JMIR Publications

ABSTRACT

Background:

High-quality sleep is essential for both physical and mental well-being. Insufficient or poor sleep is linked to numerous health issues, including cardiometabolic diseases, mental health disorders, and increased mortality. Snoring, a prevalent condition, can disrupt sleep and is associated with disease states including coronary artery disease and obstructive sleep apnea.

Objective:

The SleepWatch smartphone application (Bodymatter, Inc., Newport Beach, CA USA) aims to monitor and improve sleep quality and has snore detection capabilities built through a machine-learning process trained on over 60,000 acoustic events. This study evaluates the accuracy of the SleepWatch snore detection algorithm in a simulated real-world setting.

Methods:

The snore detection algorithm was tested using 36 simulated snoring audio files derived from 18 subjects. Each file simulated a Snoring Index (SI) between 30 and 600 snores/hour. Additionally, 9 files with non-snoring sounds were tested to evaluate the algorithm's capacity to avoid false positives. Sensitivity, specificity, and accuracy were calculated for each test, and results were compared using Bland-Altman plots and Spearman correlation to assess the correlation between detected and actual snores.

Results:

The SleepWatch algorithm showed an average sensitivity of 86.3%, specificity of 99.5%, and accuracy of 95.2% across the snoring tests. The algorithm performed exceptionally well in avoiding false positives, with a specificity of 97.1% for non-snoring files. Inclusive of all snoring and non-snore tests, the aggregated accuracy for all trials in this bench study was 95.6%. Bland-Altman analysis indicated a mean bias of -29.8 snores/hour, and Spearman correlation analysis revealed a strong positive correlation (rs=0.974, P<0.0001) between detected and actual snore rates.

Conclusions:

The SleepWatch snore detection algorithm demonstrates high accuracy and compares favorably with other snore detection applications, showing potential for broader use in sleep monitoring and as a tool for identifying individuals at risk for sleep disorders such as obstructive sleep apnea.