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

AI-Driven Detection of Obstructive Sleep Apnea Using Dual-Branch CNN and Machine Learning Models

Background/Objectives: The purpose of this research is to compare and contrast the application of machine learning and deep learning methodologies such as a dual-branch convolutional neural network (CNN) model for detecting obstructive sleep apnea (OSA) from electrocardiogram (ECG) data. Methods: This approach solves the limitations of conventional polysomnography (PSG) and presents a non-invasive method for detecting OSA in its early stages with the help of AI. Results: The research shows that both CNN and dual-branch CNN models can identify OSA from ECG signals. The CNN model achieves validation and test accuracy of about 93% and 94%, respectively, whereas the dual-branch CNN model achieves 93% validation and 94% test accuracy. Furthermore, the dual-branch CNN obtains a ROC AUC score of 0.99, meaning that it is better at distinguishing between apnea and non-apnea cases. Conclusions: The results show that CNN models, especially the dual-branch CNN, are effective in apnea classification and better than traditional methods. In addition, our proposed model has the potential to be used as a reliable, non-invasive method for accurate OSA detection that is even better than the current state-of-the-art advanced methods.

Association Between Metabolic Score for Insulin Resistance (METS-IR) and Risk of Obstructive Sleep Apnea: Analysis of NHANES Database and a Chinese Cohort

Purpose

Insulin resistance (IR) plays a significant role in the development of obstructive sleep apnea (OSA). The metabolic score for insulin resistance (METS-IR) is a novel method for assessing IR. This study aims to explore the relationship between METS-IR and the risk of OSA.

Patients and Methods

This cross-sectional study included a total of 8297 subjects from NHANES (National Health and Nutrition Examination Survey) database, as well as 581 patients who underwent sleep monitoring in Renmin Hospital of Wuhan University. Logistic regression, subgroup analysis, and receiver operating characteristic (ROC) curve analysis were employed for evaluation.

Results

In the American population, a significant positive association was found between METS-IR and increased risk of OSA. For each unit increase in METS-IR, the risk of OSA increased by 4.4% (OR= 1.044; 95% CI: 1.037-1.059; P <0.001). A similar relationship was observed in the Chinese population. Multivariate Logistic regression model showed that for each unit increase in METS-IR, the prevalence of OSA increased by 6.7% (OR= 1.067; 95% CI: 1.035-1.103; P <0.001), and apnea-hypopnea index (AHI) increased by 0.732 (β= 0.732; 95% CI: 0.573-0.732; P <0.001). Gender subgroup analysis further showed that the association between METS-IR and OSA was particularly significant in male participants (OR= 1.111; 95% CI: 1.065-1.163; P <0.001). In the ROC analysis, the area under the curve (AUC) value of METS-IR for predicting OSA was 0.777, but it is not statistically significantly different from triglyceride glucose (TyG) (AUC = 0.749; P = 0.054), body mass index (BMI) (AUC = 0.769; P = 0.269), and triglyceride glucose-body mass index (TyG-BMI) (AUC = 0.777; P = 0.996).

Conclusion

METS-IR is significantly associated with the risk of OSA and may serve as an effective predictive marker for identifying OSA.

Development and Validation of an Explainable Prediction Model for Postoperative Recurrence in Pediatric Chronic Rhinosinusitis

OBJECTIVE

This study aims to develop an interpretable machine learning (ML) predictive model to assess its efficacy in predicting postoperative recurrence in pediatric chronic rhinosinusitis (CRS).

STUDY DESIGN

A decision analysis was performed with retrospective clinical data.

SETTING

Recurrent group and nonrecurrent group.

METHODS

This retrospective study included 148 pediatric CRS treated with functional endoscopic sinus surgery from January 2015 to January 2022. We collected demographic characteristics and peripheral blood inflammatory indices, and calculated inflammation indices. Models were trained with 3 ML algorithms and compared their predictive performance using the area under the receiver operating characteristic (AUC) curve. Shapley Additive Explanations and Ceteris Paribus profiles were used for model interpretation. The final model was transformed into a web for interactive visualization.

RESULTS

Among the 3 ML models, the Random Forest (RF) model demonstrated the best discriminative ability (AUC = 0.728). After reducing features based on importance and tuning parameters, the final RF model, including 4 features (systemic immune inflammation index (SII), pan-immune-inflammation value (PIV) and percentage of eosinophils (E%) and lymphocytes (L%)), showed good predictive performance in internal validation (AUC = 0.779). Global interpretation of the model suggested that L% and E% substantially contribute to the overall model. Local interpretation revealed a nonlinear relationship between the included features and model predictions. To enhance its clinical utility, the model was converted into a web (https://juice153.shinyapps.io/CRSRecurrencePrediction/).

CONCLUSION

Our ML model demonstrated promising accuracy in predicting postoperative recurrence in pediatric CRS, revealing a complex nonlinear relationship between postoperative recurrence and the features SII, PIV, L%, and E%.