The Discovery, Validation, and Function of Hypoxia-Related Gene Biomarkers for Obstructive Sleep Apnea

Wu, Xiaofeng; Pan, Zhou; Liu, Wei; Zha, Shiqian; Song, Yan; Hu, Ke

doi:10.3389/fmed.2022.813459

Cited by 5 publications

(3 citation statements)

References 57 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study suggests that when dealing with large datasets requiring rapid real-time screening, regularized LR is a preferable choice due to its relatively fast and accurate classification results. Contrastingly, Wu et al ( 2022 ) utilized hypoxia-related genes and biomarkers to construct an RF model for OSA diagnosis, yielding a lower AUC of 0.667. Notably, their OSA samples exclusively comprised obese cases, a crucial factor in differentiating OSA.…”

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

“…As a subunit of HIF1, HIF1A is involved in regulating the homeostatic response of cells and systems related to oxygen [ 40 ]. Like HIF1A, DUSP1 is also a hypoxia-related gene [ 41 ], which can be induced by hypoxia, nutrient deprivation, oxidative stress, and other reactions [ 42 ]. Jun [ 43 ] and CAV1 can regulate cell proliferation, apoptosis, and differentiation and inhibit tumor angiogenesis [ 44 ].…”

Section: Discussionmentioning

confidence: 99%

In Silico Analysis of Ferroptosis-Related Genes and Its Implication in Drug Prediction against Fluorosis

Liu

et al. 2023

IJMS

View full text Add to dashboard Cite

Fluorosis is a serious global public health problem. Interestingly, so far, there is no specific drug treatment for the treatment of fluorosis. In this paper, the potential mechanisms of 35 ferroptosis-related genes in U87 glial cells exposed to fluoride were explored by bioinformatics methods. Significantly, these genes are involved in oxidative stress, ferroptosis, and decanoate CoA ligase activity. Ten pivotal genes were found by the Maximal Clique Centrality (MCC) algorithm. Furthermore, according to the Connectivity Map (CMap) and the Comparative Toxicogenomics Database (CTD), 10 possible drugs for fluorosis were predicted and screened, and a drug target ferroptosis-related gene network was constructed. Molecular docking was used to study the interaction between small molecule compounds and target proteins. Molecular dynamics (MD) simulation results show that the structure of the Celestrol–HMOX1 composite is stable and the docking effect is the best. In general, Celastrol and LDN-193189 may target ferroptosis-related genes to alleviate the symptoms of fluorosis, which may be effective candidate drugs for the treatment of fluorosis.

show abstract

“…Obstructive sleep apnea-hypopnea syndrome (OSAHS) is characterized by recurrent episodes of complete (apnea) or partial (hypopnea) blockage of the upper airway while sleeping, which results in a repetitive pattern of alternative hypoxia and reoxygenation [1]. The prevalence of OSA is increasing as the global obesity epidemic worsens, and OSA currently affects 9% of women and 24% of men [2]. In the United States, around 26% of individuals aged 30-70 years are estimated to have OSAHS [3], although this data may be underestimated.…”

Section: Introductionmentioning

confidence: 99%

Association between mean platelet volume and obstructive sleep apnea-hypopnea syndrome: A systemic review and meta-analysis

Zeng,

He,

Chen

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Background Despite polysomnography (PSG) being acknowledged being considered the gold standard for diagnosing obstructive sleep apnea-hypopnea syndrome (OSAHS), researchers have been seeking a biomarker that is less invasive, more practical in detection, and cost-effective for diagnosing and assessing the severity of the disease. To address this concern, the values of mean platelet volume (MPV) between patients with OSAHS and healthy controls were compared, and the relationship between MPV and multiple sleep monitoring parameters was analyzed in this study. Methods A comprehensive search was conducted across medical databases, including PubMed, Web of Science, EMBASE, CNKI, and Wanfang, up until August 2, 2023, to identify published articles related to OSAHS. This study reviewed the literature regarding the values of MPV in individuals with OSAHS and control groups, the Pearson/Spearman correlation coefficients between MPV and sleep monitoring parameters, and the odds ratios (OR) of MPV concerning the occurrence of cardiovascular diseases (CVDs) in patients with OSAHS. Meta-analyses were performed using standardized mean difference (SMD), Fisher’s z values correlation coefficients (ZCOR) and odds ratio (OR) as effect variables. A fixed-effect model was used if the heterogeneity was not significant (I2<50%); otherwise, a random-effect model was applied. We will also combine the treatment effect estimates of individual trials using fixed‐effect and random‐effects models. Statistical analysis was carried out by employing STATA 11.0 and R 4.1.3. Results In total, 31 articles were selected for the final analysis. The study involved 3604 patients and 1165 control individuals. The MPV in the OSAHS group was considerably elevated in comparison to the healthy controls (SMD = 0.37, 95%CI = 0.21–0.53, P < 0.001), particularly among individuals with severe OSAHS (SMD = 0.57, 95%CI = 0.23–0.90, P = 0.001). Subgroup analysis based on ethnicity, mean body mass index (BMI), and study design type also revealed a considerably higher MPV in the OSAHS category in comparison to the healthy controls. Furthermore, MPV showed correlations with various sleep monitoring parameters. The elevation of MPV may be one of the risk factors for CVDs in individuals with OSAHS (adjusted OR = 1.72, 95%CI = 1.08–2.73, P = 0.022). Conclusion MPV is a relatively simple, cost-effective, and practical indicator of the severity of OSAHS, with its values being linked to the risk of CVDs in individuals with OSAHS.

show abstract

The Discovery, Validation, and Function of Hypoxia-Related Gene Biomarkers for Obstructive Sleep Apnea

Cited by 5 publications

References 57 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

In Silico Analysis of Ferroptosis-Related Genes and Its Implication in Drug Prediction against Fluorosis

Association between mean platelet volume and obstructive sleep apnea-hypopnea syndrome: A systemic review and meta-analysis

Contact Info

Product

Resources

About