Hypothesis-free discovery of novel cancer predictors using machine learning.

Iqbal MadakkatelAmanda L LumsdenAnwar MulugetaIan OlverElina Hyppӧnen

Published in: European journal of clinical investigation (2023)

This hypothesis-free analysis suggests personal characteristics, metabolic biomarkers, physical measures and smoking as important predictors of cancer risk, with further studies needed to confirm causality and clinical relevance.

Keyphrases

papillary thyroid
small molecule
physical activity
mental health
squamous cell
smoking cessation
high throughput
emergency department
adverse drug
case control
young adults
electronic health record