Depression and obesity, but not mild obstructive sleep apnea, are associated factors for female sexual dysfunction

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

Objective

To 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.

Methods

We 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.

Results

Among 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.

Conclusion

Machine 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.

Approach the Patient With Obstructive Sleep Apnea and Obesity

Obstructive sleep apnea (OSA) and obesity are highly prevalent and bidirectionally associated. OSA is underrecognized, however, particularly in women. By mechanisms that overlap with those of obesity, OSA increases the risk of developing, or having poor outcomes from, comorbid chronic disorders and impairs quality of life. Using 2 illustrative cases, we discuss the relationships between OSA and obesity with type 2 diabetes, dyslipidemia, cardiovascular disease, cognitive disturbance, mood disorders, lower urinary tract symptoms, sexual function, and reproductive disorders. The differences in OSA between men and women, the phenotypic variability of OSA, and comorbid sleep disorders are highlighted. When the probability of OSA is high due to consistent symptoms, comorbidities, or both, a diagnostic sleep study is advisable. Continuous positive airway pressure or mandibular advancement splints improve symptoms. Benefits for comorbidities are variable depending on nightly duration of use. By contrast, weight loss and optimization of lifestyle behaviors are consistently beneficial.

The relationship between sleep disorders, quality, and duration and sexual dysfunction: a systematic review and meta-analysis

BACKGROUND

The associations between sexual dysfunction (SD) and sleep disorders, sleep quality, and sleep duration remain unclear.

AIM

To assess the relationship between sleep and SD through a literature review and meta-analysis.

METHODS

The PubMed, Scopus, Embase, Ovid MEDLINE, and Cochrane Library databases were systematically searched from inception to November 10, 2022.

OUTCOMES

Pooled relative risks and 95% CIs were used to examine the association of sleep disorders with SD in longitudinal studies. Pooled odds ratios (ORs) and 95% CIs were used to examine the associations between SD and sleep disorders, sleep quality, and sleep duration in cross-sectional studies.

RESULTS

Forty-three articles, including 11 longitudinal studies and 32 cross-sectional studies, were included in the quantitative analysis. The pooled relative risk of SD in patients with sleep disorders was 1.97 in longitudinal studies (95% CI, 1.46-2.67, P < .001; heterogeneity: I2 = 95.0%, P < .001), while the pooled OR of SD in patients with sleep disorders was 2.05 in cross-sectional studies (95% CI, 1.76-2.39, P < .001; heterogeneity: I2 = 91.4%, P < .001). When compared with controls, subjects with poor sleep quality had a 1.49-fold increased risk of SD (OR, 1.49; 95% CI, 1.31-1.71, P < .001; heterogeneity: I2 = 73.4%, P < .001). In addition, short sleep duration was associated with the risk of SD (OR, 1.14; 95% CI, 1.06-1.22, P < .001; heterogeneity: I2 = 0.0%, P = .849).

CLINICAL IMPLICATIONS

The risk of SD is significantly increased in patients with sleep disorders and poor sleep quality, indicating that clinicians should monitor sleep among patients with SD.

STRENGTHS AND LIMITATIONS

This study is the most comprehensive meta-analysis of the association between sleep and SD to date. However, different sleep disorders may have varying associations with sleep duration and sleep quality; thus, we could not identify the independent effects across the studies.

CONCLUSION

Our systematic review and meta-analysis results suggest that sleep disorders, especially obstructive sleep apnea, increase the risk of SD in men and women. Poor sleep quality is significantly associated with SD. Short sleep duration is associated with an increased risk of SD.

Mental and sexual well-being in non-binary and genderqueer individuals

BACKGROUND

Non-binary and genderqueer (NBGQ) individuals do not identify with a binary gender identity. Some but not all NBGQ individuals identify as transgender, and it is currently unclear on which aspects of mental and sexual well-being NBGQ and binary transgender individuals may differ.

AIM

To compare NBGQ, binary transgender and cisgender individuals on variables related to mental well-being, sexual well-being, and sexual self-concept discrepancies.

METHODS

We conducted an online questionnaire study in 125 transgender men, 72 transgender women, 78 NBGQ individuals, 98 cisgender men, and 107 cisgender women.

RESULTS

For most variables, NBGQ individuals did not differ from binary transgender individuals. These two groups differed only on gender dysphoria and transgender specific body image worries, which were both lower in the NBGQ group. Compared to the cisgender group, NBGQ individuals scored higher on gender dysphoria, actual/ought sexual self-concept discrepancies, and actual/ideal sexual self-concept discrepancies, and lower on general life satisfaction and sexual esteem related to body perception.

DISCUSSION

These results offer a first quantitative analysis of sexual well-being in NBGQ individuals, and highlight that - while both groups face unique challenges - NBGQ individuals encounter similar difficulties concerning mental and sexual well-being as binary transgender individuals.