Diagnosis and Severity of Depression Disease in Individuals with Artificial Neural Networks Method

Authors

DOI:

https://doi.org/10.18201/ijisae.2021.234

Keywords:

Depression, Artificial Neural Network, Optimization

Abstract

Depression is a disease that causes physiological and psychological problems. Depression in individuals; sleep disturbance, constant fatigue, anorexia, inability to do daily activities, and feeling constantly tired and tired. Among the causes of depression; sociological, biological and psychological conditions are counted. The first step in treating depression is to make the correct diagnosis. Beck Depression Inventory (BDI) is a self-report scale developed by Beck et al. (1961) that evaluates the severity of depressive symptoms and the risk of depression, and consists of 21 questions in total. The purpose of BDI is not to define a diagnosis of depression, but to objectively quantify the degree of depression. The aim of this study is to determine the most successful algorithm from artificial neural network algorithms by using a data set of BDI scale. In this study, Random Forest, Decision Tree, Naive Bayes and Neural Network methods were used within the scope of algorithms and the best results; The training rate was 99.9%, the test rate was 98.5%, and the loss rate was 0.1% for training and 1.5% for testing. The lowest rates were obtained with the "Decision Tree" technique, with 90.8% training and 87.1% test rates. In addition, different results were obtained with Adam, SGD and L-BFGS-B optimizations used in ANN algorithms and the best success percentage was obtained as a test result in Adam technique.

Downloads

Download data is not yet available.

Downloads

Published

25.05.2021

How to Cite

[1]
R. Butuner and H. Yuksel, “Diagnosis and Severity of Depression Disease in Individuals with Artificial Neural Networks Method”, Int J Intell Syst Appl Eng, vol. 9, no. 2, pp. 55–63, May 2021.

Issue

Section

Research Article