A Novel Hybrid Machine Learning-Based System Using Deep Learning Techniques and Meta-Heuristic Algorithms for Various Medical Datatypes Classification

Sep 17, 2026

Uploaded by Himbo

Medicine benefits from rapid advances in computer science, especially when immediate diagnosis is needed to improve patient outcomes. This work presents a hybrid machine learning framework for categorizing medical images by combining deep learning models with a meta-heuristic feature-selection strategy. Two datasets are used: MRI brain tumor images and chest X-rays for COVID-19. CNN or autoencoder feature extraction is coupled with particle swarm optimization to select optimal features, reducing dimensionality while preserving performance. Classification results include up to 99.76% for COVID-19 (CNN-PSO-SVM) and 99.51% for brain tumors (autoencoder-PSO-KNN).

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages25

Reading Time1 h 3 min

AccessFree to download

Abstract

Introduction

diagnostics Article A Novel Hybrid Machine Learning-Based System Using Deep Learning Techniques and Meta-Heuristic Algorithms for Various Medical Datatypes Classification Yezi Ali Kadhim 1,2,3, Mehmet Serdar Guzel 4 and Alok Mishra 5,6, * Citation: Kadhim, Y.A.; Guzel, M.S.; Mishra, A. A Novel Hybrid Machine Learning-Based System Using Deep Learning Techniques and MetaHeuristic Algorithms for Various Medical Datatypes Classification. Diagnostics 2024, 14, 1469. [https://](https://)[ ](https://)[doi.org/10.3390/diagnostics14141469](doi.org/10.3390/diagnostics14141469) Academic Editors: Menaka Radhakrishnan, Karthik Ramamurthy and Daehan Won Received: 22 May 2024 Revised: 27 June 2024 Accepted: 2 July 2024 Published: 9 July 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 College of Engineering, University of Baghdad, Jadriyah, Baghdad 10071, Iraq; [eng.yeziali@yahoo.com](eng.yeziali@yahoo.com) 2 Department of Modeling and Design of Engineering Systems (MODES), Atilim University, Ankara 06830, Turkey 3 Department of Electrical and Electronics Engineering, Atilim University, Incek, Ankara 06830, Turkey 4 Department of Computer Engineering, Ankara University, Yenimahalle, Ankara 06100, Turkey; [mehmet.serdar.guzel@ankara.edu.tr](mehmet.serdar.guzel@ankara.edu.tr) 5 Faculty of Engineering, Norwegian University of Science and Technology, 7034 Trondheim, Norway 6 Department of Software Engineering, Atilim University, Incek, Ankara 06830, Turkey * Correspondence: [alok.mishra@ntnu.no](alok.mishra@ntnu.no) Abstract: Medicine is one of the fields where the advancement of computer science is making significant progress. Some diseases require an immediate diagnosis in order to improve patient outcomes. The usage of computers in medicine improves precision and accelerates data processing and diagnosis. In order to categorize biological images, hybrid machine learning, a combination of various deep learning approaches, was utilized, and a meta-heuristic algorithm was provided in this research. In addition, two different medical datasets were introduced, one covering the magnetic resonance imaging (MRI) of brain tumors and the other dealing with chest X-rays (CXRs) of COVID-19 . These datasets were introduced to the combination network that contained deep learning techniques, which were based on a convolutional neural network (CNN) or autoencoder, to extract features and combine them with the next step of the meta-heuristic algorithm in order to select optimal features using the particle swarm optimization (PSO) algorithm. This combination sought to reduce the dimensionality of the datasets while maintaining the original performance of the data. This is considered an innovative method and ensures highly accurate classification results across various medical datasets. Several classifiers were employed to predict the diseases. The COVID-19 dataset found that the highest accuracy was 99.76% using the combination of CNN-PSO-SVM. In comparison, the brain tumor dataset obtained 99.51% accuracy, the highest accuracy derived using the combination method of autoencoder-PSO-KNN. Keywords: deep learning; autoencoder; classification; medical dataset; COVID-19; brain tumor; meta-heuristic algorithm 1. Introduction Medicine, the cornerstone of healthcare, is pivotal in improving and sustaining human health. It encompasses a vast array of disciplines, from preventive care to sophisticated treatment modalities, all of which are aimed at enhancing the quality of life. In recent times, the focus on medicine combined with computer science has intensified in order to save time and effort and delve deeper into

FAQs

What datasets are used for disease classification?

The method evaluates two medical datasets: MRI images for brain tumors and chest X-ray images for COVID-19.

How does the hybrid system select features?

Deep learning models (CNN or autoencoder) extract features, which are then combined with a particle swarm optimization meta-heuristic to select optimal features.

What classification accuracy is reported for COVID-19 and brain tumors?

COVID-19 reaches a highest accuracy of 99.76% with CNN-PSO-SVM, while the brain tumor dataset reaches 99.51% with autoencoder-PSO-KNN.

Sep 17, 2026

Uploaded by Himbo