Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status
Kamala K. Arumalla, Jean-François Haince, Rashid A. Bux, Guoyu Huang, Paramjit S. Tappia, Bram Ramjiawan, W. Randolph Ford, Maria Vaida · 2024
Read Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status by Kamala K. Arumalla, Jean-François Haince, Rashid A. Bux, Guoyu Huang, Paramjit S. Tappia, Bram Ramjiawan, W. Randolph Ford, Maria Vaida (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11641454.txt.
Description
Kamala Arumalla and co-authors read a breast tumor's hormone status from a blood sample's chemistry, using machine learning on blood chemistry profiles. Their 2024 study analyzes plasma from 188 patients and 73 healthy controls, hunting chemical patterns that separate estrogen-receptor-positive from negative cancers, a distinction that steers treatment.
Feature selection narrowed the signal to twenty-nine metabolites plus age. With synthetic balancing to fix the class imbalance, four algorithms were tuned and compared. A random forest won, reaching ninety-three percent accuracy and near-excellent discrimination. Current receptor testing needs tumor tissue; a blood-based screen could triage faster, with no biopsy, especially where biopsy capacity is scarce. The authors present a proof of concept on a modest cohort, with the usual caveat about outside validation. The panel itself, once confirmed, becomes a biological clue about how receptor status rewires metabolism.
Catalog record
| CREATOR | Kamala K. Arumalla, Jean-François Haince, Rashid A. Bux, Guoyu Huang, Paramjit S. Tappia, Bram Ramjiawan, W. Randolph Ford, Maria Vaida |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |