Clinical Predictors of Mixed Apneas in Patients with Obstructive Sleep Apnea (OSA)

Central and mixed apneas in children with obstructive sleep apnea: effect of adenotonsillectomy

PURPOSE

Investigate the effect of adenotonsillectomy on mixed apnea index (MAI) and central apnea index (CAI) in children with moderate-to-severe obstructive sleep apnea syndrome (OSAS).

METHODS

Observational retrospective analysis of polysomnographic data in children diagnosed with moderate-to-severe OSAS and without comorbidity, submitted to adenotonsillectomy.

RESULTS

Data were available for 80 children, 55 boys and 25 girls, with a median age of 3.6 years (2.1-5.9). Before surgery AHI was 14.1 (11.0-18.4) per hour, with a median preoperative OAI of 7.1 (4.1-10.6), MAI of 1.2 (0.6-1.6) and CAI of 1.0 (0.4-2.0). Adenotonsillectomy caused significant improvements in MAI, from 1.2 (0.6-1.6) to 0.5 (0.1-0.8) (p < 0.001) and CAI from 1.0 (0.4-2.0) to 0.5 (0.1-0.9) (p < 0.001). This represents a normalization of MAI in 91.7% and CAI in 75.6% of children that had an abnormal value prior surgery.

CONCLUSION

Non obstructive apneas are common in children with OSAS. Adenotonsillectomy caused significant decrease not only in OAI, but also in MAI and CAI in children with moderate-to-severe OSAS.

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.

Obstructive Sleep Apnea in Pregnancy: A Comprehensive Review of Maternal and Fetal Implications

Obstructive sleep apnea (OSA) is a prevalent yet underdiagnosed condition in pregnancy, associated with various maternal and fetal complications. This review synthesizes the current evidence on the epidemiology, pathophysiology, and neurological consequences of OSA in pregnancy, along with the potential management strategies. Articles were sourced from the PubMed, EMBASE, and Cochrane databases until 2023. Our comprehensive review highlights that the incidence of OSA increases during pregnancy due to physiological changes such as weight gain and hormonal fluctuations. OSA in pregnancy is linked with gestational hypertension, pre-eclampsia, gestational diabetes, and potential adverse fetal outcomes such as intrauterine growth restriction and preterm birth. Continuous positive airway pressure (CPAP) therapy remains the most effective management strategy for pregnant women with OSA. However, adherence to CPAP therapy is often suboptimal. This comprehensive review underscores the importance of the early recognition, timely diagnosis, and effective management of OSA in pregnancy to improve both maternal and fetal outcomes. Future research should focus on enhancing screening strategies and improving adherence to CPAP therapy in this population.

Assessing the contribution of mild high-altitude exposure to obstructive sleep apnea-hypopnea syndrome comorbidities

Background

Obstructive sleep apnea-hypopnea syndrome (OSAHS) is a common sleep disorder. The lower atmospheric pressure and decreased oxygen levels of high-altitude areas can exacerbate the severity of OSAHS, but research into OSAHS in high-altitude areas remains limited. This study, from June 2015 to January 2020, involved 4,667 patients with suspected OSAHS and 38 healthy volunteers. The non-OSAHS group (AHI <5/h) had 395 patients, while the larger OSAHS group (AHI ≥5/h) comprised 4,272 patients. The significant size difference between the groups emphasized the study's focus on OSAHS, using the non-OSAHS mainly for comparison.

Methods

Sleep technicians monitored the OSAHS patient group overnight by polysomnography (PSG), the apnea-hypopnea index (AHI), the mean oxygen saturation (MSpO2), lowest oxygen saturation (LSpO2), the oxygen desaturation index (ODI) and the total sleep time with oxygen saturation less than 90% (TST-SpO2 <90%). Healthy volunteers self-monitored sleep patterns at home, using the CONTEC RS01 respiration sleep monitor with a wristwatch sleep apnea screen meter. The RSO1 wristwatch-style device has already been studied for consistency and sensitivity with the Alice-6 standard multi-lead sleep monitor and can be used for OSAHS screening in this region.

Results

LSpO2 recordings from healthy volunteers (86.36 ± 3.57%) and non-OSAHS (AHI <5/h) cohort (78.59 ± 11.99%) were much lower than previously reported normal values. Regression analysis identified no correlations between AHI levels and MSpO2 or TST-SpO2 <90%, weak correlations between AHI levels and LSpO2 or MSpO2, and a strongly significant correlation between AHI levels and the ODI (r = 0.76, p < 0.05). The data also indicated that the appropriate clinical thresholds for OSAHS patients living at mild high altitude are classified as mild, moderate, or severe based on LSpO2 saturation criteria of 0.85-0.90, 0.65-0.84, or <0.65, respectively.

