Webinar: Diagnostic Decision Support for Coronary Artery Disease

Overview

In this webinar, we illustrate how Bayesian networks can serve as a practical tool for optimizing the sequence of diagnostic steps to arrive at a medical diagnosis quickly and cost-efficiently. Bayesian networks allow us to precisely quantify the amount of information contributed by each to-be-observed variable, such as risk factors and symptoms. This capability is one of the key points where machine-learned Bayesian networks distinguish themselves from other predictive models, such as neural networks.

We will utilize the dataset published by Dr. Zahra Alizadeh Sani on Coronary Artery Disease to demonstrate a complete research workflow, from importing the raw data to publishing a final model with a web interface.

Workflow

• Data Import into BayesiaLab.
• Discretization of continuous variables.
• Definition of variable classes.
• Supervised Learning using the Markov Blanket and Augmented Markov Blanket algorithms.
• Structural Coefficient Analysis for Bayesian network model optimization.
• Network Performance Analysis with regard to one or multiple Target Nodes (e.g., Stenosis of LAD, LCX, or RCA).
• Introduction to information-theoretic concepts such as Entropy and Mutual Information.
• 2D Mapping to illustrate Mutual Information between variables and Target Nodes.
• Computation of an interactive and dynamic Adaptive Questionnaire for optimized evidence-seeking with regard to the diagnosis.
• Introduction of the cost of diagnostic procedures for optimization, i.e., trading off the cost of information gain versus the expected reduction of uncertainty.
• Computation of a Target Interpretation Tree as a static decision support tool.
• Publication of the Adaptive Questionnaire to the BayesiaLab WebSimulator as a decision support tool for external users.

Presentation Video

References

• Cardiovascular Imaging Department, Rajaei Cardiovascular, Medical & Research Center, Iran University, Tehran, Iran
  • Updated (Extended) Dataset: https://www.researchgate.net/publication/311582821_extention_of_Z-Alizadeh_sani_dataset (opens in a new tab)
  • Original (Limited) Dataset: https://archive.ics.uci.edu/ml/datasets/Z-Alizadeh+Sani (opens in a new tab)