Prediction model of obstructive sleep apnea-related hypertension: Machine learning-based development and interpretation study

Development and Evaluation of a Hypertension Prediction Model for Community-Based Screening of Sleep-Disordered Breathing

Purpose

Approximately 30% of patients with sleep-disordered breathing (SDB) present with masked hypertension, primarily characterized by elevated nighttime blood pressure. This study aimed to develop a hypertension prediction model tailored for primary care physicians, utilizing simple, readily available predictors derived from type IV sleep monitoring devices.

Patients and Methods

Participants were recruited from communities in Guangdong Province, China, between April and May 2021. Data collection included demographic information, clinical indicators, and results from type IV sleep monitors, which recorded oxygen desaturation index (ODI), average nocturnal oxygen saturation (MeanSpO2), and lowest recorded oxygen saturation (MinSpO2). Hypertension was diagnosed using blood pressure monitoring or self-reported antihypertensive medication use. A nomogram was constructed using multivariate logistic regression after Least Absolute Shrinkage and Selection Operator (LASSO) regression identified six predictors: waist circumference, age, ODI, diabetes status, family history of hypertension, and apnea. Model performance was evaluated using area under the curve (AUC), calibration plots, and decision curve analysis (DCA).

Results

The model, developed in a cohort of 680 participants and validated in 401 participants, achieved an AUC of 0.775 (95% CI: 0.730-0.820) in validation set. Calibration plots demonstrated excellent agreement between predictions and outcomes, while DCA confirmed significant clinical utility.

Conclusion

This hypertension prediction model leverages easily accessible indicators, including oximetry data from type IV sleep monitors, enabling effective screening during community-based SDB assessments. It provides a cost-effective and practical tool for prioritizing early intervention and management strategies in both primary care and clinical settings.

Craniofacial Development Characteristics in Children with Obstructive Sleep Apnea for Establishment and External Validation of the Prediction Model

Purpose

Aimed to analyze the developmental characteristics of craniofacial structures and soft tissues in children with obstructive sleep apnea (OSA) and to establish and evaluate prediction model.

Methods

It's a retrospective study comprising 747 children aged 2-12 years (337 patients and 410 controls) visited the Department of Otolaryngology-Head and Neck Surgery, the Second Affiliated Hospital of Xi'an Jiaotong University (July 2017 to March 2024). Lateral head radiographs were obtained to compare the cephalometric measurements. The clinical prediction model was constructed using LASSO regression analysis. We analyzed 300 children from the Xi'an Children's Hospital for external validation.

Results

Children with OSA had a higher body mass, a higher tonsil grade, larger AN ratio (ratio of the adenoids to the skeletal upper airway width), larger radius of the tonsils, a smaller angle between the skull base and maxilla (SNA) and smaller angle between the skull base and mandible (SNB), a larger distance from the hyoid to the mandibular plane (H-MP) and smaller distance between the third cervical vertebra and hyoid (H-C), a larger thickness of the soft palate (SPT) and smaller inclination angle of the soft palate than those of the controls (all p < 0.05). A prediction model was constructed for 2-12 years group (AUC of 0.812 [95% CI: 0.781-0.842]). Age-specific prediction models were developed for preschool children (AUC of 0.769 [95% CI: 0.725-0.814]), for school-aged children (AUC of 0.854 [95% CI: 0.812-0.895]).

Conclusion

Our study findings support the important role of craniofacial structures such as the hyoid, maxilla, mandible, and soft palate in pediatric OSA. Age-stratified predictive models for pediatric OSA indicated varying parameters across different age groups which underscore the necessity for stratifying by age in future research. The prediction model designed will greatly assist health care practitioners with rapidly identifying.

Uveal melanoma distant metastasis prediction system: A retrospective observational study based on machine learning

Uveal melanoma (UM) patients face a significant risk of distant metastasis, closely tied to a poor prognosis. Despite this, there is a dearth of research utilizing big data to predict UM distant metastasis. This study leveraged machine learning methods on the Surveillance, Epidemiology, and End Results (SEER) database to forecast the risk probability of distant metastasis. Therefore, the information on UM patients from the SEER database (2000-2020) was split into a 7:3 ratio training set and an internal test set based on distant metastasis presence. Univariate and multivariate logistic regression analyses assessed distant metastasis risk factors. Six machine learning methods constructed a predictive model post-feature variable selection. The model evaluation identified the multilayer perceptron (MLP) as optimal. Shapley additive explanations (SHAP) interpreted the chosen model. A web-based calculator personalized risk probabilities for UM patients. The results show that nine feature variables contributed to the machine learning model. The MLP model demonstrated superior predictive accuracy (Precision = 0.788; ROC AUC = 0.876; PR AUC = 0.788). Grade recode, age, primary site, time from diagnosis to treatment initiation, and total number of malignant tumors were identified as distant metastasis risk factors. Diagnostic method, laterality, rural-urban continuum code, and radiation recode emerged as protective factors. The developed web calculator utilizes the MLP model for personalized risk assessments. In conclusion, the MLP machine learning model emerges as the optimal tool for predicting distant metastasis in UM patients. This model facilitates personalized risk assessments, empowering early and tailored treatment strategies.

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.

