International Journal of Computer Science Trends and Technology (IJCST) – Volume 10 Issue 5, Sep-Oct 2022

RESEARCH ARTICLE OPEN ACCESS

Sorting and Guess of Heart Disease Risk Using Data Mining

Techniques and Machine Learning
Mrs J Sarada MCA,M.Tech,M.Phil,(Ph.D) [1], Yeddula Pavani [2]
[1]
Associate Professor, Department of Computer Applications
[2]
Student, Department of Computer Applications
[1],[2]
Chadalawada Ramanamma Engineering College (Autonomous)

ABSTRACT
Nowadays, heart disease is one of the prevailing main causes of morbidity and mortality. It is a hot health topic
in our daily life, and heart disease treatment is very complicated. It is one-third of all deaths globally, stroke and
heart disease. They both are globally the biggest killer, and their diagnosis availability is infrequent,
especially in developing countries. This paper contains a framework based on some machine learning and data
mining classification techniques on the heart disease dataset. There is no operational use of the data produced
from the hospitals. Some convinced tools are used to extract the facts from the database to recognize the
heart. This work is done by using Cleveland heart disease dataset that is sourced from the "UCI Machine
Learning (ML) repository" to test and analyze on some various supervised ML and data mining techniques, some
different attributes associated with causing of cardiovascular heart disease age, sex, chest pain type,
chol, thal, etc. We will use these respective data to a model that will predict whether the patient has heart
disease or not. This paper discussed the results of the modern techniques and will be used to predict the results
for heart disease by summarizing some current research. The proposed method works best result in 86.89%
accuracy by using a logistic regression algorithm.
Keywords: - Machine Learning, Classification Techniques, Prediction, Data Mining, Heart Disease, Python
Programming.

I. INTRODUCTION
Machine learning is self-restraint that deals with
Data mining is a process that is used for mining programming, and it learns automatically and
information or knowledge from a huge database. improves with experience. Bayesian and data
It is an essential and significant step for mining analysis is trending, adding the demand
discovering knowledge from existing databases. for machine learning. Data mining has four
Data mining's primary task is that extract the different main techniques: cluster, Regression,
hidden information and knowledge from the vast Classification, and association rules. Classification
database. It is identified as Knowledge Discovery in is a fundamental technique in data mining. We can
Database (KDD). It is an important process where get the future outcome and predict the data based
some common data mining techniques are used to on historical data available in a database. The
extract the data arrangement. Data mining's dataset can be classified into two categories through
technique helps to organizations to gain knowledge- the classification technique, namely Yes and No.
based information. It includes understanding the This method can achieve relevant and essential
business, data preparation, evaluating the data, information for data and easily classify our data into
and deployment. Its techniques work very rapidly different classes. "Data mining is the method for
and can find large amounts of data with the short determining potentially useful arrangements through
passage of time. More likely, sometimes, it is referred huge data sets and a large amount of database or
to as knowledge discovery in databases. Suppose metadata. It comes from different data sources, it
we use some professional and proficient may be sorted in various data warehouses and
computerized systems that are based on data mining data mining sorting techniques" [2]. Knowledge
and machine-learning algorithms. In that case, they Discovery in Database (KDD) is used for data
can help us for achieving clinical assessments or integration and cleaning, data discovery patterns,
diagnoses to minimize heart disease risk. Knowledge Presentation, data selection, and data

ISSN: 2347-8578 www.ijcstjournal.org Page 311

International Journal of Computer Science Trends and Technology (IJCST) – Volume 10 Issue 5, Sep-Oct 2022

transformation. Healthcare association produces broad data to mark the factual decisions.

Data mining whole process is based on some various steps for Extracting respective knowledge. Data cleaning in
data mining is how we can remove noise and corrupt or inaccurate records from data. We can prepare correct and
complete data for data analysis by eliminating duplication in data through the data cleaning process. This
data is usually not helpful when it comes to data analysis. The data cleaning process helps ensure that
respective information is matched with the field and ensures data selection and transformation. The data
transformation process is used to transform the data in a proper way required by data mining procedures. The
pattern evaluation is used to represents knowledge based on different measures of interest that are given.
We can use other heart disease patients' data collected after some diagnosis analysis and utilize the
experience and knowledge of several specialists split with the same symptoms of coronary heart diseases.
Complete and correct data helps the diagnosis analysis of patients for providing efficient treatment.

