Effects of Various Heavy Metal Exposures on Insulin Resistance in Non-diabetic Populations: Interpretability Analysis from Machine Learning Modeling Perspective.
{"title":"Effects of Various Heavy Metal Exposures on Insulin Resistance in Non-diabetic Populations: Interpretability Analysis from Machine Learning Modeling Perspective.","authors":"Jun Liu, Xingyu Li, Peng Zhu","doi":"10.1007/s12011-024-04126-3","DOIUrl":null,"url":null,"abstract":"<p><p>Increasing and compelling evidence has been proved that heavy metal exposure is involved in the development of insulin resistance (IR). We trained an interpretable predictive machine learning (ML) model for IR in the non-diabetic populations based on levels of heavy metal exposure. A total of 4354 participants from the NHANES (2003-2020) with complete information were randomly divided into a training set and a test set. Twelve ML algorithms, including random forest (RF), XGBoost (XGB), logistic regression (LR), GaussianNB (GNB), ridge regression (RR), support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), AdaBoost (AB), Gradient Boosting Decision Tree (GBDT), Voting Classifier (VC), and K-Nearest Neighbour (KNN), were constructed for IR prediction using the training set. Among these models, the RF algorithm had the best predictive performance, showing an accuracy of 80.14%, an AUC of 0.856, and an F1 score of 0.74 in the test set. We embedded three interpretable methods, the permutation feature importance analysis, partial dependence plot (PDP), and Shapley additive explanations (SHAP) in RF model for model interpretation. Urinary Ba, urinary Mo, blood Pb, and blood Cd levels were identified as the main influencers of IR. Within a specific range, urinary Ba (0.56-3.56 µg/L) and urinary Mo (1.06-20.25 µg/L) levels exhibited the most pronounced upwards trend with the risk of IR, while blood Pb (0.05-2.81 µg/dL) and blood Cd (0.24-0.65 µg/L) levels showed a declining trend with IR. The findings on the synergistic effects demonstrated that controlling urinary Ba levels might be more crucial for the management of IR. The SHAP decision plot offered personalized care for IR based on heavy metal control. In conclusion, by utilizing interpretable ML approaches, we emphasize the predictive value of heavy metals for IR, especially Ba, Mo, Pb, and Cd.</p>","PeriodicalId":8917,"journal":{"name":"Biological Trace Element Research","volume":" ","pages":"5438-5452"},"PeriodicalIF":3.4000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biological Trace Element Research","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1007/s12011-024-04126-3","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/26 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Increasing and compelling evidence has been proved that heavy metal exposure is involved in the development of insulin resistance (IR). We trained an interpretable predictive machine learning (ML) model for IR in the non-diabetic populations based on levels of heavy metal exposure. A total of 4354 participants from the NHANES (2003-2020) with complete information were randomly divided into a training set and a test set. Twelve ML algorithms, including random forest (RF), XGBoost (XGB), logistic regression (LR), GaussianNB (GNB), ridge regression (RR), support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), AdaBoost (AB), Gradient Boosting Decision Tree (GBDT), Voting Classifier (VC), and K-Nearest Neighbour (KNN), were constructed for IR prediction using the training set. Among these models, the RF algorithm had the best predictive performance, showing an accuracy of 80.14%, an AUC of 0.856, and an F1 score of 0.74 in the test set. We embedded three interpretable methods, the permutation feature importance analysis, partial dependence plot (PDP), and Shapley additive explanations (SHAP) in RF model for model interpretation. Urinary Ba, urinary Mo, blood Pb, and blood Cd levels were identified as the main influencers of IR. Within a specific range, urinary Ba (0.56-3.56 µg/L) and urinary Mo (1.06-20.25 µg/L) levels exhibited the most pronounced upwards trend with the risk of IR, while blood Pb (0.05-2.81 µg/dL) and blood Cd (0.24-0.65 µg/L) levels showed a declining trend with IR. The findings on the synergistic effects demonstrated that controlling urinary Ba levels might be more crucial for the management of IR. The SHAP decision plot offered personalized care for IR based on heavy metal control. In conclusion, by utilizing interpretable ML approaches, we emphasize the predictive value of heavy metals for IR, especially Ba, Mo, Pb, and Cd.
期刊介绍:
Biological Trace Element Research provides a much-needed central forum for the emergent, interdisciplinary field of research on the biological, environmental, and biomedical roles of trace elements. Rather than confine itself to biochemistry, the journal emphasizes the integrative aspects of trace metal research in all appropriate fields, publishing human and animal nutritional studies devoted to the fundamental chemistry and biochemistry at issue as well as to the elucidation of the relevant aspects of preventive medicine, epidemiology, clinical chemistry, agriculture, endocrinology, animal science, pharmacology, microbiology, toxicology, virology, marine biology, sensory physiology, developmental biology, and related fields.