Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach

A Machine Learning Prediction Model of Adult Obstructive Sleep Apnea Based on Systematically Evaluated Common Clinical Biochemical Indicators

Objective

Obstructive sleep apnea (OSA) is a common and potentially fatal sleep disorder. The purpose of this study was to construct an objective and easy-to-promote model based on common clinical biochemical indicators and demographic data for OSA screening.

Methods

The study collected the clinical data of patients who were referred to the Sleep Medicine Center of the Second Affiliated Hospital of Fujian Medical University from December 1, 2020, to July 31, 2023, including data for demographics, polysomnography (PSG), and 30 biochemical indicators. Univariate and multivariate analyses were performed to compare the differences between groups, and the Boruta method was used to analyze the importance of the predictors. We selected and compared 10 predictors using 4 machine learning algorithms which were "Gaussian Naive Bayes (GNB)", "Support Vector Machine (SVM)", "K Neighbors Classifier (KNN)", and "Logistic Regression (LR)". Finally, the optimal algorithm was selected to construct the final prediction model.

Results

Among all the predictors of OSA, body mass index (BMI) showed the best predictive efficacy with an area under the receiver operating characteristic curve (AUC) = 0.699; among the predictors of biochemical indicators, triglyceride-glucose (TyG) index represented the best predictive performance (AUC = 0.656). The LR algorithm outperformed the 4 established machine learning (ML) algorithms, with an AUC (F1 score) of 0.794 (0.841), 0.777 (0.827), and 0.732 (0.788) in the training, validation, and testing cohorts, respectively.

Conclusion

We have constructed an efficient OSA screening tool. The introduction of biochemical indicators in ML-based prediction models can provide a reference for clinicians in determining whether patients with suspected OSA need PSG.

The Association Between Erectile Dysfunction and Sleep Parameters: Data from a Prospective, Controlled Cohort

BACKGROUND

Many studies have reported a possible strong relationship between poor sleep quality, sleep disruption, sleep disorders, and erectile dysfunction (ED).

AIM

This study aimed to investigate the relationship between sleep quality and ED.

METHODS

Patients diagnosed with ED by the International Index of Erectile Function-5 (IIEF-5) questionnaire and 72 healthy adult men were included. Participants completed the questionnaire, underwent a detailed physical examination, and provided blood samples. All enrolled subjects then wore the Fitbit Charge 2 that monitored sleep throughout the night.

OUTCOMES

Primary outcome measures included scores on the IIEF-5, General Anxiety Disorder-7 (GAD-7) scale, Patient Health Questionnaire-9 (PHQ-9), Pittsburgh Sleep Quality Index (PSQI), and sleep monitoring parameters obtained from Fitbit Charge 2.

RESULTS

Finally, a total of 107 ED patients and 72 healthy adult men were enrolled in this study. Univariate analysis indicated that the GAD-7 (P < .001), PHQ-9 (P < .001), and PSQI scores (P < .001) significantly differed according to the presence/absence of ED. Further multiple logistic regression analysis showed that the PHQ-9 (odds ratio [OR]: 1.227, 95% confidence interval [CI]: 1.070-1.407; P = .003) and PSQI scores (OR: 1.220, 95%CI: 1.116-1.334; P < .001) were independent risk factors for ED. Analysis of objective sleep monitoring parameters showed that total sleep time (TST) (P = .001), sleep onset latency (SOL) (P = .026), deep sleep (N3) duration (P = .011) and rapid eye movement (REM) sleep duration (P < .001) were significantly differed between the 2 groups, with durations in the ED group significantly lower than those in the non-ED group. In addition, receiver operating characteristic (ROC) curve analysis indicated that the REM sleep duration had the highest area under the curve (AUC: 0.728) of all sleep parameters, with a P value < .001, a sensitivity of 72.2% and a specificity of 73.8%.

CLINICAL IMPLICATIONS

Urologists and andrologists should be aware of impacted sleep quality and depression in ED patients.

STRENGTHS & LIMITATIONS

The strength of this study is that the relationship between sleep quality and ED was assessed with both a subjective scale and an objective sleep monitoring tool. However, our study only described an association between sleep quality and ED and did not establish a causal relationship.

CONCLUSION

Sleep parameters are strongly associated with ED, indicating that poor sleep quality may increase the likelihood of ED. Wu X, Zhang Y, Zhang W, et al. The Association Between Erectile Dysfunction and Sleep Parameters: Data from a Prospective, Controlled Cohort. J Sex Med 2022;XX:XXX-XXX.