 90% of patients met the criteria at these visits. Only two patients (< 2%) who had therapy activated discontinued treatment prior to 6 months due to stimulation intolerance. Patients with median delivered therapy ≥4 hours/night reported more quality of life improvement than patients with < 4 hours of therapy. Conclusion The automatic activation of TPNS therapy resulted in a higher duration of nightly usage and higher rate of adequate delivered therapy than generally are reported for mask-based therapies. This high usage may yield a greater overall reduction in central sleep apnea burden over the whole night compared to therapies that require the patient to initiate the therapy. Support (if any) ZOLL Respicardia, Inc.

Abstract Introduction Identifying central sleep apnea (CSA) during home sleep apnea testing is important to guide appropriate treatment for sleep-disordered breathing (SDB) and underlying cardiovascular conditions, including heart failure and atrial fibrillation. SANSA (Huxley Medical, Inc.) is a multi-diagnostic chest-worn monitor capable of detecting SDB, cardiac arrhythmias, and heart function. Using polysomnography (PSG) as a reference, we developed a machine learning (ML) method to classify respiratory events from this monitor as central or obstructive. Methods Data was analyzed from ninety-five subjects with suspected SDB who wore the chest monitor simultaneously with PSG overnight. To address known scoring heterogeneity of CSA, PSG records were scored for central apneas by two core laboratories (Core 1 and Core 2). Core 1 annotations from twenty-eight records were first used to train a random forest classifier to differentiate obstructive (N=680) and central events (N=388). The model used oximetry, respiratory effort, and snoring to classify events based on effort, duration, and other features. A five-fold cross validation was used to evaluate event-level performance. The model was then used to estimate subject-level CAI for all subjects and compared with Core 2 scores. Results Algorithm event-level sensitivity and specificity to detect central events was 72.7% and 81.0%. Subject-level CAI for all records between the chest monitor and Core 2 had a correlation coefficient of 0.90 and root mean squared error (RMSE) of 4.6 events/hour, versus 0.82 and 4.7 events/hour comparing Core 1 and Core 2. Sensitivity and specificity to detect CAI≥10 events/hour was 80.0% (4/5) and 98.9% (89/90), compared to 100% (3/3) and 98.9% (91/92) for CAI≥15. Conclusion An ML algorithm to differentiate obstructive and central events collected from the chest-worn monitor demonstrated favorable event-level performance and comparable CAI agreement to that between two PSG core laboratories. Home-based CSA detection alongside cardiac monitoring could identify high risk patients for expedited therapy, cardiology referral, or follow-up PSG. These results motivate further validation in a larger cohort as well as investigation of outcomes related to time to evaluation and management. Support (if any) National Science Foundation; Georgia Research Alliance; Huxley Medical, Inc.