TITLE:
Risk Factor Hypertension Prediction Model
AUTHORS:
Vercus Ntirandekura, Jeremie Ndikumagenge
KEYWORDS:
Artificial Intelligence, Machine Learning, Prediction, Gradient Descent, Hypertension, Cardiovascular Disease
JOURNAL NAME:
Journal of Applied Mathematics and Physics,
Vol.11 No.2,
February
13,
2023
ABSTRACT: According to the 2020 Ministry of Health reports, the public health sector is facing an acute shortage of logistical resources and qualified competent human resources, as evidenced by the doctor-to-hospital ratio in relation to population [1]. Aside from these structural and cyclical issues, the above ratios are even lower in rural areas with low incomes. Underdevelopment is a major impediment to establishing a normal public health situation, though the Burundian government is working hard to ensure that it is at an acceptable level. Furthermore, some Burundian traditions, customs, and practices are undermining efforts to build an international-standard public health facility. Indeed, the mental state of a people (tradition, culture, and practices) has a significant impact on the fluctuation of risk factors in public health. It is determined by the socioeconomic development and sociocultural behavior of the population. This demonstrates that hypertension is a public health concern in Burundi. Unfortunately, the vast majority of people are completely unaware of the risks that high blood pressure poses to public health. High blood pressure, on the other hand, has always been a key physiological measure in medical examinations, serving as one of the most important biological markers in clinical evaluation. As a result, cardiovascular diseases caused by high blood pressure have a significant impact on mortality worldwide, particularly in Burundi. Predicting high blood pressure based on risk factors can help to reduce complications associated with this disease, which is known as a silent killer. The digital era provides a variety of tools for studying, analyzing, managing, and monitoring the risk factors that contribute to and degenerate high blood pressure. The primary goal of this work is to create a decision-making tool based on the outcomes of high blood pressure epidemic and/or pandemic predictions from sanitarian districts. The current paper work employs a prediction support tool created using linear regression methods from machine learning, one of the fields of artificial intelligence. It is especially useful for optimizing the cost function. The latter allows the predicted values to be determined and defined using the gradient descent algorithm.