Heart Disease Prediction Model: Dissertation

HEART DISEASE PREDICTION MODEL
DISSERTATION
Submitted in Partial Fulfilment of the Requirements for the degree of
M. TECH
IN
ARTIFICIAL INTELLIGENCE & RESEARCH
Submitted By: CHIRAG SINGH

(Roll No. :17/IEC/018)
Under the supervision of
Dr. ARTI GAUTAM DINKER
To the
DEPARTMENT OF ECE
SCHOOL OF ICT
GAUTAM BUDDHA UNIVERSITY
December 2021
1. Introduction :
What is machine learning? Machine learning in simple terms is the process of teaching
a computer system to make accurate predictions when served with data. The predictions
that a machine learning models can make are innumerable from detecting the type of
object to making complicated decisions
Methods of Machine Learning The methods with which a machine learning algorithm
can be trained are broadly classified into 1. Supervised Machine Learning: During
training for supervised learning, systems are exposed to large amounts of labelled data,
when exposed to enough data the machine learning algorithm can make accurate
prediction. Because of the large amount of data set required for this method it gets
relatively laborious 2. Unsupervised Machine Learning: In unsupervised learning the
model takes in large amounts of data and tries to find out relationships and patterns in
the data. This type of learning is more about finding patterns and relationships that
would be laborious for humans to extract rather than predicting the results. 3.
Reinforcement Learning :Reinforcement learning directly takes inspiration from how
human beings learn from data in their lives. It features an algorithm that improves upon
itself and learns from new situations using a trial-and-error method. Favorable outputs
are encouraged, or ‘reinforced’, and no favorable outputs are discouraged or ‘punished’
MACHINE LEARNING IN THE AREA OF HEALTHCARE: The machine learning is

