Exploring the diagnostic performance of machine learning in prediction of metabolic phenotypes focusing on thyroid function
Open Access
- 28 June 2024
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (6) , e0304785
Abstract
In this study, we employed various machine learning models to predict metabolic phenotypes, focusing on thyroid function, using a dataset from the National Health and Nutrition Examination Survey (NHANES) from 2007 to 2012. Our analysis utilized laboratory parameters relevant to thyroid function or metabolic dysregulation in addition to demographic features, aiming to uncover potential associations between thyroid function and metabolic phenotypes by various machine learning methods. Multinomial Logistic Regression performed best to identify the relationship between thyroid function and metabolic phenotypes, achieving an area under receiver operating characteristic curve (AUROC) of 0.818, followed closely by Neural Network (AUROC: 0.814). Following the above, the performance of Random Forest, Boosted Trees, and K Nearest Neighbors was inferior to the first two methods (AUROC 0.811, 0.811, and 0.786, respectively). In Random Forest, homeostatic model assessment for insulin resistance, serum uric acid, serum albumin, gamma glutamyl transferase, and triiodothyronine/thyroxine ratio were positioned in the upper ranks of variable importance. These results highlight the potential of machine learning in understanding complex relationships in health data. However, it’s important to note that model performance may vary depending on data characteristics and specific requirements. Furthermore, we emphasize the significance of accounting for sampling weights in complex survey data analysis and the potential benefits of incorporating additional variables to enhance model accuracy and insights. Future research can explore advanced methodologies combining machine learning, sample weights, and expanded variable sets to further advance survey data analysis.Keywords
Funding Information
- National Institute on Minority Health and Health Disparities (2U54MD007601-36)
- National Institute of General Medical Sciences (U54GM138062)
This publication has 34 references indexed in Scilit:
- Optimizing classification of diseases through language model analysis of symptomsScientific Reports, 2024
- Predicting female pelvic tilt and lumbar angle using machine learning in case of urinary incontinence and sexual dysfunctionScientific Reports, 2023
- Utilizing convolutional neural networks to classify monkeypox skin lesionsScientific Reports, 2023
- Healthy Weight and Obesity PreventionJACC, 2018
- Machine learning: a primerNature Methods, 2017
- Association between thyroid function and lipid profiles, apolipoproteins, and high-density lipoprotein functionJournal of Clinical Lipidology, 2017
- Variations in Serum Free Thyroxine Concentration Within the Reference Range Predicts the Incidence of Metabolic Syndrome in Non-Obese Adults: A Cohort StudyThyroid®, 2017
- Triiodothyronine and Free Thyroxine Levels are Differentially Associated with Metabolic Profile and Adiposity-Related Cardiovascular Risk Markers in Euthyroid Middle-Aged SubjectsThyroid®, 2014
- Total, direct, and indirect serum bilirubin concentrations and metabolic syndrome among the Korean populationEndocrine, 2010
- Abdominal obesity and metabolic syndromeNature, 2006