HEART_DISEASE_PREDICTION for roll CES.pptx

Notes

1. HEART DISEASE PREDICTION USING PYTHON Presented By: Presented To: Harsh Singh(2155026) Mr. Pravin Kumar Pandey Himanshu Singh(2155027) Dr. Divyendu Kumar Mishra ( B.Tech , 4 th Year, C.S.E.) (Assistant Professor) Department of Computer Science & Engineering Faculty of Engineering & Technology ( Uma Nath Singh Institute of Engineering & Technology) Veer Bahadur Singh Purvanchal University, Jaunpur

2. INTRODUCTION This project focuses on developing a machine learning model to predict heart disease using historical health data and other existing factors. The main aim of heart disease prediction using Machine Learning (ML) is to develop a predictive model that can accurately identify individuals at high risk of developing heart disease.

3. PROPOSED SYSTEM FLOW DIAGRAM Input Data: The meaning of Input data is to access the data set from Kaggle. Data preprocessing: The main step is preparing the dataset. This includes: Handling missing values, filling in or replacing any missing data so the analysis can proceed without gaps. Data Splitting: Data Splitting is the process of split the data set into the Training data and Testing data. Modeling: The goal of modeling in machine learning is to identify patterns, trends, and correlations within data.

4. PROGRESS IN WORK We divide our work of project into four objective. Which are as follows:- Objective#1 : Perform the data collection . Objective#2 : Perform the data pre-processing and clean data, remove the noise. Objective#3 : Splitting the dataset into training and testing data and trained the model using different ML algorithm. Objective#4 : Compare the model accuracy using different ML algorithms.

5. FEATURE OF DATASET Age Gender Chest Pain Blood Pressure Cholestoral Blood Sugar Maximum heart rate achieved etc..

6. CURRENT PROGRESS Completed Objective: Objective#1&2 is completed. The dataset of heart disease is obtained from online dataset on Kaggle. This include the 13 feature and 303 rows. Pre-processing method are applied on dataset in order to remove the noise. Split the dataset into the training data and testing data in order to apply the machine learning algorithms. First we apply Logistic Regression Algorithm and we found that model the accuracy score is 82%. Under Progree : Objective#3: Splitting the dataset into training and testing data and trained the model using different ML algorithm. Objective#4: Compare the model accuracy using different ML algorithms.

7. Thank You