making inroads into the healthcare sector as well. With healthcare requiring lots of
manual analytics machine learning has opened avenues to aid the medical professionals
to get the information in reduced amount of time Just as other fields healthcare and
medical is still to see machine learning contributing a lot. But it is safe to say that
machine learning certainly has a great potential in healthcare. There are numerous
examples to suggest advent of ML in healthcare as well 1. Google has developed a
machine learning algorithm to help identify cancerous tumours on mammograms. 2.
Stanford is using a deep learning algorithm to identify skin cancer 3. Project Hanover
developed by Microsoft is using ML-based technologies for multiple initiatives
including developing AIbased technology for cancer treatment and personalizing drug
combination for AML (Acute Myeloid Leukaemia). 4. IBM recently partnered with
Medtronic to decipher, accumulate, and make available diabetes and insulin data in real
time based on the crowd sourced information.
2. Review of Literature:
Several studies have reported the development of heart disease diagnosis based on
machine learning models with the aim of providing an HDPM with enhanced
performance. Two publicly available heart disease datasets, namely Statlog and
Cleveland, have been widely used to compare the performance of prediction models
among researchers. For Stat log dataset, a heart disease clinical decision support system
based on chaos firefly algorithm and rough sets-based attribute reduction (CFARS-AR)
was developed by Long et al. (2015) [1]. The rough sets were used to reduce the number
of attributes while the chaos firefly algorithm was used to classify the disease. The
developed model was then compared with other models such as NB, SVM and ANN. The
results revealed that the proposed model achieved the highest performance among all the
models with accuracy, sensitivity, and specificity of 88.3%, 84.9%, and 93.3%,
respectively. The combination of rough sets-based attributes selection and BPNN (RS-
BPNN) was proposed by Nahato et al. (2015) [3]. With the selected attributes, the
proposed RS-BPNN achieved accuracy of up to 90.4%. Dwivedi (2018) [4] compared six
machine learning models (ANN, SVM, LR, k-nearest neighbor (kNN), classification tree
and NB) with various performance metrics. The results showed that LR performed better
than the other models by achieving up to 85%, 89%, 81%, and 85 for the accuracy,
sensitivity, specificity, and precision, respectively. Amin et al. (2019) [2] performed
comparison analysis by identifying significant attributes and applying machine learning
models (k-NN, DT, NB, LR, SVM, Neural Network (NN) and a hybrid (voting with NB
and LR)). The experiment results revealed that the hybrid model (voting with NB and
LR) with selected attributes achieved the highest accuracy (87.41%)
3. Objectives of the Study:
Cardiovascular diseases:
Our heart is a very important organ, pumping blood to each cell of the body diligently.
Alas we forget to take care of such an important organ, and it is due to this
cardiovascular problems are the number one cause of death globally. More people die of
CVD (cardiovascular diseases) than any other cause. An estimated 17.9 million people
died from CVDs in 2016, representing 31% of all global deaths. Of these deaths, 85%
are due to heart attack and stroke. A lot of these deaths could have been avoided by early
detection of the problem and taking corrective measures.
The aim is to help people decide whether they may or may not have some sort of heart
or cardiovascular problem based on the inputs they give.
We have tried to create a machine learning algorithm based on the dataset available in
the public domain to achieve maximum possible accuracy in detecting heart problems.
The aim is to give preliminary hint to the user on the possibility of having a heart
problem in response to which a person can choose to consult a doctor to get further
insights to the problem he/she may have.
4.Research Methodology:
1)In this machine learning project dataset has been collected from Kaggle
(https://www.kaggle.com/ronitf/heart-disease-uci) and we will be using Machine
Learning to make predictions on whether a person is suffering from heart disease or
not.
2) Let's first import all the necessary libraries. We will be using numpy and pandas to
start with. For visualization, we will use pyplot sub package of matplotlib, use
rcParams to add styling to the plots and rainbow for colors. For implementing
Machine Learning models and processing of data, we will use the sklearn library.
3) Now we can import the dataset and look at it. Dataset has a total of 303 rows and there
are no missing values. There is a total of 13 features along with one target value.
4) We can use visualizations to better understand our data and then look at any
processing we might want to do. For this we will be using heatmap and checking all
the correlations.
5. References:
[1] N. C. Long, P. Meesad, and H. Unger, ‘‘A highly accurate firefly-based algorithm
for heart disease prediction,’’ Expert Syst. Appl., vol. 42, no. 21, pp. 8221–8231, Nov.
2015
[2] M. S. Amin, Y. K. Chiam, and K. D. Varathan, ‘‘Identification of significant features and

data mining techniques in predicting heart disease,’’ Telematics Inform., vol. 36, pp. 82–93,
Mar. 2019
[3] K. B. Nahato, K. N. Harichandran, and K. Arputharaj, ‘‘Knowledge mining from clinical

datasets using rough sets and backpropagation neural network,’’ Comput. Math. Methods Med.,
vol. 2015, pp. 1–13, Mar. 2015,
[4] A. K. Dwivedi, ‘‘Performance evaluation of different machine learning techniques for

prediction of heart disease,’’ Neural Comput. Appl., vol. 29, no. 10, pp. 685–693, May 2018, d

Heart Disease Prediction Model: Dissertation

Uploaded by

Copyright:

Available Formats

Heart Disease Prediction Model: Dissertation

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Heart Disease Prediction Model: Dissertation

Uploaded by

Copyright:

Available Formats

What is machine learning and its methods?

What are some applications of machine learning in healthcare?

HEART DISEASE PREDICTION MODEL

Submitted in Partial Fulfilment of the Requirements for the degree of

Submitted By: CHIRAG SINGH

Under the supervision of

Dr. ARTI GAUTAM DINKER

GAUTAM BUDDHA UNIVERSITY

MACHINE LEARNING IN THE AREA OF HEALTHCARE: The machine learning is

3. Objectives of the Study:

[2] M. S. Amin, Y. K. Chiam, and K. D. Varathan, ‘‘Identification of significant features and

[3] K. B. Nahato, K. N. Harichandran, and K. Arputharaj, ‘‘Knowledge mining from clinical

[4] A. K. Dwivedi, ‘‘Performance evaluation of different machine learning techniques for

You might also like