You are on page 1of 30

HEART DISEASE PREDICTION USING

MACHINE LEARNING
AGENDA
1 ABSTRACT 8 SYSTEM
SPECIFICATION

2 AIM AND SCOPE 9 ARCHITECTURE

3 EXISTING 10 MODULES
SYSTEM

4 LIMITATIONS 11 EXPERIMENTS

5 PROPOSED 12 SCREENSHOTS
SYSTEM
6 ADVANTAGES 13 CONCLUSION

7 LITERATURE 14 REFERENCE
SURVEY
ABSTRACT

In today’s common modern life, deaths due to the heart disease has become one of the major issues, roughly one
person dies every minute due to heart illness. Worldwide the death due to heart disease is increasing day by day.
Heart illness became the major reason of death with an average value of about 1 person every 1 minute which is
about 31% of all deaths globally. In India too, heart related diseases have become the leading cause of mortality.
The risk factor of heart disease is high and has to be diagnosed timely. The diagnosis has to be very accurate,
reliable and sensible to take effective safety measures. Predicting the occurrence of disease at early stages is
highly challenging. Machine language applied to many field provide an efficient and accurate system. Machine
language is also used in health care. This is capable of early and accurate detection of disease. An efficient and
accurate system to diagnosis heart disease is proposed and the system is based on machine learning techniques.
The system proposed namely HDDS (heart disease diagnosis system) is used for heart disease prediction. This is
capable of early and accurate diagnosis of heart disease. This system is based on classification algorithms.
Classification algorithms in machine learning use input training data to predict the likelihood that subsequent
data will fall into one of the predetermined categories.
AIM

• The goal of this project is to see the patient's medical characteristics to


predict heart disease in early-stage with high accuracy using machine
learning and deploying using flask.

SCOPE

• Predicting the data ahead of time can help ML forecast the existence
or absence of neurological disorders, heart problems, and other conditions .
EXISTING SYSTEM

• For HD prediction various techniques is used


(SVM, ANN, NV,KNN)
• Overall highest accuracy score among is below 92%
• 297 samples 13 features is Trained and tested
limitations

• Not the best choice for large number of features


• Poor results on very small datasets
• More complex
Proposed system

• We have used Random forest algorithm(classification algorithm)


• 1988 samples and 14 attributes
• Got 100% accuracy as data sample is large
• Then trained model is deployed in flask framework using Vscode
• The app will give API to Display the results (healthy 0r not healthy)
ADVANTAGES

• Accuracy is better when compared to other machine learning techniques


• Random forest is capable of performing both classification and regression
tasks
• It is capable of handling large datasets with high dimensionality
LITERATURE SURVEY
PAPER TITLE AUTHOR INFERENCE DRAWBACKS
Heart Disease Identification Jian Ping, Amin ul haq , Salah The system is developed based Not the best choice for large
Method Using Machine ud din , Jalaluddin khan, Asif on Classification algorithms number of features and is more
Learning Classification in E- khan , and Abdus Saboor. includes Support vector complex .
Healthcare. machine, Logistic regression,
Artificial neural network, K-
nearest neighbor, Naïve bays,
and Decision tree
Heart disease classification Ilias Tougui, Abdelilah Jilbab & It compares six common data Inappropriate modeling leading
using data mining tools Jamal El Mhamdi mining tools: Orange, Weka, to inaccurate predictions
machine learning techniques RapidMiner, Knime, Matlab,
and Scikit-Learn, using six
machine learning techniques

Predicting Heart Disease at Rahul Katarya; Polipireddy Some of the supervised Unexplained functioning of the
Early Stages using Machine Srinivas machine learning techniques network and is dependent on
Learning: A Survey used in this prediction of heart user’s ability.
disease are ANN, DT, RF,
SVM, NB and k-nearest
neighbour algorithm
SYSTEM SPECIFICATION

SOFTWARE SPECIFICATION
• Requirements:
• Languages used : python, html /CSS
• Algorithm : classification- random forest
• Front end : flask framework, html/CSS
HARDWARE SPECIFICATION:
• Requirements:
• Processor : intel® core ™ i5 processor
• RAM : 4 GB or more
• System type : 64-bit operating system
• Keyboard : normal or multimedia
• Mouse : compatible mouse
ARCHITECTURE
MODULES
DATA COLLECTION

• Data is collected from kaggle repository, this data set dates from
1988 and consists of four databases: cleveland, hungary, switzerland,
and long beach V.
• The "target" field refers to the presence of heart disease in the
patient. It is integer valued 0 = no disease and 1 = disease.
DATA LOADING

