A Recall-First CNN for Sleep Apnea Screening from Snoring Audio

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mallick, Anushka, Noorain, Afiya, Menon, Ashwin, Solanki, Ashita, Balaji, Keertan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912620371509248
author Mallick, Anushka
Noorain, Afiya
Menon, Ashwin
Solanki, Ashita
Balaji, Keertan
author_facet Mallick, Anushka
Noorain, Afiya
Menon, Ashwin
Solanki, Ashita
Balaji, Keertan
contents Sleep apnea is a serious sleep-related breathing disorder that is common and can impact health if left untreated. Currently the traditional method for screening and diagnosis is overnight polysomnography. Polysomnography is expensive and takes a lot of time, and is not practical for screening large groups of people. In this paper, we explored a more accessible option, using respiratory audio recordings to spot signs of apnea.We utilized 18 audio files.The approach involved converting breathing sounds into spectrograms, balancing the dataset by oversampling apnea segments, and applying class weights to reduce bias toward the majority class. The model reached a recall of 90.55 for apnea detection. Intentionally, prioritizing catching apnea events over general accuracy. Despite low precision,the high recall suggests potential as a low-cost screening tool that could be used at home or in basic clinical setups, potentially helping identify at-risk individuals much earlier.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00052
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Recall-First CNN for Sleep Apnea Screening from Snoring Audio
Mallick, Anushka
Noorain, Afiya
Menon, Ashwin
Solanki, Ashita
Balaji, Keertan
Sound
Machine Learning
Audio and Speech Processing
Sleep apnea is a serious sleep-related breathing disorder that is common and can impact health if left untreated. Currently the traditional method for screening and diagnosis is overnight polysomnography. Polysomnography is expensive and takes a lot of time, and is not practical for screening large groups of people. In this paper, we explored a more accessible option, using respiratory audio recordings to spot signs of apnea.We utilized 18 audio files.The approach involved converting breathing sounds into spectrograms, balancing the dataset by oversampling apnea segments, and applying class weights to reduce bias toward the majority class. The model reached a recall of 90.55 for apnea detection. Intentionally, prioritizing catching apnea events over general accuracy. Despite low precision,the high recall suggests potential as a low-cost screening tool that could be used at home or in basic clinical setups, potentially helping identify at-risk individuals much earlier.
title A Recall-First CNN for Sleep Apnea Screening from Snoring Audio
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2510.00052