A predictive model for neoadjuvant therapy response in breast cancer

Area of Science:

• Oncology
• Metabolomics
• Machine Learning

Background:

• Neoadjuvant therapy is a standard breast cancer treatment with variable patient response.
• Accurate prediction of treatment response is crucial for personalized medicine.

Purpose of the Study:

• To develop and validate machine learning models using circulating metabolites to predict neoadjuvant therapy response in breast cancer patients.
• To enhance personalized treatment strategies through accurate response forecasting.

Main Methods:

• Retrospective analysis of 30 young women breast cancer patients (responders vs. non-responders).
• Plasma metabolome analysis using liquid chromatography-tandem mass spectrometry, focusing on 40 metabolites.
• Machine learning model development and validation to identify predictive biomarkers.

Main Results:

• Identified 18 significant biomarkers, including acylcarnitines and amino acids.
• Developed a predictive model with 90.7% accuracy and an AUC of 0.999.
• Highlighted the significant role of circulating metabolites in predicting therapy outcomes.

Conclusions:

• Metabolomics is crucial for personalized breast cancer medicine.
• Metabolite biomarkers can be effectively identified to correlate with neoadjuvant therapy response.
• This approach enables tailoring treatment based on individual metabolic profiles to improve patient outcomes.