A risk prediction nomogram for resistant hypertension in patients with obstructive sleep apnea

Patients with obstructive sleep apnea (OSA) are liable to have resistant hypertension (RH) associated with unfavorable cardiovascular events. It is of necessity to predict OSA patients who are susceptible to resistant hypertension. Hence, we conducted a retrospective study based on the clinical records of OSA patients admitted to Yixing Hospital Affiliated to Jiangsu University from January 2018 to December 2022. According to different time periods, patients diagnosed between January 2018 and December 2021 were included in the training set (n = 539) for modeling, and those diagnosed between January 2022 and December 2022 were enrolled into the validation set (n = 259) for further assessment. The incidence of RH in the training set and external validation set was comparable (P = 0.396). The related clinical data of patients enrolled were collected and analyzed through univariate analysis and least absolute shrinkage and selection operator (LASSO) logistic regression analysis to identify independent risk factors and construct a nomogram. Finally, five variables were confirmed as independent risk factors for OSA patients with RH, including smoking, heart disease, neck circumference, AHI and T90. The nomogram established on the basis of variables above was shown to have good discrimination and calibration in both the training set and validation set. Decision curve analysis indicated that the nomogram was useful for a majority of OSA patients. Therefore, our nomogram might be useful to identify OSA patients at high risk of developing RH and facilitate the individualized management of OSA patients in clinical practice.

Sleep Quality, Nutrient Intake, and Social Development Index Predict Metabolic Syndrome in the Tlalpan 2020 Cohort: A Machine Learning and Synthetic Data Study

This study investigated the relationship between Metabolic Syndrome (MetS), sleep disorders, the consumption of some nutrients, and social development factors, focusing on gender differences in an unbalanced dataset from a Mexico City cohort. We used data balancing techniques like SMOTE and ADASYN after employing machine learning models like random forest and RPART to predict MetS. Random forest excelled, achieving significant, balanced accuracy, indicating its robustness in predicting MetS and achieving a balanced accuracy of approximately 87%. Key predictors for men included body mass index and family history of gout, while waist circumference and glucose levels were most significant for women. In relation to diet, sleep quality, and social development, metabolic syndrome in men was associated with high lactose and carbohydrate intake, educational lag, living with a partner without marrying, and lack of durable goods, whereas in women, best predictors in these dimensions include protein, fructose, and cholesterol intake, copper metabolites, snoring, sobbing, drowsiness, sanitary adequacy, and anxiety. These findings underscore the need for personalized approaches in managing MetS and point to a promising direction for future research into the interplay between social factors, sleep disorders, and metabolic health, which mainly depend on nutrient consumption by region.

Shapely additive values can effectively visualize pertinent covariates in machine learning when predicting hypertension

Machine learning methods are widely used within the medical field to enhance prediction. However, little is known about the reliability and efficacy of these models to predict long-term medical outcomes such as blood pressure using lifestyle factors, such as diet. The authors assessed whether machine-learning techniques could accurately predict hypertension risk using nutritional information. A cross-sectional study using data from the National Health and Nutrition Examination Survey (NHANES) between January 2017 and March 2020. XGBoost was used as the machine-learning model of choice in this study due to its increased performance relative to other common methods within medical studies. Model prediction metrics (e.g., AUROC, Balanced Accuracy) were used to measure overall model efficacy, covariate Gain statistics (percentage each covariate contributes to the overall prediction) and SHapely Additive exPlanations (SHAP, method to visualize each covariate) were used to provide explanations to machine-learning output and increase the transparency of this otherwise cryptic method. Of a total of 9650 eligible patients, the mean age was 41.02 (SD = 22.16), 4792 (50%) males, 4858 (50%) female, 3407 (35%) White patients, 2567 (27%) Black patients, 2108 (22%) Hispanic patients, and 981 (10%) Asian patients. From evaluation of model gain statistics, age was found to be the single strongest predictor of hypertension, with a gain of 53.1%. Additionally, demographic factors such as poverty and Black race were also strong predictors of hypertension, with gain of 4.33% and 4.18%, respectively. Nutritional Covariates contributed 37% to the overall prediction: Sodium, Caffeine, Potassium, and Alcohol intake being significantly represented within the model. Machine Learning can be used to predict hypertension.

Differential diagnosis of secondary hypertension based on deep learning

Secondary hypertension is associated with higher risks of target organ damage and cardiovascular and cerebrovascular disease events. Early aetiology identification can eliminate aetiologies and control blood pressure. However, inexperienced doctors often fail to diagnose secondary hypertension, and comprehensively screening for all causes of high blood pressure increases health care costs. To date, deep learning has rarely been involved in the differential diagnosis of secondary hypertension. Relevant machine learning methods cannot combine textual information such as chief complaints with numerical information such as the laboratory examination results in electronic health records (EHRs), and the use of all features increases health care costs. To reduce redundant examinations and accurately identify secondary hypertension, we propose a two-stage framework that follows clinical procedures. The framework carries out an initial diagnosis process in the first stage, on which basis patients are recommended for disease-related examinations, followed by differential diagnoses of different diseases based on the different characteristics observed in the second stage. We convert the numerical examination results into descriptive sentences, thus blending textual and numerical characteristics. Medical guidelines are introduced through label embedding and attention mechanisms to obtain interactive features. Our model was trained and evaluated using a cross-sectional dataset containing 11,961 patients with hypertension from January 2013 to December 2019. The F1 scores of our model were 0.912, 0.921, 0.869 and 0.894 for primary aldosteronism, thyroid disease, nephritis and nephrotic syndrome and chronic kidney disease, respectively, which are four kinds of secondary hypertension with high incidence rates. The experimental results show that our model can powerfully use the textual and numerical data contained in EHRs to provide effective decision support for the differential diagnosis of secondary hypertension.