Screening for Obstructive Sleep Apnea Risk by Using Machine Learning Approaches and Anthropometric Features

Tsai, Cheng-Yu; Huang, Huei-Tyng; Cheng, Hsueh-Chien; Wang, Jieni; Duh, Ping-Jung; Hsu, Wen-Hua; Stettler, Marc; Kuan, Yi Chun; Lin, Yi; Hsu, Chia-Rung; Lee, Kang‐Yun; Kang, Jiunn Horng; Wu, Dean; Lee, Hsin Chien; Wu, Chia-Chang; Majumdar, Arnab; Liu, Wen‐Te

doi:10.3390/s22228630

Cited by 9 publications

(5 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This might explain the disparity between their RF model and the current study. Tsai et al ( 2022 ) employed waist circumference, neck circumference, BMI, and visceral fat level to establish risk models for predicting moderate to severe OSA using LR, k-nearest neighbor, Bayesian, RF, SVM, and XGBoost. The RF model, applied to the moderate-severe category, demonstrated an accuracy of 84.74% and an AUC of 90.41%, highlighting its robust performance.…”

Section: Discussionmentioning

confidence: 99%

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

Liu,

Geng,

Shen

et al. 2024

Front. Big Data

View full text Add to dashboard Cite

ObjectiveTo develop a robust machine learning prediction model for the automatic screening and diagnosis of obstructive sleep apnea (OSA) using five advanced algorithms, namely Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) to provide substantial support for early clinical diagnosis and intervention.MethodsWe conducted a retrospective analysis of clinical data from 439 patients who underwent polysomnography at the Affiliated Hospital of Xuzhou Medical University between October 2019 and October 2022. Predictor variables such as demographic information [age, sex, height, weight, body mass index (BMI)], medical history, and Epworth Sleepiness Scale (ESS) were used. Univariate analysis was used to identify variables with significant differences, and the dataset was then divided into training and validation sets in a 4:1 ratio. The training set was established to predict OSA severity grading. The validation set was used to assess model performance using the area under the curve (AUC). Additionally, a separate analysis was conducted, categorizing the normal population as one group and patients with moderate-to-severe OSA as another. The same univariate analysis was applied, and the dataset was divided into training and validation sets in a 4:1 ratio. The training set was used to build a prediction model for screening moderate-to-severe OSA, while the validation set was used to verify the model's performance.ResultsAmong the four groups, the LightGBM model outperformed others, with the top five feature importance rankings of ESS total score, BMI, sex, hypertension, and gastroesophageal reflux (GERD), where Age, ESS total score and BMI played the most significant roles. In the dichotomous model, RF is the best performer of the five models respectively. The top five ranked feature importance of the best-performing RF models were ESS total score, BMI, GERD, age and Dry mouth, with ESS total score and BMI being particularly pivotal.ConclusionMachine learning-based prediction models for OSA disease grading and screening prove instrumental in the early identification of patients with moderate-to-severe OSA, revealing pertinent risk factors and facilitating timely interventions to counter pathological changes induced by OSA. Notably, ESS total score and BMI emerge as the most critical features for predicting OSA, emphasizing their significance in clinical assessments. The dataset will be publicly available on my Github.

show abstract

Section: Discussionmentioning

confidence: 99%

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

Liu,

Geng,

Shen

et al. 2024

Front. Big Data

View full text Add to dashboard Cite

show abstract

“…Consistent with previous findings, we observed significant associations between the visceral fat level and trunk-to-limb fat ratio in the low-ArTH OSA group. A study reported that visceral fat was a predominant indicator in the evaluation of the AHI level and nocturnal hypoxemia severity [ 38 ]. Another study reported that excess visceral fat can cause severe hypoxemia during sleep and an increased risk of metabolic syndrome [ 39 ].…”

Section: Discussionmentioning

confidence: 99%

Association of Low Arousal Threshold Obstructive Sleep Apnea Manifestations with Body Fat and Water Distribution

