XTRACTIS for Precision Medicine

Blood Test-Based Opportunistic Diagnosis of Diabetes

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

Design an AI-based decision system that accurately establishes a rational and explainable medical diagnosis of diabetes based on the patient’s medical characteristics and blood test results.

Goals & Benefits

  1. Identify the parameters actually involved in opportunistic diagnosis of diabetes, i.e. even if the patient is not fasting.
  2. Enhance medical knowledge by helping healthcare professionals understand the causal relationships between these parameters, their combination, and the disease.
  3. Help the medical profession identify patients who may be at risk of having diabetes through rapid, systematic and explainable diagnoses, in order to request additional tests reinforcing the diagnosis, if necessary.

XTRACTIS-induced Decision System

Intelligible Model, Explainable Decisions
  • The top-model is a decision system composed of 12 rules without chaining.
  • Each rule uses from 1 to 5 predictors among the 8 variables that XTRACTIS automatically identified as significant in the decision process (out of the 8 Potential Predictors).
  • Only a few rules are triggered at a time to compute the decision

It has a good Real Performance (on unknown data). But some other predictors seem missing.

It computes real-time predictions up to 70,000 decisions/second, offline or online (API).

LoR = Logistic Regression RFo=Random Forests
BT=Boosted Trees
NN=Neural Networks

Detailed results and explanations in full document

Use Case 2025/07 (v1.1)

Powered by XTRACTIS® REVEAL v13.2.52316 (2024/09)

Download Document

CONTENTS

  1. Problem Definition
  2. XTRACTIS-induced Decision System
  3. XTRACTIS Process
  4. Top-Model Induction
  5. Explained Predictions for 2 unkown cases
  6. Top-Models Benchmark
  7. Quantitative Metrics