Olukemi V. Olatunde et al, International Journal of Computer Science and Mobile Computing, Vol.13 Issue.4, April- 2024, pg. 59-67 © 2024, IJCSMC All Rights Reserved, ZAIN Publications, Fridhemsgatan 62, 112 46, Stockholm, Sweden 59 Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320–088X IMPACT FACTOR: 7.056 IJCSMC, Vol. 13, Issue. 4, April 2024, pg.59 – 67 Unlocking Pneumonia Severity Diagnosis with Deep Learning Olukemi V. Olatunde 1 ; Olumide S. Adewale 2 ; Oladunni A. Daramola 3 ¹Software Engineering Department, Federal University of Technology, Akure, Nigeria ²Department of Computer Science, Federal University of Technology, Akure, Nigeria ³Department Information Technology, Federal University of Technology, Akure, Nigeria 1 kftaiwo@futa.edu.ng; 2 adewale@futa.edu.ng; 3 oadaramola@futa.edu.ng DOI: https://doi.org/10.47760/ijcsmc.2024.v13i04.007 Abstract— Pneumonia is a form of acute respiratory infection that affects the lungs. The lungs are made up of small sacs called alveoli, which is normally fill with air in a healthy person, but filled with pus and fluid in an individual with pneumonia thereby reduces oxygen intake and making breathing difficult Pneumonia is a fatal and leading cause of morbidity and mortality worldwide, especially among children five years and below; and the elderly 65 years and above especially those with weakened immune systems. Pneumonia can be caused by bacteria, virus, and fungi, and the severity ranges from mild to severe depending on the causative agent and the duration of the infection. Early diagnosis, particularly knowing the severity level of Pneumonia gains a paramount importance for saving lives. Medical diagnosis using artificial intelligence (AI) systems, is currently an active research area in medicine widely used in biomedical systems. Deep learning, a subset of Artificial intelligence provides a powerful tool that assist medical experts to analyze, model, and make sense of complex clinical image data across a broad range of medical applications. This paper proposes a deep learning technique of classifying X-ray images of pneumonia patients into their severity classes. Keywords— Pneumonia, Severity, Deep Learning, Medical Diagnosis, Artificial Intelligence I. INTRODUCTION Pneumonia is a potentially life-threatening respiratory illness and a major global health issue characterized by inflammation of the lungs, impacting people across all age groups and leading to high rates of illness and death worldwide. It is a form of acute respiratory infection that affect either one or both lungs. The lungs are made up of small sacs called alveoli, which is normally fill with air in a healthy person, but filled with pus and fluid in an individual with pneumonia thereby reduces oxygen intake and making breathing difficult. Pneumonia is a fatal and leading cause of morbidity and mortality worldwide, especially among the vulnerable; children five years and below, and the elderly 70 years and above especially those with weakened immune systems. Pneumonia can be caused by bacteria, virus, and fungi, and the severity ranges from mild to severe depending on the causative agent and the duration of the infection. Fig. 1 shows the global death rate from year 2000 to 2019.