Cardiovascular diseases (CVDs) are the number 1 cause of death globally, taking an estimated 17.9 million lives each year, which accounts for 31% of all deaths worlwide.
Heart failure in particluar is a common event caused by CVDs; it is a chronic, progressive condition in which the heart muscle is unable to pump enough blood to meet the body’s needs for blood and oxygen. Most cardiovascular diseases can be prevented by addressing behavioural risk factors such as tobacco use, unhealthy diet and obesity, physical inactivity and harmful use of alcohol using population-wide strategies. People with cardiovascular disease or who are at high cardiovascular risk (due to the presence of one or more risk factors such as hypertension, diabetes, hyponatremia or already established disease) need early detection and management.
The proposed work addresses this compelling problem with an application of a Bayesian Network for medical diagnosis and prediction which has its main advantage in its explainability and readability. In particular, both causes and effects of cardiovascluar problems are take into consideration in the Network, in order to be able to prevent and detect those situations in high risk population, given factors such as: gender, age, unhealthy habits and relevant levels of chemical elements in human blood.
The report is organized as follows:
- a brief descrpition of the dataset used and the data manipulation process done
- a detailed view of the Bayesian Network (with emphasis on both the analysis of its structure and the parameter learning process)
- examples of inferences on the network (with particluar emphasis on the number of different methods used to address the inference process)
- a narrow view on some highly relevant queries and conclusion thoughts related