Comparing learning algorithms in neural network for diagnosing cardiovascular disease

TL;DR

This paper evaluates nine neural network learning algorithms for diagnosing cardiovascular diseases, comparing their accuracy, sensitivity, transparency, AROC, and convergence rate using cross-validation.

Contribution

It provides a comparative analysis of nine neural network algorithms specifically for cardiovascular disease diagnosis, highlighting the best performers in various metrics.

Findings

Lonberg-M has the best training efficiency across metrics

OSS achieves the highest accuracy in testing phase

SCG offers maximum transparency

Abstract

Today data mining techniques are exploited in medical science for diagnosing, overcoming and treating diseases. Neural network is one of the techniques which are widely used for diagnosis in medical field. In this article efficiency of nine algorithms, which are basis of neural network learning in diagnosing cardiovascular diseases, will be assessed. Algorithms are assessed in terms of accuracy, sensitivity, transparency, AROC and convergence rate by means of 10 fold cross validation. The results suggest that in training phase, Lonberg-M algorithm has the best efficiency in terms of all metrics, algorithm OSS has maximum accuracy in testing phase, algorithm SCG has the maximum transparency and algorithm CGB has the maximum sensitivity.