Scholarlink

Background <p>Asthma is a prevalent chronic respiratory disease with significant morbidity and healthcare burden. Identifying novel biomarkers for asthma risk prediction is crucial for early intervention and personalized management. The monocyte-to-high-density lipoprotein cholesterol ratio (MHR) has emerged as a potential inflammatory marker in various chronic diseases. This study aimed to investigate the association between MHR and asthma risk using data from the National Health and Nutrition Examination Survey (NHANES) and to develop a predictive model for asthma risk incorporating MHR and other clinical variables.</p> Methods <p>Data from NHANES (2001–2018) were used. Weighted logistic regression was employed to assess the relationship between MHR and asthma risk. Participants were randomly divided into training (70%) and validation (30%) cohorts. The Boruta algorithm was used to evaluate the training cohort, select the best model, and identify potential confounding factors. A nomogram-based predictive model was constructed using variables selected by the Boruta algorithm [smoke, age, hypertension, cardiovascular disease (CVD), marital status, gender, race, poverty–income ratio (PIR), body mass index (BMI), cancer, education, diabetes, and MHR]. The model’s performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves. The variables selected by Boruta algorithm are included in the machine learning (ML) model for analysis. SHAP (SHapley Additive exPlanations) analysis was performed to assess the contribution of each variable.</p> Results <p>A total of 28,855 participants were included after excluding those with missing data. MHR was positively associated with asthma incidence (<i>P</i> &lt; 0.05). The Boruta algorithm achieved an AUC of 0.64 in the validation cohort. Among the ML models, the Xgboost model demonstrated the best performance with an AUC of 0.640 (95% CI 0.623–0.656). SHAP analysis identified CVD as the most influential factor, followed by age, BMI, PIR, and gender.</p> Conclusions <p>This study demonstrates a positive association between the MHR and asthma risk, indicating a significant cross-sectional relationship. The nomogram-based predictive model incorporating MHR and other clinical variables showed moderate discriminative ability.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning and nomogram prediction model to explore the relationship between monocyte-to-high-density lipoprotein cholesterol ratio and asthma: results from the NHANES 2001–2018

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月26日

查看全文
  • Lizhen Zou,
  • Jijing Zhao,
  • Yingding Ruan,
  • Yunpeng Wang

摘要

Background

Asthma is a prevalent chronic respiratory disease with significant morbidity and healthcare burden. Identifying novel biomarkers for asthma risk prediction is crucial for early intervention and personalized management. The monocyte-to-high-density lipoprotein cholesterol ratio (MHR) has emerged as a potential inflammatory marker in various chronic diseases. This study aimed to investigate the association between MHR and asthma risk using data from the National Health and Nutrition Examination Survey (NHANES) and to develop a predictive model for asthma risk incorporating MHR and other clinical variables.

Methods

Data from NHANES (2001–2018) were used. Weighted logistic regression was employed to assess the relationship between MHR and asthma risk. Participants were randomly divided into training (70%) and validation (30%) cohorts. The Boruta algorithm was used to evaluate the training cohort, select the best model, and identify potential confounding factors. A nomogram-based predictive model was constructed using variables selected by the Boruta algorithm [smoke, age, hypertension, cardiovascular disease (CVD), marital status, gender, race, poverty–income ratio (PIR), body mass index (BMI), cancer, education, diabetes, and MHR]. The model’s performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves. The variables selected by Boruta algorithm are included in the machine learning (ML) model for analysis. SHAP (SHapley Additive exPlanations) analysis was performed to assess the contribution of each variable.

Results

A total of 28,855 participants were included after excluding those with missing data. MHR was positively associated with asthma incidence (P < 0.05). The Boruta algorithm achieved an AUC of 0.64 in the validation cohort. Among the ML models, the Xgboost model demonstrated the best performance with an AUC of 0.640 (95% CI 0.623–0.656). SHAP analysis identified CVD as the most influential factor, followed by age, BMI, PIR, and gender.

Conclusions

This study demonstrates a positive association between the MHR and asthma risk, indicating a significant cross-sectional relationship. The nomogram-based predictive model incorporating MHR and other clinical variables showed moderate discriminative ability.