A Medical Modelling Using Multiple Linear Regression

Prediction of anemia with a particle swarm optimization-based approach

“…The dataset has been prepared from observations of anemia disease. The dataset that consists of the anemia measurements contains 5 classes and 539 subjects provided from the literature [9], [11], [12] whose main concerns are creating mathematical models that can predict the type of anemia based on various blood variables by only specific algorithms while in the current study, a hybrid algorithm has been developed using pathological individuals from a population and their corresponding blood variables. The data has been collected from individuals between aged 6 to 56 years.…”

“…In the literature, there have been several methods [8][9][10][11][12][13][14][15][16] to analyze anemia types. Besides to their notable advantages, many common properties, such as being costly, difficulty in usage, timeconsuming and having constraints in daily usage, lead to their drawbacks.…”

“…In this work, the hybrid algorithm of PSO with another important optimization algorithm, support vector machine (SVM), has been created to predict types of anemia. To the best of the authors' knowledge, this is the first time a combination of PSO and SVM has been used to forecast anemia types using biological data, despite the fact that certain conventional methods are utilized for evaluating anemia types in the literature [7][8][9][10][11][12][13][14][15]. The PSO-SVM algorithm has been suggested for reliable data treatment and further analysis for interpretation due to its high level of flexibility and lack of requirement for specialized knowledge in statistics [25][26][27].…”