Developing a Smart Health Monitoring System Using Machine Learning Techniques

Abstract

Today more than half of the world’s population lives in cities with more than six devices per person connected to the Internet. This implies that billions of devices and systems are embedded in a city’s infrastructure, which is called today a smart city. The current healthcare system faces significant challenges in providing quality and low-cost healthcare services. These challenges are also aggravated by the increasing elderly population, which translates into a higher demand for healthcare services. Moreover, it is difficult in some cities to obtain a proper healthcare service due to limited resources. Due to this, the current healthcare system needs to evolve into a smart healthcare system. Smart healthcare is a concept involving various entities and technologies, including: sensors, wearable devices, Information Communication and Technology (ICT) and much more.

One of the ICT devices is the Intensive Care Unit (ICU) equipment. It includes patient monitoring, respiratory and cardiac support, pain management, emergency resuscitation devices, and other life support equipment. This equipment is designed to care for patients who are seriously injured, have a critical or life-threatening illness, or have undergone a major surgical procedure, thereby requiring 24-hour care and monitoring. Sepsis is a major cause of mortality and morbidity in ICUs. Sepsis remains a major health problem in ICU patients worldwide and is associated with high mortality rates. However, there is vast variability in the sepsis rates and outcomes for ICU patients around the world. Sepsis prediction is a challenging problem and remains so despite many years of research because its appearance is often unclear until later stages.