Work

Improving Machine Learning Classification Models for Anaemia Type Prediction by Oversampling Imbalanced Complete Blood Count Data With Smote-based Algorithms

Year: 2024

Type: article

Abstract: Computer-assisted disease diagnosis is cost-effective and time-saving, increasing accuracy and reducing the need for an additional workforce in medical decision-making. In our prior research, we trained, tested, and compared the accuracies of nine optimizable classification models to diagnose and predict eight anaemia types from Complete Blood Count (CBC) data. This study aimed to improve these classification models by oversampling the original imbalanced dataset with four algorithms related to the Synthetic Minority Over-sampling Technique (SMOTE). The results showed that the validation accuracy increased from 99.22% (Ensemble model) to 99.57% (Tree model), and most importantly, the False Discovery Rate (FDR) for the anaemia type with the highest FDR decreased from 23.1% to 1.5%.

Source: AD ALTA Journal of Interdisciplinary Research

DOI: 10.33543/j.1402.469475

Authors: LADISLAV VÉGH, NORBERT ANNUŠ, KRISZTINA CZAKÓOVÁ, ONDREJ TAKÁČ

Institution: J. Selye University

Language: English

Topic: Imbalanced Data Classification Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: diamond

Funder: Kultúrna a Edukacná Grantová Agentúra MŠVVaŠ SR