• Data is loaded using Pandas lib


• read_csv function in Pandas read our file
• Save it and we can display the dataframes
DATASETS
ALGORITHM USED

RANDOM FOREST
• A random forest classifier is used to train the model.
• It is a meta estimator that fits a number of decision tree
• The sub-sample size is controlled with the max_samples parameter if
brootstrap = True(default), otherwise the whole dataset is used to build each
tree.
EXPERIMENTS
ANALYZING TARGET VARIABLE

• From the data, we have found that the percentage of


patients without heart problems is 45.54%
• And the percentage of a patient with heart problems
is 54.46. Clearly, this is a classification problem, with
target variable having ‘0’ and ‘1’
ANALYZING THE 'SEX' FEATURE
• From the data snapshot, we will conclude that
we have analyzed between males and females.
Where the variable ‘0’ is high so notice that
females are more likely to have heart problems
than males
ANALYZING THE 'CHEST PAIN TYPE’
FEATURE

This CP feature has a value from 0 to 3, they


are
chest pain type
0: typical angina
1: atypical angina
2: non-anginal pain
3: asymptomatic
ANALYZING THE ‘RESTECG’
FEATURE

• We realize that people with restecg '1' and '0'


are much more likely to have a heart disease
than with restecg '2'
ANALYSING THE 'EXANG' FEATURE

• We observe, that Slope '2' causes heart pain


much more than Slope '0' and '1'
ANALYSING THE ‘CA’ FEATURE

• From the above snapshot we know that ‘ca’


feature has values from 0 to 4. ca=4 has an
astonishingly large number of heart patients
ANALYSING ‘THAL’ FEATURE
• From the above snapshot, we can classify the
“Thal’ feature by Values such as
thal:
6 = normal;
6 = fixed defect;
7 = reversible defect
SCREENSHOTS
• The above figure represents an application for HD prediction designed using
flask framework.
• This app's engine is a py script that is used to execute the application.
• the model prediction.Py is a python script that may be used to create and train
a machine learning model.
• The main.Html and result.Html files in the templates folder outline the
structure
• The flask framework connects these files to python.
• The style.Css file in the static folder adds some styling to the programme and
improves its appearance
PREDICTION RESULT
PREDICTION RESULT
CONCLUSION

• The Random Forest algorithm is a powerful ensemble learning system for


regression and classification procedures. As a result, early-stage prediction
accuracy is efficiently accomplished.
• If a patient or user is unable to contact a doctor, he or she can use this
application to anticipate disease simply by entering the report information.
• And can decide whether or not to seek medical advice
• The information should also be forwarded to the local hospital. Another
option that should be offered is an online doctor consultation with the closest
doctor.
REFERENCES
[1] Li, J.P., Haq, A.U., Din, S.U., Khan, J., Khan, A. and Saboor, A., 2020. Heart disease identification method using machine
learning classification in e-healthcare. IEEE Access, 8, pp.107562-107582.

[2] Katarya, R. and Srinivas, P., 2020, July. Predicting heart disease at early stages using machine learning: A survey. In 2020
International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 302-305). IEEE.

[3] Tougui, I., Jilbab, A. and El Mhamdi, J., 2020. Heart disease classification using data mining tools and machine learning
techniques. Health and Technology, 10(5), pp.1137-1144.

[4] Rajdhan, A., Agarwal, A., Sai, M., Ravi, D. and Ghuli, P., 2020. Heart disease prediction using machine
learning. International Journal of Research and Technology, 9(04), pp.659-662.

[5] Diwakar, M., Tripathi, A., Joshi, K., Memoria, M. and Singh, P., 2021. Latest trends on heart disease prediction using machine
learning and image fusion. Materials Today: Proceedings, 37, pp.3213-3218.

[6] Khan, M.A., Abbas, S., Atta, A., Ditta, A., Alquhayz, H., Khan, M.F. and Naqvi, R.A., 2020. Intelligent cloud based heart disease
prediction system empowered with supervised machine learning.

[7] Krittanawong, C., Virk, H.U.H., Bangalore, S., Wang, Z., Johnson, K.W., Pinotti, R., Zhang, H., Kaplin, S., Narasimhan, B.,
Kitai, T. and Baber, U., 2020. Machine learning prediction in cardiovascular diseases: a meta-analysis. Scientific reports, 10(1), pp.1-
11.
QUERIES?
THANK YOU
For your Attention

You might also like