Conclusion

The study findings suggest that individuals with an AHI score below 5 in OSAHS, who reside in high-altitude areas, also require closer monitoring due to the elevated risk of nocturnal hypoxia. Furthermore, the significant correlation between ODI values and the severity of OSAHS emphasizes the importance of considering treatment options. Additionally, the assessment of hypoxemia severity thresholds in OSAHS patients living in high-altitude regions provides valuable insights for refining diagnostic guidelines.

Incorporating neck circumference or neck-to-height ratio into the GOAL questionnaire to better detect and describe obstructive sleep apnea with application to clinical decisions

Objective

Although neck circumference (NC) and neck-to-height ratio (NHR) have been recognized as effective predictors of the clinical diagnosis of adult obstructive sleep apnea (OSA), they have not been included in the widely used GOAL questionnaire. Not coincidentally, the NHR has not been adequately considered in the development and validation of the STOP-Bang questionnaire, No-Apnea score and the NoSAS score. The motivation for the study was (1) to combine the GOAL questionnaire with the NC and NHR, respectively, to evaluate its predictive performance and (2) to compare it with the STOP-Bang questionnaire, the No-Apnea score, the NOSAS score, and the GOAL questionnaire.

Materials and methods

This retrospectively allocated cross-sectional study was conducted from November 2017 to March 2022 in adults who underwent nocturnal polysomnography (PSG) or home sleep apnea testing (HSAT). In this paper, the GOAL questionnaire was combined with the NC and NHR, respectively, using logistic regression. The performance of the six screening tools was assessed by discriminatory ability [area under the curve (AUC) obtained from receiver operating characteristic (ROC) curves] and a 2 × 2 league table [including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (LR+), and negative likelihood ratio (LR−)] and compared under AHI ≥5/h, AHI ≥15/h, and AHI ≥30/h conditions.

Results

A total of 288 patients were enrolled in the study. For all severity OSA levels, the sensitivity of GOAL+NC ranged from 70.12 to 70.80%, and specificity ranged from 86.49 to 76.16%. The sensitivity of GOAL+NHR ranged from 73.31 to 81.75%, while specificity ranged from 83.78 to 70.86%. As for area under the curve (AUC) value under ROC curve, when AHI ≥5/h, compared with GOAL (0.806), No-Apnea (0.823), NoSAS (0.817), and GOAL+NC (0.815), GOAL+NHR (0.831) obtained the highest AUC value, but lower than STOP-Bang (0.837).

Conclusion

The predictive power of incorporating NC or NHR into the GOAL questionnaire was significantly better than that of the GOAL itself. Furthermore, GOAL+NHR was superior to GOAL+NC in predicting OSA severity and better than the No-Apnea score and the NoSAS score.

Development and assessment of a risk prediction model for moderate-to-severe obstructive sleep apnea

Background

OSA is an independent risk factor for several systemic diseases. Compared with mild OSA, patients with moderate-to-severe OSA have more severe impairment in the function of all organs of the body. Due to the current limited medical condition, not every patient can be diagnosed and treated in time. To enable timely screening of patients with moderate-to-severe OSA, we selected easily accessible variables to establish a risk prediction model.

Method

We collected 492 patients who had polysomnography (PSG), and divided them into the disease-free mild OSA group (control group), and the moderate-to-severe OSA group according to the PSG results. Variables entering the model were identified by random forest plots, univariate analysis, multicollinearity test, and binary logistic regression method. Nomogram were created based on the binary logistic results, and the area under the ROC curve was used to evaluate the discriminative properties of the nomogram model. Bootstrap method was used to internally validate the nomogram model, and calibration curves were plotted after 1,000 replicate sampling of the original data, and the accuracy of the model was evaluated using the Hosmer-Lemeshow goodness-of-fit test. Finally, we performed decision curve analysis (DCA) of nomogram model, STOP-Bang questionnaire (SBQ), and NoSAS score to assess clinical utility.

Results

There are 6 variables entering the final prediction model, namely BMI, Hypertension, Morning dry mouth, Suffocating awake at night, Witnessed apnea, and ESS total score. The AUC of this prediction model was 0.976 (95% CI: 0.962–0.990). Hosmer-Lemeshow goodness-of-fit test χ² = 3.3222 (P = 0.1899 > 0.05), and the calibration curve was in general agreement with the ideal curve. The model has good consistency in predicting the actual occurrence of moderate-to-severe risk, and has good prediction accuracy. The DCA shows that the net benefit of the nomogram model is higher than that of SBQ and NoSAS, with has good clinical utility.

Conclusion

The prediction model obtained in this study has good predictive power for moderate-to-severe OSA and is superior to other prediction models and questionnaires. It can be applied to the community population for screening and to the clinic for prioritization of treatment.