A new study led by Dr. Rafael Nambo Venegas and colleagues, published in Metabolomics (Feb 2025), presents a high-accuracy predictive model for forecasting response to neoadjuvant therapy in breast cancer patients.
Combining metabolomic profiling and machine learning, the study analyzed plasma samples from young women with breast cancer to identify 18 key circulating biomarkers including acylcarnitines and amino acids linked to therapy outcomes.
The model achieved an impressive 90.7% accuracy and an AUC of 0.999, demonstrating strong predictive performance. These results support the development of a web-based clinical decision support tool to enhance treatment planning and move closer to truly personalized cancer care.
This work represents a critical step toward integrating metabolic signatures into predictive models for tailored oncology.
Full study: https://lnkd.in/dV7t3FFH
