Transitional case study of pulmonary tuberculosis using Markov chains

Abstract

Probability theory aims to study the probabilistic laws of many-occurring random events of the same type.
Knowing the probabilistic laws followed by many random accidents allows for prediction, hence the Markov process was of great importance from an applied point of view in studying and interpreting these accidents.
In this study, Markov chains were used, which is a special case of the Markov process, as it was based on the fact that the phenomenon moves from one state to another depending on certain probability laws called Transition probability.
The subject of the study is characterized by the transmission of the disease from one case to another among the three cases, which is pulmonary tuberculosis (within the lung) and its three transmissions. The third is all these cases with bloody sputum and a decrease in the patient's immunity, so the best representation of the process of pulmonary tuberculosis and its three transmissions is the use of Markov chains, and among the most important conclusions reached, the average number of cases of tuberculosis recorded the highest rate (2) compared to With other transformation processes as in Table No. (5), the path that may lead to the end of pulmonary tuberculosis (the finished case) represented by (M5) is about (51.13%) of the total cases.