ISSUES

<Journal> </Journal>

<ArticleTitle>A Decision Support System Based on Neural Network and Genetic Algorithm: Case Study of Breast Cancer</ArticleTitle>

<FirstPage>375</FirstPage>

<LastPage>375</LastPage>

<ELocationID>10.30699/fhi.v11i1.375</ELocationID>

<Language>EN</Language>

<AuthorList> </AuthorList>

<History> </History>

<Abstract>Introduction: Artificial intelligence is changing the way healthcare is provided in many high-risk environments or areas with poor healthcare facilities. The emergence of epidemics and new diseases, and the crucial role of early diagnosis in prevention and adoption of more effective treatments has highlighted the need to design accurate and self-organized Clinical Decision Support Systems (CDSSs).Materials and Methods: In this study, a CDSS based on a multi-layer perceptron and genetic algorithm is proposed. Due to the dependence of neural network (NN) efficiency on its parameters as well as the need for knowledge professionals in the face of new data in order to fine-tune the parameters, a new chromosomal structure is proposed to determine the optimal NN structure including the number of layers and neurons. The goal is to increase the reusability of the model and ease of use by health professionals.Results: To evaluate the performance of the model, two standard breast cancer (BC) datasets, WBC and WDBC, were used. The model uses 70% of the data set for training and the remaining equally for evaluation and testing. The accuracy of the proposed model on 15% of WBC and WDBC datasets was 98.51 and 97.55%, respectively.Conclusion: The proposed chromosomal structure is able to derive optimal NN structures. In according to the high classification accuracy of the model in the diagnosis of BC and provideing the different structures in accordance with the hardware implementation considerations, the proposed model can be used effectively in the diagnosis of other diseases.</Abstract>