Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health

Ali Nemati5 days ago26 sec read19 views

The study identifies multilevel predictors of overweight and obesity among U.S. adolescents using various statistical and machine learning models, finding that logistic regression, gradient boosting, and MLP perform best in balancing discrimination and calibration. The key takeaway is that improving data quality and focusing on equity rather than increasing model complexity can better address persistent subgroup disparities.

Read the full article at arXiv cs.AI (Artificial Intelligence)

Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.

Comments

Tech & Learning Awards of Excellence 2025 Winner

ManagedMethods' Classroom Manager and Content Filter won the Tech & Learning Awards of Excellence in the Primary Education category for 2025, high...ManagedMethods' Classroom Manager and Content Filter won the Tech & Learning Awards of Excellence in the Primary Education category for 2025, highlighting their effectiveness in cybersecurity and classroom management solutions for K-12 schools. T...

Ali Nemati

AI & Machine Learning5 days ago25 sec read

Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling

Researchers propose a new framework for heart rate prediction that addresses data heterogeneity from both device and user variability, improving real-...Researchers propose a new framework for heart rate prediction that addresses data heterogeneity from both device and user variability, improving real-world performance by learning unified latent representations. The model's effectiveness is demonstra...

Ali Nemati

AI & Machine Learning5 days ago25 sec read

Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study

Researchers developed a machine learning model called MASER to predict Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) using electron...Researchers developed a machine learning model called MASER to predict Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) using electronic health records, aiming for early detection. The model balances predictive accuracy and fairness a...

Ali Nemati

AI & Machine Learning6 days ago23 sec read

Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning

The Similarity-as-Evidence (SaE) framework addresses overconfidence in Vision-Language Models used for medical active learning by calibrating text-ima...The Similarity-as-Evidence (SaE) framework addresses overconfidence in Vision-Language Models used for medical active learning by calibrating text-image similarities to better select informative samples for annotation. This approach improves accuracy...

Ali Nemati

AI & Machine LearningFeb 2030 sec read

Position: Evaluation of ECG Representations Must Be Fixed

Researchers argue that current benchmarking practices in 12-lead ECG representation learning need to be revised to include broader clinical targets be...Researchers argue that current benchmarking practices in 12-lead ECG representation learning need to be revised to include broader clinical targets beyond arrhythmia for more reliable progress. They highlight that a randomly initialized encoder perfo...

Ali Nemati

Multilevel Determinants of Overweight and Obesity Among U.S. Children Aged 10-17: Comparative Evaluation of Statistical and Machine Learning Approaches Using the 2021 National Survey of Children's Health

Related Articles

Tech & Learning Awards of Excellence 2025 Winner

Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling

Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study

Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning

Position: Evaluation of ECG Representations Must Be Fixed