Heart Disease Prediction using Machine Learning

Supervised By Prepared By
Nusrat Tabassum 1. Sanjida Akter Trisha (20103113)
Lecturer 2. Md Tanvir Ahammad (20103172)
Department of CSE
2
 INDEX
• Introduction
• Motivation
• Objective
• Literature review
• Methodology
• Dataset Attribute
• Proposed methodology
• Application
• Conclusion
• References
3
 INTRODUCTION
• Heart disease is considered as one of the major causes of death throughout the
world.
• The healthcare environment is still ‘information rich’ but ‘knowledge poor’.
• According to World Health Organization (WHO), heart related diseases are
responsible for the taking 17.7 million lives every year, 31% of all global
deaths.
• The goal is to extract the hidden patterns by applying data mining techniques
on the dataset, which are noteworthy to heart diseases and to predict the
presence of heart disease in patients where the presence is valued on a scale.

4
 MOTIVATION

• It is seen that about 17.7 million people die each year as a result of heart
disease.
• Heart disease may occur for different reason. They are:
• Hypertension, Diabetes, Dyslipidemia (Abnormal cholesterol), Smoking,
Family History, Obesity, Stress and existing clinical symptom which may
suggest underlying non detected IHD.
• We will analyze Bangladesh Heart Disease patient information .
• Minimize the cost of clinical tests .

5
 OBJECTIVE
Broad Objective: To collect the patient data, resource management data, and transformed data
and analyze the data Heart Disease patient of Bangladesh. Also find out the suitable Machine
Learning technique that is computationally efficient as well as accurate for the prediction of
heart disease.

Specific Objectives:

• Easy to use.
• No human intervention required.
• Not only detect the heart disease type but also suggest precautions.
• Efficient use of available annotated data samples.

6
 Literature review
ALGORITHMS USED AND
AUTHOR TITLE PURPOSE
ACCURACY
1)Mr.Santhana Prediction of Heart Disease In this system, a heart disease data set is Decision tree 91%
Krishnan.J, Using Machine Learning used. The main aim of this system is to Naive Bayes 87%
Dr.Geetha.S Algorithms Year-2018 predict the possibilities of occurring heart
disease of the patients in terms of
percentage. This is performed through data
mining classification techniques

2) M. Marimuthu, Analysis of Heart Disease To achieve better accuracy and to make the KNN 83.60% NB 80.66% Decision
S.Deivarani, Prediction using Various system more efficient so that it can predict tree 75.58%
Gayathri.R Machine Learning the chances of heart attack. SVM 65.56%
Techniques Year-2018

3)Sanchayita Dhar A Hybrid Machine In this paper, to develop a prediction system Naive Bayes Decision tree Random
Pritha Datta, Ankur Learning Approach for that be capable to envisage heart diseases Forest
Biswas, Tanusree Prediction of Heart based on measurements, are extracted from
Dey, Krishna Roy Diseases Year-2018 The ERIC laboratory consisting of 209 test
cases.

4)Rajesh N, T Prediction of Heart Disease In this paper, processing patient's dataset Naive Bayes Decision tree (ID3
Maneesha, Shaik Using Machine Learning and a data of patients to whom we need to Algorithm)
Hafeez, Hari Krishna Algorithms predict the chance of occurrence of a heart
TITLE Year-2018 disease.
7
 METHODOLOGY
• Python 3.7 programming language was used for building ML based heart disease prediction
system.

• Powerful software libraries supported by Python namely NumPy, Pandas, Seaborn,

Statsmodels.api, SciPy and Sklearn etc were used for exploratory analysis of data17.

• Implementing five ML algorithms namely k-Nearest Neighbours (k-NN), Naive Bayes

(NB), Logistic Regression (LR), AdaBoost (AB) and Random Forest (RF).

8
 Dataset Attribute
• There are 10 columns in the dataset, which are describe below:
1. Age: displays the age of individual.
2. Gender: displays the gender of individual using the following format:
1= male
2= female
3. Chest-type: displays the types of chest-pain experienced by the individual using the following
format:
1= typical angina
2= atypical angina
3= non angina pain
4= asymptotic
4. Resting Blood Pressure: displays the resting blood pressure value of individual in mmHg (unit)
5. Serum Cholesterol: displays the serum cholesterol in mg/dl (unit)
6. Fasting Blood Sugar: compares the fasting blood sugar value of an individual with 120mg/dl
if fasting blood sugar > 120mg/dl then : 1 (true)
else : 0 (false) 9
 Dataset Attribute (Continue)
7. Resting ECG: displays resting Electro Cardio Graphic result
0= normal
1= having ST-T wave abnormal
2= left ventricular hypertrophy
8. Max heart rate achieved: displays the max heart rate achieved by an individual.
9. Exercise induced angina: (1= yes ; 2= no).
10. Diagnosis of heart disease: displays whether the individual is suffering from heart disease
or not :
0= absence
1,2,3,4=present

10
 PROPOSED METHODOLOGY
Start

Collect Heart Disease Dataset

Extract Significant Variable

Data Preprocessing

Splitting Data

Training Data Testing data

(KNN, Naïve Bays,

Heart Disease
Logistic Regression,
AdaBoost, Random Classifier
Forest) Normal
11
 APPLICATION
Medical Institutions:
To show clinical understudies how the coronary episode been estimated, or how
to recognize that the individual is experiencing heart disease.
Hospitals:
To distinguish, that is the individual having heart disease or not.

12
 CONCLUSION
• Heart disease is one of the major concerns for society today.
• Heart disease prediction is challenging and very important in medical
field.
• It is difficult to manually determine the odds of getting heart disease
based on risk factors .
• However machine learning techniques are useful to predict the output
from existing data.

13
 REFERENCES
• [1] Effective heart disease prediction using hybrid machine learning techniques:-Senthil Kumar
mohan,chandrasegar thirumalai, and Gautam Srivastava -(19 JUNE 2019).
• [2] Prediction of Heart Disease Using Machine Learning:- Aditi Gavhane, Gouthami Kokkula,
Isha Pandya, Prof. Kailas Devadkar (PhD) - 2018.
• [3] Prediction of Heart Disease at early stage using Data Mining and Big Data Analytics: A
Survey:- Salma Banu N.K, Suma Swamy.-2019.
• [4] Prediction of Heart Disease Using Machine Learning Algorithms. :- Mr.Santhana Krishnan.J,
Dr.Geetha.S.- 2019.
• [5] Heart Disease Prediction using Machine Learning:-Abhijeet Jagtap, Priya Malewadkar,
Omkar Baswat
• [6] Prediction of Heart Disease Using Machine Learning Algorithms:- Ijaems Journal
• [7] Heart disease prediction using machine learning algorithms to cite this article: Harshit Jindal
et al 2021 IOP Conf. Ser.: Mater. Sci. Eng. 1022 012072
• [8] Machine learningebased heart disease prediction system for Indian population: An
exploratory study done in South India, Ekta Maini, Bondu Venkateswarlu, Baljeet Maini,
Dheeraj Marwaha
14
15
16