Predicting Obstructive Sleep Apnea with Periodic Snoring Sound Recorded at Home

Alakuijala, Anniina; Salmi, Tapani

doi:10.5664/jcsm.5922

Cited by 23 publications

(20 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frequent snoring was detected during feature selection as yet another pertinent feature for OSA prediction, and is part of the minimal feature set for the trained models. Although experts in [63] advise caution in the interpretation of snoring symptoms for assessing sleep apnea, they state it can be reliable when used in conjunction with additional clinical and physical readings, which is the case in our presented work. While the features of insomnia and daytime sleepiness (quantified by ESS) were included in feature selection, they only showed a marginal association with OSA, as opposed to the stipulations of [64,65], respectively.…”

Section: Discussionmentioning

confidence: 80%

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

et al. 2021

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA) is a common, chronic, sleep-related breathing disorder characterized by partial or complete airway obstruction in sleep. The gold standard diagnosis method is polysomnography, which estimates disease severity through the Apnea-Hypopnea Index (AHI). However, this is expensive and not widely accessible to the public. For effective screening, this work implements machine learning algorithms for classification of OSA. The model is trained with routinely acquired clinical data of 1479 records from the Wisconsin Sleep Cohort dataset. Extracted features from the electronic health records include patient demographics, laboratory blood reports, physical measurements, habitual sleep history, comorbidities, and general health questionnaire scores. For distinguishing between OSA and non-OSA patients, feature selection methods reveal the primary important predictors as waist-to-height ratio, waist circumference, neck circumference, body-mass index, lipid accumulation product, excessive daytime sleepiness, daily snoring frequency and snoring volume. Optimal hyperparameters were selected using a hybrid tuning method consisting of Bayesian Optimization and Genetic Algorithms through a five-fold cross-validation strategy. Support vector machines achieved the highest evaluation scores with accuracy: 68.06%, sensitivity: 88.76%, specificity: 40.74%, F1-score: 75.96%, PPV: 66.36% and NPV: 73.33%. We conclude that routine clinical data can be useful in prioritization of patient referral for further sleep studies.

show abstract

Section: Discussionmentioning

confidence: 80%

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[ 17 ] A recent study including 211 participants, aged 18 years and older, showed that there is a strong positive correlation ( r = 0.727, P < 0.001) between periodic snoring sounds measured during home sleep apnea testing and AHI. [ 18 ] Conversely, Hong et al ., while studying the relationship between OSAS severity and snoring time, did not find a linear correlation between the snoring rate and total AHI. However, while comparing the snoring rates between the groups (divided according to the severity of OSAS by AHI), they found that the snoring rates increased as the AHI increased from the control to the moderate OSAS group and decreased as the AHI increased from the moderate to the very severe OSAS group.…”

Section: Discussionmentioning

confidence: 99%

Snoring time versus snoring intensity: Which parameter correlates better with severity of obstructive sleep apnea syndrome?

et al. 2020

View full text Add to dashboard Cite

“…According to the results of a recent study consisting of 211 patients undergoing PSG testing, there was strong correlation between periodic snoring and presence of OSAS and the authors have concluded that prior to more expensive studies, measuring periodic snoring at home might be a simple and useful method for predicting the probability of OSA, particularly among women who are often unaware of their apnea-related snoring. 15 Furthermore Akhter et al 16 have shown that it was appropriate to predict mild/ severe OSAS with high sensitivity in REM/non-REM sleep based on snoring/breathing sounds obtained using simple bedside sound receivers.…”

Section: Discussionmentioning

confidence: 99%

The Perioperative Utilization of Sleep Monitoring Applications on Smart Phones in Habitual Snorers With Isolated Inferior Turbinate Hypertrophy

Kazıkdaş

2019

Ear Nose Throat J

View full text Add to dashboard Cite

The aim of this study is to investigate the novel use of sleep monitoring applications in simple snorers undergoing concha radiofrequency surgery and to compare and correlate the pre-and postoperative symptoms of these patients using the Nasal Obstruction Symptom Evaluation (NOSE) scale. In this retrospective analysis, we have selected 18 consecutive patients with no comorbid sleep or medical disorders suffering from chronic nasal blockage and habitual snoring due to isolated submucous inferior turbinate hyperplasia. After a median follow-up of 8.3 months, the NOSE scale and snoring sound intensity levels monitored by the smart phone application showed statistically significant improvements after the surgical procedure (P < .05), and we also detected a positive correlation between the levels of snoring percentage and the total NOSE scores (P < .05). We hypothesize that sleep monitoring applications could be easily used as portable monitors for basic home sleep studies in conjunction with a comprehensive sleep evaluation. Alternatively, such applications may simply be used for objective monitoring of the postoperative success of surgical interventions in the upper respiratory tract region such as concha reduction surgeries as presented herein.

show abstract

Predicting Obstructive Sleep Apnea with Periodic Snoring Sound Recorded at Home

Cited by 23 publications

References 33 publications

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

Towards Validating the Effectiveness of Obstructive Sleep Apnea Classification from Electronic Health Records Using Machine Learning

Snoring time versus snoring intensity: Which parameter correlates better with severity of obstructive sleep apnea syndrome?

The Perioperative Utilization of Sleep Monitoring Applications on Smart Phones in Habitual Snorers With Isolated Inferior Turbinate Hypertrophy

Contact Info

Product

Resources

About