Hsu

Yang

Tsai

et al. 2023

Life

Self Cite

View full text Add to dashboard Cite

Obstructive sleep apnea (OSA) with a low arousal threshold (low-ArTH) phenotype can cause minor respiratory events that exacerbate sleep fragmentation. Although anthropometric features may affect the risk of low-ArTH OSA, the associations and underlying mechanisms require further investigation. This study investigated the relationships of body fat and water distribution with polysomnography parameters by using data from a sleep center database. The derived data were classified as those for low-ArTH in accordance with criteria that considered oximetry and the frequency and type fraction of respiratory events and analyzed using mean comparison and regression approaches. The low-ArTH group members (n = 1850) were significantly older and had a higher visceral fat level, body fat percentage, trunk-to-limb fat ratio, and extracellular-to-intracellular (E–I) water ratio compared with the non-OSA group members (n = 368). Significant associations of body fat percentage (odds ratio [OR]: 1.58, 95% confident interval [CI]: 1.08 to 2.3, p < 0.05), trunk-to-limb fat ratio (OR: 1.22, 95% CI: 1.04 to 1.43, p < 0.05), and E–I water ratio (OR: 1.32, 95% CI: 1.08 to 1.62, p < 0.01) with the risk of low-ArTH OSA were noted after adjustments for sex, age, and body mass index. These observations suggest that increased truncal adiposity and extracellular water are associated with a higher risk of low-ArTH OSA.

show abstract

“…Specifically, on the basis of our literature review, six machine learning approaches, including random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbor (kNN), support vector machine (SVM), naive Bayes (NB), and logistic regression (LR), were recruited to establish screening models for two different OSA severity risk levels. 27 , 28 Figure 2 demonstrates the flowchart of developing the models. Initially, all of the collected data were integrated as a total dataset and subsequently independently separated into training and test datasets at an 80% to 20% ratio.…”

Section: Methodsmentioning

confidence: 99%

Screening the risk of obstructive sleep apnea by utilizing supervised learning techniques based on anthropometric features and snoring events

et al. 2023

Self Cite

View full text Add to dashboard Cite

Objectives Obstructive sleep apnea (OSA) is typically diagnosed by polysomnography (PSG). However, PSG is time-consuming and has some clinical limitations. This study thus aimed to establish machine learning models to screen for the risk of having moderate-to-severe and severe OSA based on easily acquired features. Methods We collected PSG data on 3529 patients from Taiwan and further derived the number of snoring events. Their baseline characteristics and anthropometric measures were obtained, and correlations among the collected variables were investigated. Next, six common supervised machine learning techniques were utilized, including random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbor (kNN), support vector machine (SVM), logistic regression (LR), and naïve Bayes (NB). First, data were independently separated into a training and validation dataset (80%) and a test dataset (20%). The approach with the highest accuracy in the training and validation phase was employed to classify the test dataset. Next, feature importance was investigated by calculating the Shapley value of every factor, which represented the impact on OSA risk screening. Results The RF produced the highest accuracy (of >70%) in the training and validation phase in screening for both OSA severities. Hence, we employed the RF to classify the test dataset, and results showed a 79.32% accuracy for moderate-to-severe OSA and 74.37% accuracy for severe OSA. Snoring events and the visceral fat level were the most and second most essential features of screening for OSA risk. Conclusions The established model can be considered for screening for the risk of having moderate-to-severe or severe OSA.

show abstract

Screening for Obstructive Sleep Apnea Risk by Using Machine Learning Approaches and Anthropometric Features

Cited by 9 publications

References 48 publications

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

Association of Low Arousal Threshold Obstructive Sleep Apnea Manifestations with Body Fat and Water Distribution

Screening the risk of obstructive sleep apnea by utilizing supervised learning techniques based on anthropometric features and snoring events

Contact Info

Product

Resources

About