Page 61 - FULL REPORT 30012024

Figure 2.14 User interface of the web project
(Source: Bhat, 2021)

2.9.2 Cardio Vascular Disease Prediction Using Machine Learning

Web Application

This project focuses on predicting cardiovascular disease using a dataset from

the Cleveland data set of UCI store of coronary illness patients available in
Kaggle. Moreover, it involves several essential steps, including data

collection, pre-processing, feature selection, classification algorithms, and

performance evaluation. The dataset comprises 303 occurrences, 14
attributes, and one objective quality. During pre-processing, missing values,

corrupted data, and inconsistencies are addressed. Furthermore, feature
selection is performed to identify the most relevant elements for the

classification algorithms.

Additionally, the project utilizes the K-Nearest Neighbour (KNN) algorithm
for prediction, and the performance of the algorithms is evaluated based on

accuracy, precision, recall, and F-measure. To enhance user interaction, a

web application is implemented using Flask and deployed on Heroku. The
application allows individuals to assess their risk of heart disease and obtain

timely predictions. Figure 2.15 shows the performance result obtained for

KNN algorithm and figure 2.16 depicts the front end of the web application.

44