Research Article
A Pneumonia Diagnosis Scheme Based on Hybrid Features
Extracted from Chest Radiographs Using an Ensemble
Learning Algorithm
Mehedi Masud ,
1
Anupam Kumar Bairagi ,
2
Abdullah-Al Nahid ,
3
Niloy Sikder ,
2
Saeed Rubaiee ,
4
Anas Ahmed ,
4
and Divya Anand
5
1
Department of Computer Science, College of Computers and Information Technology, Taif University, P.O. Box 11099,
Taif 21944, Saudi Arabia
2
Computer Science and Engineering Discipline, Khulna University, Khulna 9208, Bangladesh
3
Electronics and Communication Engineering Discipline, Khulna University, Khulna 9208, Bangladesh
4
Department of Industrial and Systems Engineering, University of Jeddah, P.O. Box: 80327, Jeddah 21589, Saudi Arabia
5
Department of Computer Science and Engineering, Lovely Professional University, Punjab 144411, India
Correspondence should be addressed to Mehedi Masud; mmasud@tu.edu.sa
Received 4 January 2021; Revised 6 February 2021; Accepted 10 February 2021; Published 26 February 2021
Academic Editor: Dilbag Singh
Copyright©2021MehediMasudetal.isisanopenaccessarticledistributedundertheCreativeCommonsAttributionLicense,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Pneumonia is a fatal disease responsible for almost one in five child deaths worldwide. Many developing countries have high
mortality rates due to pneumonia because of the unavailability of proper and timely diagnostic measures. Using machine learning-
baseddiagnosismethodscanhelptodetectthediseaseearlyandinlesstimeandcost.Inthisstudy,weproposedanovelmethodto
determinethepresenceofpneumoniaandidentifyitstype(bacterialorviral)throughanalyzingchestradiographs.Weperformeda
three-classclassificationbasedonfeaturescontainingdiverseinformationofthesamples.Afterusinganaugmentationtechniqueto
balance the dataset’s sample sizes, we extracted the chest X-ray images’ statistical features, as well as global features by employing a
deep learning architecture. We then combined both sets of features and performed the final classification using the RandomForest
classifier.Afeatureselectionmethodwasalsoincorporatedtoidentifythefeatureswiththehighestrelevance.Wetestedtheproposed
method on a widely used (but relabeled) chest radiograph dataset to evaluate its performance. e proposed model can classify the
dataset’s samples with an 86.30% classification accuracy and 86.03% F-score, which assert the model’s efficacy and reliability.
However, results show that the classifier struggles while distinguishing between viral and bacterial pneumonia samples. Imple-
menting this method will provide a fast and automatic way to detect pneumonia in a patient and identify its type.
1. Introduction
Pneumonia refers to severe inflammation caused by infec-
tions inside the lungs, which are crucial organs of the re-
spiratory system. ese infections can be caused by several
infectiousagents,includingbacteria,viruses,andfungi,and
can occur in one or both lungs. ese infections fill the
minusculeair-sacsinsidethelungs(calledalveoli)withfluid
and pus, restricting them to get oxygen-rich air that we
breathe in. As a result, breathing for the patient becomes
increasinglydifficultandpainful.Apneumoniapatientmay
also experience other symptoms such as fever, dry cough,
vomiting, exhaustion, and chest pain [1]. e effects of
pneumonia can range from mild infections to lethal organ
failure, depending on the severity of the condition, the
patient’s age, and his/her immune system. Apart from in-
fants and toddlers, people with asthma, diabetes, chronic
obstructive pulmonary disease (COPD), sickle cell disease,
the history of other heart-related problems, and smoking
habit have a higher chance of getting pneumonia.
Every year pneumonia kills more than two million
people worldwide, most of whom are children under five
Hindawi
Journal of Healthcare Engineering
Volume 2021, Article ID 8862089, 11 pages
https://doi.org/10.1155/2021/8862089