A comprehensive study on thyroid diagnosis by neural networks and swarm intelligence

Makas, Hasan; Yumuşak, Nejat

doi:10.1109/icecco.2013.6718258

Cited by 7 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Razia and Narasinga Rao [9] have explored the neural network models which describe the aspects related to thyroid gland functionality, autoimmune condition and various conditions of thyroid disease. Makas and Yumusak [3] have designed multi-layer neural network (MLNN), learning vector quantization (LVQ) network, probabilistic neural network (PNN), general regression neural network (GRNN), Elman neural network (ENN), focused time delay neural network (FTDNN) and cascade feed-forward neural network (CFNN) to diagnose the thyroid disease. They were able to increase the accuracy of these networks by only creating suitable training data subsets and using proper network topologies and network parameters.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Hence, it will consume more time for diagnosing the thyroid function abnormalities. Therefore, to save the precious time of the patient and even the physician, a computer aided diagnosis system will be more useful which can provide a guidance to the physicians in the diagnosis process [3]. One reason for medication errors is inadequate decisions in primary care and hospital settings.…”

Section: Introductionmentioning

confidence: 99%

“…Both types of the models have precision closer to 1 which means that there is perfect precision. In the study by(Makas and Yumusak (2013), they have reported the accuracy values between 98% and 99% for all the neural network models developed. This study shows that Scaled Conjugate Gradient algorithm gives higher accuracy rates.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Decision Support for Diagnosing Thyroid Diseases using Machine Learning

Jayamini¹,

Weerasinghe²

2021

IJSRP

View full text Add to dashboard Cite

This research was carried out to compare the applicability of machine learning techniques in a way to support decision making in Thyroid disease diagnosis. In this research work, two types of machine learning algorithms; Multilayer perceptron Neural Network with Back-propagation and Random Forest were used, and a comparison of their performance was done to identify the most suitable machine learning algorithm which can be used to assist the diagnostic process of Thyroid diseases. Each of the models developed under the two machine learning techniques were trained and tested using two thyroid datasets from the UCI machine learning repository. The performance of the models was evaluated using the performance measures, Accuracy (%), Mean Absolute Error, Root Mean Squared Error, True Positive rate, False Positive rate, Precision and Recall.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%