XTRACTIS FOR PREDICTIVE MEDECINE

secteur santé - diagnotic cancer

ANATOMOPATHOLOGICAL DIAGNOSIS OF BREAST CANCER

Benchmark: XTRACTIS VS. RANDOM FORESTS, BOOSTED TREES & NEURAL NETWORKS

This study aims to solve the following problem:

How to make an automated medical diagnosis of breast cancer from microscopic images of patient tumors?

GOALS

  • Enhance medical knowledge by helping pathologists and oncologists understand the causal relationships between mammal cell characteristics under the microscope and the presence of cancer.
  • Assist the medical profession in making an earlier and more individualized decision, thanks to rapid and systematic diagnoses.
  • Contribute to improving patient care (pain, survival, duration of treatment) and access to diagnostics even in medical deserts.
 
XTRACTIS RESULTS
 
A predictive model that is:
  • Intelligible. 7 gradual unchained rules, based on 13 predictors.
  • Robust. Excellent predictive performance.
  • Efficient. Instant prediction (online or offline).

CONTENTS

  1. Problem Definition
  2. Xtractis Solution
  3. Top-Model Induction
  4. Prediction for 2 Unknown Cases of Testing
  5. Top-IVE Benchmark
Results by XTRACTIS® GENERATE 12.1.40851 (March 2022)
Use Case first version: June 2018
Current Version: June 2022