Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status
International Journal of Molecular Sciences · 2024
DOI: 10.3390/ijms252313029 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Kamala K Arumalla und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA. Hauptthemen laut MEDLINE: Breast Neoplasms, Receptors, Estrogen, Machine Learning, Metabolomics. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: BioMark Diagnostics Inc (Richmond, BC, Canada), BioMark Diagnostics Inc..
Abstract (Originalsprache)
Breast cancer is a global concern as a leading cause of death for women. Early and precise diagnosis can be vital in handling the disease efficiently. Breast cancer subtyping based on estrogen receptor (ER) status is crucial for determining prognosis and treatment. This study uses metabolomics data from plasma samples to detect metabolite biomarkers that could distinguish ER-positive from ER-negative breast cancers in a non-invasive manner. The dataset includes demographic information, ER status, and metabolite levels from 188 breast cancer patients and 73 healthy controls. Recursive Feature Elimination (RFE) with a Random Forest (RF) classifier identified an optimal subset of 30 features—29 biomarkers and age—that achieved the highest area under the curve (AUC). To address the class imbalance, Gaussian noise-based augmentation and Adaptive Synthetic Oversampling (ADASYN) were applied, ensuring balanced representation during training. Four machine learning (ML) algorithms—Random Forest, Support Vector Classifier (SVC), XGBoost, and Logistic Regression (LR)—were evaluated using grid search. The Random Forest classifier emerged as the top performer, achieving an AUC of 0.95 and an accuracy of 93%. These results suggest that ML has great promise for identifying specific metabolites linked to ER expression, paving the development of a novel analytical tool that can minimize current challenges in identifying ER status, and improve the precision of breast cancer subtyping.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA.
- BioMark Diagnostic Solutions Inc., Quebec, QC G1K 3G5, Canada.
- BioMark Diagnostics Inc., Richmond, BC V6X 2W2, Canada.
- Asper Clinical Research Institute, Winnipeg, MB R2H2A6, Canada.
- Department of Pharmacology & Therapeutics, Max Rady College of Medicine, University of Manitoba, Winnipeg, MB R3E 0T6, Canada.
ORCID-Profile: Jean-François Haince, Guoyu Huang, Paramjit S Tappia
Förderung
- BioMark Diagnostics Inc (Richmond, BC, Canada)
- BioMark Diagnostics Inc.
Zitieren
APA
Arumalla, K. K., Haince, J. F., Bux, R. A., Huang, G., Tappia, P. S., Ramjiawan, B., Ford, W. R., & Vaida, M. (2024). Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms252313029
Vancouver
Arumalla KK, Haince JF, Bux RA, Huang G, Tappia PS, Ramjiawan B, et al. Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms252313029
BibTeX
@article{Arumalla2024,
author = {Arumalla, Kamala K and Haince, Jean-François and Bux, Rashid A and Huang, Guoyu and Tappia, Paramjit S and Ramjiawan, Bram and Ford, W Randolph and Vaida, Maria},
title = {Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status},
journal = {International Journal of Molecular Sciences},
year = {2024},
doi = {10.3390/ijms252313029}
}
EUVIMED