II. LITERATURE SURVEY

Shaikh Abdul Hannan et al. [5] used a Radial Basis Function(RBF) to predict the medical prescription for heart
disease. About 300 patient’s data were collected from the Sahara Hospital, Aurangabad. RBFNN (Radial Basis
Function–Neural Network) can be described as a three-layer feed forward structure. The three layers are the input
layer, hidden layer and output layer. The hidden layer consists of a number of RBF units (nh) and bias (bk). Each
neuron on the hidden layer uses a radial basis function as a nonlinear transfer function to operate on the input data.
The most often used RBF is usually a Gaussian function. Designing a RBFNN involves selecting centres, number of
hidden layer units, width and weights. The various ways of selecting the centres are random subset selection, k-
means clustering and others. The methodology was applied in MATLAB. Obtained results show that radial basis
function can be successfully used (with an accuracy of 90 to 97%) for prescribing the medicines for heart disease.

AH Chen et al. [6] presented a heart disease prediction system that can aid doctors in predicting heart disease status
based on the clinical data of patients. Thirteen important clinical features such as age, sex, chest pain type were
selected. An artificial neural network algorithm was used for classifying heart disease based on these clinical
features. Data was collected from machine learning repository of UCI .The artificial neural network model contained
three layers i.e. the input layer, the hidden layer and the output layer having 13 neurons, 6 neurons and 2 neurons
respectively. Learning Vector Quantization (LVQ) was used in this study. LVQ is a special case of an artificial
neural network that applies a prototype-based supervised classification algorithm. C programming language was

ISSN: 2347-8578 www.ijcstjournal.org Page 312

International Journal of Computer Science Trends and Technology (IJCST) – Volume 10 Issue 5, Sep-Oct 2022

used as a tool to implement heart disease classification and prediction trained via artificial neural network.The
system was developed in C and C# environment.The accuracy of the proposed method for prediction is near to 80%.

Mrudula Gudadhe et al.[7] presented a decision support system for heart disease classification. Support vector
machine (SVM) and artificial neural network (ANN) were the two main methods used in this system. A multilayer
perceptron neural network (MLPNN) with three layers was employed to develop a decision support system for the
diagnosis of heart disease. This multilayer perceptron neural network was trained by back-propagation algorithm
which is computationally an efficient method. Results showed that a MLPNN with back-propagation technique can
be successfully used for diagnosing heart disease.

Manpreet Singh et al. [8] proposed a heart disease prediction system based on Structural Equation Modelling (SEM)
and Fuzzy Cognitive Map (FCM).They used Canadian Community Health Survey (CCHS) 2012 dataset. Here,
twenty significant attributes were used. SEM is used to generate the weight matrix for the FCM model which then
predicts a possibility of cardiovascular diseases. A SEM model is defined with correlation between CCC 121(a
variable which defines whether the respondent has heart disease) along with 20 attributes. To construct FCM a
weight matrix representing the strength of the causal relationship between concepts must be constructed first. The
SEM defined in the previous section is now used as the FCM though they have achieved the required ingredients
(i.e. weight matrix, concepts and causality).80% of the data set was used for training the SEM model and the
remaining 20% for testing the FCM model. The accuracy obtained by using this model was 74%.

III. EXISTING SYSTEM

Numerous types of information mining furthermore, machine learning methods have been executed have applied
some techniques of data mining and machine learning namely Random Forest, J48 and Logistic Model Tree to build
up a framework for precise heart disease prediction. Data mining can be viably used to anticipate sicknesses from
the information base. Characterization procedures for example Decision Tree, Neural Network, Naive Bayes are
used. Naive Bayes, KNN and ID3 algorithms are selected for prediction. It consists of two phases classifier and
prediction. To foresee coronary illness with great exactness outcome. Coronary illness using a weighted fuzzy rule-
based choice aid framework. The automated technique to produce the fuzzy rules is the benefit of the proposed
framework. The amount of analytical information of coronary illness in the information layer, unseen layer might be
changed to get reduce mistakes and huge exactness. The large information for checking the patients to have an
upgraded arranging, dynamic, and cure with a decreased time and price.

