Leveraging machine learning in precision medicine to unveil organochlorine pesticides as predictive biomarkers for thyroid dysfunction
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Organochlorine pesticide exposure is linked to thyroid dysfunction. Machine learning models accurately identified specific pesticides, like Methoxychlor and DDT, associated with these health risks.
Area Of Science
- Environmental Health
- Toxicology
- Endocrinology
Background
- Organochlorine pesticides (OCPs) are persistent environmental pollutants.
- OCP exposure is associated with various adverse health outcomes, including endocrine disruption.
Purpose Of The Study
- To investigate the association between OCP exposure and thyroid disturbances.
- To evaluate the efficacy of machine learning models in classifying thyroid status based on OCP exposure.
Main Methods
- Analysis of 16 OCPs and thyroid hormones (T3, T4, TSH) in blood samples.
- Application of traditional (Logistic Regression, LASSO) and advanced machine learning models (Random Forest, SVM, XGBoost, GBM).
Main Results
- High detection frequencies (>70%) of several OCPs, including Heptachlor and Methoxychlor.
- Machine learning models, particularly Random Forest and GBM, achieved high accuracy (90.91%).
- XGBoost demonstrated a high ROC-AUC score (94.02%), indicating strong predictive performance.
Conclusions
- A strong correlation exists between OCP exposure and thyroid dysfunction.
- Specific OCPs, including Methoxychlor, p,p-DDT, and Heptachlor, are significantly associated with impaired thyroid function.
- Machine learning models provide accurate classification of thyroid status in relation to OCP exposure.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
