A review on diagnosis of chronic obstructive pulmonary disease

Abstract

Chronic obstructive pulmonary disease is a significant state that leads to progressive airflow obstruction and subsequent irreversible damage to the airways. It is a major factor causing death and has a very high mortality rate worldwide. In recent years, the mortality rate has increased due to Chronic obstructive pulmonary disease (COPD) and it is estimated to increase in the coming years. This paper reviews the emerging techniques using these technologies that can be used to detect and monitor the severity of chronic obstructive pulmonary disease. The Internet of Things can help to detect and monitor the condition of a patient suffering from chronic obstructive pulmonary disease using sensors which are used to measure a particular parameter like concentration of different gases present in the exhaled breath and ensure that his condition doesn’t get worse. Using an Artificial Intelligence and Machine Learning based approach, a system can be developed where the data is collected from sensors, followed by pre-processing and feature extraction for further estimation using a model to identify a person suffering from this disease. The conventional methods used by medical practitioners for the detection of this disease are expensive, time consuming as a lot of tests are to be performed and can cause exposure to radiation. Therefore, research has been carried out in recent years to find other ways to detect this disease. It has been found that with the help of advancing technologies such as Internet of Things, Artificial Intelligence, Machine Learning and Signal processing techniques, it is possible to develop an easy, fast, non-invasive and cost-effective system that would help to diagnose and detect this disease and provide accurate results.