Collop, Nancy A.

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.

Objectives: With over 2 million cases of acute respiratory failure in the United States per year, noninvasive ventilation has become a leading treatment modality, often supplanting invasive mechanical ventilation as the initial treatment of choice. Most acute respiratory failure patients use a full face (oronasal) mask with noninvasive ventilation, which is known to impair communication, but its popularity and benefit has led many providers to accept the communication impairment. Medical staff periodically remove masks to communicate with patients, but patients are often limited to short utterances and risk lung derecruitment upon removal of positive pressure. These problems can lead to noninvasive ventilation failure, which is often linked to worse outcomes than first initiating invasive mechanical ventilation and can lead to increased hospitalization costs. Data Sources: We searched MEDLINE and Google Scholar for “speech,” “communication,” “impairment,” “failure,” “complications,” “NIPPV,” “NIV,” and “noninvasive ventilation.” Study Selection: We included articles with patients in acute respiratory failure. We excluded articles for patients using noninvasive ventilation therapy for obstructive sleep apnea. Data Synthesis: Communication impairment has been associated with increasing noninvasive ventilation anxiety (odds ratio, 1.25). Of patients using noninvasive ventilation, 48% require early discontinuation, 22% refuse noninvasive ventilation, and 9% are ultimately intubated. Improvements to communication have been shown to reduce fear and anxiety in invasive mechanical ventilation patients. Analogous communication problems exist with effective solutions in other fields, such as fighter pilot masks, that can be easily implemented to enhance noninvasive ventilation patient care, increase adherence to noninvasive ventilation treatment, and improve patient outcomes. Conclusions: Communication impairment is an underappreciated cause of noninvasive ventilation complications and failure and requires further characterization. Analogous solutions—such as throat microphones and mask-based microphones—that can be easily implemented show potential as cost-effective methods to reduce noninvasive ventilation failure.

Prediction models aim to use available data to predict a health state or outcome that has not yet been observed. Prediction is primarily relevant to clinical practice, but is also used in research, and administration. While prediction modeling involves estimating the relationship between patient factors and outcomes, it is distinct from casual inference. Prediction modeling thus requires unique considerations for development, validation, and updating. This document represents an effort from editors at 31 respiratory, sleep, and critical care medicine journals to consolidate contemporary best practices and recommendations related to prediction study design, conduct, and reporting. Herein, we address issues commonly encountered in submissions to our various journals. Key topics include considerations for selecting predictor variables, operationalizing variables, dealing with missing data, the importance of appropriate validation, model performance measures and their interpretation, and good reporting practices. Supplemental discussion covers emerging topics such as model fairness, competing risks, pitfalls of “modifiable risk factors”, measurement error, and risk for bias. This guidance is not meant to be overly prescriptive; we acknowledge that every study is different, and no set of rules will fit all cases. Additional best practices can be found in the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines, to which we refer readers for further details.