Medical diagnosis using neural network

TL;DR

This paper introduces the MFNNCA, a new neural network algorithm that incrementally constructs minimal architectures for medical diagnosis, outperforming human diagnostic accuracy on benchmark problems.

Contribution

The paper presents a novel constructive algorithm for neural networks that optimizes architecture size and accuracy for medical diagnosis tasks.

Findings

MFNNCA produces near-minimal neural networks.

The algorithm achieves high accuracy on cancer, heart disease, and diabetes datasets.

Neural diagnostic systems outperform human capabilities.

Abstract

This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. This paper describes a modified feedforward neural network constructive algorithm (MFNNCA), a new algorithm for medical diagnosis. The new constructive algorithm with backpropagation; offer an approach for the incremental construction of near-minimal neural network architectures for pattern classification. The algorithm starts with minimal number of hidden units in the single hidden layer; additional units are added to the hidden layer one at a time to improve the accuracy of the network and to get an optimal size of a neural network. The MFNNCA was tested on several benchmarking classification problems including the cancer, heart disease and diabetes. Experimental results show that the MFNNCA can produce optimal neural network architecture with good generalization ability.