Analysing Risk of Coronary Heart Disease through Discriminative Neural Networks

TL;DR

This paper proposes a discriminative neural network approach using Siamese architecture and contrastive loss to effectively handle class imbalance in binary medical diagnostics, specifically for coronary heart disease risk analysis.

Contribution

It introduces a novel distance-based neural network model that addresses class imbalance in binary classification tasks for medical diagnostics.

Findings

Effective handling of class imbalance in coronary heart disease data

Improved discrimination between positive and negative cases

Open-source code available for replication

Abstract

The application of data mining, machine learning and artificial intelligence techniques in the field of diagnostics is not a new concept, and these techniques have been very successfully applied in a variety of applications, especially in dermatology and cancer research. But, in the case of medical problems that involve tests resulting in true or false (binary classification), the data generally has a class imbalance with samples majorly belonging to one class (ex: a patient undergoes a regular test and the results are false). Such disparity in data causes problems when trying to model predictive systems on the data. In critical applications like diagnostics, this class imbalance cannot be overlooked and must be given extra attention. In our research, we depict how we can handle this class imbalance through neural networks using a discriminative model and contrastive loss using a Siamese neural network structure. Such a model does not work on a probability-based approach to classify samples into labels. Instead it uses a distance-based approach to differentiate between samples classified under different labels. The code is available at https://tinyurl.com/DiscriminativeCHD/