A hybrid model for classification of medical data set based on factor analysis and extreme learning machine: FA + ELM

•A hybrid model based on Factor Analysis (FA) and Extreme Learning Machine (ELM) was proposed in this study for diagnosing breast cancer, Lymphography, and erythemato-squamous diseases.•The best success rate achieved by classifying the DERM dataset directly using ELM was determined as 100%, while the highest success rate achieved after preprocessing with FA did not change. However, the average success rate achieved after preprocessing of DETM dataset with FA increased from 96.39% to 96.94%.•The highest success rate achieved by classifying the LYMP dataset directly using ELM was determined as 90.00 %, while the result obtained using FA + ELM as 93.33 %. FA increased the average success rate from 84.50 % to %85.10.•The best success rate achieved for the Wisconsin breast cancer data set using ELM and FA + ELM was 99.27 %. However, FA increased the average success rate from 97.10 % to 97.25 %.•In all datasets, higher success rates were obtained using FA despite decreasing the dimension (size) of attributes.•As a result, important conclusions were obtained in classifying medical data using the hybrid model based on factor analysis and the extreme learning machine proposed in this study. The proposed method will be helpful in the decision-making stage in medical diagnosis systems. Data mining techniques such as classification, clustering, and prediction are used extensively for medical diagnosis in epidemiological fields. A hybrid model based on Factor Analysis (FA) and Extreme Learning Machine (ELM) was proposed in this study for diagnosing breast cancer, Lymphography, and erythemato-squamous diseases. The proposed hybrid model consists of two stages. Firstly, FA was used for preprocessing the medical dataset, and then, the factors obtained using FA were used as input features for the ELM model. Dermatology, Lymphography, and Wisconsin Breast Cancer real datasets obtained from the UCI machine learning database were used to test the proposed model. An average success rate of 96.39 % and 96.94 % was obtained after classifying the dermatology dataset with ELM and FA + ELM models. While the success rate obtained by classifying the lymphography data set using ELM is 84.50 %, the result obtained with FA + ELM is 85.10 %. The success rates of 97.10 % and 97.25 % are achieved respectively for Wisconsin Breast Cancer (WBC) using ELM and FA + ELM. As a result, it was observed that preprocessing of the data increased the average classification success in three different m