A COMPARATIVE STUDY OF DEEP LEARNING-BASED SYSTEM INTERNET OF THINGS AND MANUAL SYSTEM IN HEALTHCARE APPLICATIONS IN NIGERIA.

Abstract

Healthcare in Nigeria continues to struggle with slow diagnosis, poor data handling, and limited 
patient monitoring, especially in busy or underserved hospitals. This study compares the current 
manual healthcare system with a deep learning–based Internet of Things (DL-IoT) model to 
determine how technology can improve service delivery. Performance was measured based on 
diagnostic accuracy, speed of disease detection, data management, patient monitoring, cost, 
scalability, and decision support. The results show major improvements with the deep learning
based Internet of Things system. Diagnostic accuracy rose from 75% to 96%, while data handling 
and analysis improved by over 350%. Remote monitoring also became far more efficient, helping 
doctors respond faster to patient needs. These improvements support early disease detection, 
reduce clinical workload, and improve patient outcomes, particularly for chronic health conditions. 
However, deploying this technology in Nigeria faces challenges such as unstable digital 
infrastructure, cybersecurity concerns, high setup costs, and low technology awareness in rural 
areas. With strong government support and investment in digital health, deep learning–based 
Internet of Things can play a vital role in transforming healthcare in Nigeria by making services 
faster, smarter, and more accessible for everyone.