XTRACTIS FOR PREDICTIVE MEDECINE

Genetic Identification of Lung Cancer

Benchmark vs. Logistic Regression, Random Forests, Boosted Trees & Neural Networks

How to make an automated — yet totally transparent — medical diagnosis of lung cancer from genetic sequencing of different tissues?

Goals & benefits

Identify the genes involved in cancer and enhance medical knowledge by helping pulmonologists and oncologists understand the causal relationships between specific genes, their combination, and the type of cancer.

Help the medical profession to make earlier and more personalized decisions through rapid, systematic, and explainable diagnoses.

Contribute to improving patient care (pain, survival, duration of treatment) and extend access to high-level diagnoses even in medical deserts.

XTRACTIS RESULTS

We get a Predictive Model that is:

Intelligible.

A Decision System composed of only 2 unchained gradual rules, each using 1 or 2 variables that XTRACTIS identified as significant (out of 12,533 levels of expression of genes characterizing each patient).

Robust.

Perfect Real Performance on External Test.

Efficient & Operational.

Running in real-time up to 70,000 predictions per second (i7 @2.5GHz with 8 physical cores), offline or online (API).

full use case

 Use Case 2023/01 (v1.1)

Results by
XTRACTIS® GENERATE 12.2.44169 (2022/12)

DOCUMENT CONTENTS

  1. Problem Definition
  2. Xtractis Solution
  3. Top-Model Induction
  4. Explained Predictions for 3 cases
  5. Top-Models Benchmark