Towards Artificial Neural Network Model To Diagnose Thyroid Problems

Medical diagnosis can be viewed as a pattern classification problem: based a set of input features the goal is to classify a patient as having a particular disorder or as not having it. Thyroid hormone problems are the most prevalent problems nowadays. In this paper an artificial neural network approach is developed using a back propagation algorithm in order to diagnose thyroid problems. It gets a number of factors as input and produces an output which gives the result of whether a person has the problem or is healthy. It is found that back propagation algorithm is proved to be having high sensitivity and specificity. I. I NTRODUCTION edical decision making has become very essential nowadays because of the awareness of various health problems. It can be viewed as a pattern recognition problem whereby various patterns are recognized in order to arrive at a conclusion(1). A group of causing factors of a particular disease or problem is given as inputs. Based on the given input values a decision will be arrived. The decision making can be done using an artificial neural network approach. In this paper thyroid hormonal problems are diagnosed using an artificial neural network approach. The back propagation learning algorithm is used to train the neural network. The efficiency of the network is analyzed. It is concluded to enhance the algorithm for still better results. This paper is organized as sections as follows: Section II discusses about medical decision making and it's advantages. Section III introduces about thyroid problems due to hormonal activities. Section IV gives brief explanation about neural networks. Section V gives the steps to construct a neural network for thyroid diseases diagnosis. Section VI analyses the given back propagation algorithm. Section VII concludes the article giving future directions.