Size Matters: A Large-Scale, Real-World Dataset of Smartphone-Based Obstructive Sleep Apnea Screening in the General...

Background: Obstructive sleep apnea (OSA) is a highly prevalent sleep-related breathing disorder that remains substantially underdiagnosed and is causally linked to cardiovascular and metabolic morbidity. Clinical diagnosis relies on the apnea-hypopnea index (AHI) derived from polysomnography (PSG) or home sleep apnea testing. Low-threshold, clinically validated screening tools that can be used repeatedly outside a clinical setting may help to reduce underdiagnosis and to capture longitudinal information. Methods: We describe a real-world dataset generated by a medical device-grade, smartphone-only OSA screening application (Snorefox M) that calculates the AHI from nocturnal breathing sounds. All users who provided informed consent for the research use of their anonymized data between March 2023 and December 2025 were included. The diagnostic performance of the application had previously been validated against parallel PSG. Additional post hoc analysis of classification performance at additional AHI thresholds, together with the linear correlation between the app-derived and PSG-derived AHI are described. Results: The dataset comprises 239,132 measurements from 31,647 consenting adults. A total of 14,351 users contributed at least two valid nights, yielding 221,820 nights of longitudinal screening data. Across all attempted measurements, 96.5% yielded a valid analysis result. The mean per-measurement AHI was 14.3 (median 11.8, SD 11.0). Voluntary, self-reported demographic information was available for a subgroup of 8092 users (mean age 54.4 years, mean ESS score 7.2). Against PSG, the application detected moderate-to-severe OSA (AHI ≥ 15) with a sensitivity of 0.91 and a specificity of 0.83, and severe OSA (AHI ≥ 30) with a sensitivity of 0.93 and a specificity of 0.97. The app-derived AHI correlated strongly with the PSG-derived AHI (Pearson r = 0.80, p < 0.001). The app-derived AHI discriminated against the PSG reference with an area under the curve (AUC) of 0.951 for severe OSA (AHI ≥ 30), 0.925 for moderate-to-severe OSA (AHI ≥ 15) and 0.877 for the AHI ≥ 10 threshold. Conclusions: This is, to our knowledge, the largest longitudinal dataset of unsupervised, real-world OSA screening from a general adult population using a clinically validated, low-threshold smartphone tool. Smartphone-based screening can complement established diagnostic pathways, support pre-clinical triage and generate longitudinal data not accessible through single-night testing, while self-selection and the unsupervised nature of data capture constrain representativeness. By introducing this resource, this work provides the basis for the in-depth analyses of demographics, symptom-result concordance and night-to-night variability.