Assessment of obstructive sleep apnea severity using audio-based snoring features

•Novel audio-based features that exploit snoring characteristics including the variability of snoring sounds and trend in snore energy were proposed.•An extreme gradient boosting model was trained for apnea-hypopnea index estimation with a medium real-world clinical OSA population.•Audio-based estim...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Biomedical signal processing and control Ročník 86; s. 104942
Hlavní autori: Xie, Jiali, Fonseca, Pedro, van Dijk, Johannes, Overeem, Sebastiaan, Long, Xi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.09.2023
Predmet:
AHI
Apnea-hypopnea index
Audio signal processing
Machine learning
OSA classification
Sleep apnea
Sleep disordered breathing
Snoring
Sound features
OSA classification
AHI
Audio signal processing
Sound features
Apnea-hypopnea index
Machine learning
Sleep apnea
Sleep disordered breathing
Snoring
ISSN:1746-8094, 1746-8108
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:•Novel audio-based features that exploit snoring characteristics including the variability of snoring sounds and trend in snore energy were proposed.•An extreme gradient boosting model was trained for apnea-hypopnea index estimation with a medium real-world clinical OSA population.•Audio-based estimates of the apnea-hypopnea index showed a significant correlation with the polysomnographic gold standard, outperforming the model with the baseline feature set from a previous study. Snoring is a prima symptom of obstructive sleep apnea (OSA). Here, we add audio-based snoring features to improve the non-obtrusive assessment of sleep apnea, by estimating the apnea-hypopnea index (AHI) and classifying OSA severity. We propose novel features to quantify temporal changes between snores (snore rate variability) and to describe trends in snore energy, based on the assessment of snore sounds from audio signals over the full night. We then combined those features with age, body mass index (BMI) and features described in literature. An extreme gradient boosting algorithm was trained with all these features on AHI estimation. The estimated AHI was then used to classify OSA severity. Audio-based estimated AHI showed a significant Spearman's correlation with the AHI based on gold-standard polysomnography (R = 0.786, P < 0.0001). Our results outperformed a model trained with solely previously described features in our dataset (R = 0.676, P < 0.0001) and a model trained with the combination of previously described features, age, and BMI (R = 0.731, P < 0.0001). The mean absolute error of AHI estimation was 7.26 events/h. Area under the receiver operating characteristic curve outcomes were 0.90, 0.87 and 0.93 for classifying patients with varying severity separated by the canonical thresholds of 5, 15 and 30 events/h respectively. The accuracy of classifying subjects to four classes (no, mild, moderate, and severe OSA) was 59.3 %. Additional audio-based snore features can improve the performance of non-obtrusive AHI estimation and OSA severity classification methods.
ISSN:1746-8094
1746-8108
DOI:10.1016/j.bspc.2023.104942