Screening of serum biomarkers in patients with PCOS through lipid omics and ensemble machine learning

PLoS ONE, Год журнала: 2025, Номер 20(1), С. e0313494 - e0313494

Опубликована: Янв. 7, 2025

Polycystic ovary syndrome (PCOS) is a primary endocrine disorder affecting premenopausal women involving metabolic dysregulation. We aimed to screen serum biomarkers in PCOS patients using untargeted lipidomics and ensemble machine learning. Serum from non-PCOS subjects were collected for analysis. Through analyzing the classification of differential lipid metabolites association between clinical indexes, learning, data preprocessing, statistical test pre-screening, learning method secondary screening, verification evaluation, diagnostic panel model construction performed on lipidomics. Results indicated that different not only differ groups but also have close effects corresponding indexes. PI (18:0/20:3)-H PE (18:1p/22:6)-H identified as candidate biomarkers. Three models, logistic regression, random forest, support vector machine, showed screened had better ability effect. In addition, correlation was low, indicating overlap selected combination panels more optimized. When AUC value set constructed 0.815, model’s accuracy 0.74, specificity 0.88, sensitivity 0.7. This study demonstrated applicability robustness algorithms analyze metabolism efficient reliable biomarker screening. great potential diagnosing PCOS.

Язык: Английский

Metabolomics based analysis reveals the therapeutic effects of Incarvillea arguta (Royle) Royle aqueous extract against alcohol-induced liver injury

Phytomedicine, Год журнала: 2025, Номер 140, С. 156639 - 156639

Опубликована: Март 12, 2025

Язык: Английский