1269 Continuous Home Monitoring of CPAP Therapy Using a Sound-Based AI Apnea Tracking Device

Abstract Introduction Continuous positive airway pressure (CPAP) is the standard treatment for obstructive sleep apnea (OSA). Still, real-world adherence is frequently insufficient, and CPAP device data capture only the treated portion of sleep. As a result, untreated OSA during mask removal is often missed. ApnoTrack is a Class II smartphone-based device that uses AI analysis of breathing sounds to detect apneas and hypopneas across the entire sleep period. This study examined whether ApnoTrack can accurately assess nightly apnea–hypopnea index (AHI) in CPAP users and identify untreated OSA across different levels of adherence. Methods A prospective observational study was conducted in 45 adults newly prescribed CPAP therapy (BMI 27.0, baseline AHI 36.9, age 44.5; all male). Of these, 26 participants completed simultaneous monitoring with their CPAP device and ApnoTrack, yielding 560 nights. To evaluate AHI discrepancies arising when CPAP is removed during sleep, nights were categorized according to how much CPAP usage time was shorter than sleep duration estimated by ApnoTrack (ApnoTrack time minus CPAP time): full-use (≤5 mins), intermediate-use (5-30 mins), and partial-use (>30 mins). For each category, AHI values measured by the two devices were compared. Results Of all recorded nights, 287, 128, and 145 nights were classified as full-use, intermediate-use, and partial-use, respectively. On full-use nights, ApnoTrack AHI closely matched CPAP-reported values, with a mean difference of 0.22 events/hour (2.76 ± 4.08 vs. 2.54 ± 2.01; p=0.24). On intermediate-use nights, the difference increased to 3.78 events/hour (7.66 ± 5.54 vs. 3.88 ± 3.40; p< 0.001). On partial-use nights, ApnoTrack reported a substantially higher whole-night AHI, with a mean difference of 10.26 events/hour (13.53 ± 6.62 vs. 3.27 ± 2.48; p< 0.001). Conclusion Across the three categories, ApnoTrack-measured AHI rose progressively (2.76 → 7.66 → 13.53), whereas CPAP-reported AHI remained relatively stable (2.54 → 3.88 → 3.27). These findings indicate that ApnoTrack accurately measures apnea severity on nights of full CPAP adherence and identifies untreated OSA on nights of partial CPAP use, providing clinically meaningful information that CPAP data alone cannot provide. Continuous sound-based monitoring with ApnoTrack enables more comprehensive assessment of CPAP treatment use and whole-night OSA burden. Support (if any)

Authors

Institutions

Publication Details

Journal
SLEEP
Published
2026-05-01
DOI
https://doi.org/10.1093/sleep/zsag091.1268
Primary Topic
Obstructive Sleep Apnea Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

1269 Continuous Home Monitoring of CPAP Therapy Using a Sound-Based AI Apnea Tracking Device

Hyun Jik Kim, Jeong‐Whun Kim, Yoo‐Sam Chung, Joonki Hong et al.
SLEEP
Obstructive Sleep Apnea Research
article

1269 Continuous Home Monitoring of CPAP Therapy Using a Sound-Based AI Apnea Tracking Device

Hyun Jik Kim, Jeong‐Whun Kim, Yoo‐Sam Chung, Joonki Hong, Sujin Lee, Dongheon Lee, Sungjin Heo, Sungeun Moon
article en

Abstract

Abstract Introduction Continuous positive airway pressure (CPAP) is the standard treatment for obstructive sleep apnea (OSA). Still, real-world adherence is frequently insufficient, and CPAP device data capture only the treated portion of sleep. As a result, untreated OSA during mask removal is often missed. ApnoTrack is a Class II smartphone-based device that uses AI analysis of breathing sounds to detect apneas and hypopneas across the entire sleep period. This study examined whether ApnoTrack can accurately assess nightly apnea–hypopnea index (AHI) in CPAP users and identify untreated OSA across different levels of adherence. Methods A prospective observational study was conducted in 45 adults newly prescribed CPAP therapy (BMI 27.0, baseline AHI 36.9, age 44.5; all male). Of these, 26 participants completed simultaneous monitoring with their CPAP device and ApnoTrack, yielding 560 nights. To evaluate AHI discrepancies arising when CPAP is removed during sleep, nights were categorized according to how much CPAP usage time was shorter than sleep duration estimated by ApnoTrack (ApnoTrack time minus CPAP time): full-use (≤5 mins), intermediate-use (5-30 mins), and partial-use (>30 mins). For each category, AHI values measured by the two devices were compared. Results Of all recorded nights, 287, 128, and 145 nights were classified as full-use, intermediate-use, and partial-use, respectively. On full-use nights, ApnoTrack AHI closely matched CPAP-reported values, with a mean difference of 0.22 events/hour (2.76 ± 4.08 vs. 2.54 ± 2.01; p=0.24). On intermediate-use nights, the difference increased to 3.78 events/hour (7.66 ± 5.54 vs. 3.88 ± 3.40; p< 0.001). On partial-use nights, ApnoTrack reported a substantially higher whole-night AHI, with a mean difference of 10.26 events/hour (13.53 ± 6.62 vs. 3.27 ± 2.48; p< 0.001). Conclusion Across the three categories, ApnoTrack-measured AHI rose progressively (2.76 → 7.66 → 13.53), whereas CPAP-reported AHI remained relatively stable (2.54 → 3.88 → 3.27). These findings indicate that ApnoTrack accurately measures apnea severity on nights of full CPAP adherence and identifies untreated OSA on nights of partial CPAP use, providing clinically meaningful information that CPAP data alone cannot provide. Continuous sound-based monitoring with ApnoTrack enables more comprehensive assessment of CPAP treatment use and whole-night OSA burden. Support (if any)

SLEEPVol. 49(Supplement_1)
Seoul National University (KR), Asan Medical Center (KR), New Generation University College (ET), Seoul National University Bundang Hospital (KR)
Openalex Percentile: Top 6%
Obstructive Sleep Apnea Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.