Disadvantages
• To train the dataset KNN algorithm is used and in the expectation module, information is tried through the
ID3 method. Then, risk level was divided into three categories minimum, maximum and average.
• Analytical information of coronary illness in the information layer, unseen layer might be changed to get
reduce mistakes and huge exactness.

IV. PROPOSED SYSTEM

In this we introduced to sum up the new examination along relative outcomes on coronary illness expectation
furthermore construct scientific ends by using techniques of data mining Clinical science additionally utilized a
portion of crucial accessible instruments inside personal computer technology. During a decade ago expert system
has acquired its instant in light of development within calculation ability. The clinical information of the patients has
unseen patterns that are very important for information investigation in the diagnosis of coronary illness. It is the
way of finding hidden information by examining a lot of information stored the heap of cardiovascular infection is
quickly expanding. We will save human wealth since we do not require complex detection procedures in medical
clinics with correct expectations, we can tackle the unessential issues.

ISSN: 2347-8578 www.ijcstjournal.org Page 313

International Journal of Computer Science Trends and Technology (IJCST) – Volume 10 Issue 5, Sep-Oct 2022

Advantages
• Input dataset of heart disease has been taken have applied some techniques to anticipate coronary illness.
• The automated technique to produce the fuzzy rules is the benefit of the proposed framework.
• Fuzzy standards are applied to make the choice aid framework by applying a fuzzy conclusion framework
and the prediction of risk can be completed on a planned fuzzy system

IMPLEMENTATION
• Admin
• Doctor
• Patient

Admin
Admin can add the doctor and schedule as per the doctor available time. Admin can view the patient appointment
and he can schedule patient time as per available doctor.
Doctor
Doctor can view the patient request and after the check-up doctor add the patient report like Personal
Information,Lab Observation 1, Lab Observation 2, Critical Conditions, Diseases Details, Treatment Detail, and
Medicine Detail. As a final result we will showing Actual result, Predicated Result and Attack Stage.
Patient
Patient should register and login patient can book appointment and see the doctor schedule which doctor available
that time.

V. DISCUSSION portion of new task have considered mixture of

The whole section describes a portion of new task models. The possibility of mixture model is to
performed within information mining identified with consolidate few familiar determination methods in
cardiovascular illnesses. Information mining methods solitary model to give better outcomes. It has been
can be successfully applied to convert raw data from noticed that mixture of models has achieved better
the tremendous measure of information available in accuracy than a solitary model.
medical field. Such studies illustrate, instead of
implementing a specific data mining method to a VI. CONCLUSION
particular database, the creators have applied a fusion Heart disease is another dangerous and preventable
framework. Outcomes are more beneficial if an disease that cause millions of deaths in the world
assortment of mining strategies are utilized. Weka, today. Each clinical specialist has not equivalent
MATLAB and so forth are a portion of the other information moreover expertise to obtain a precise
famous instruments utilized for information choice, where a few specialists provide a weak
investigation. Cautious determination of the mixture sensible choice that guide individuals to risky
of data mining strategies with exact usage of these circumstances. So, preventing the occurrences of
strategies on database returns quick and viable usage heart disease is much important to reduce the number
of framework for coronary illness. A portion of the of deaths. Different types of techniques have been
task is to differentiate various categorization used to predict heart disease based on risk factors and
strategies on database to exactly characterize whether brief analysis of the accuracy of those techniques.
the patients have heart disease or not. Normally The exactness of algorithms in machine learning
utilized classifying methods are Decision tree, Naive relies on the dataset that is used for preparing and
Bayes, ANN, fuzzy approach. Other than testing purposes. One of the significant disadvantages
investigating those generally utilized procedures, a of the task is that the principal centre has been around

ISSN: 2347-8578 www.ijcstjournal.org Page 314

International Journal of Computer Science Trends and Technology (IJCST) – Volume 10 Issue 5, Sep-Oct 2022

the use of categorization procedures for coronary [9] N. Singh and D. Singh, “Performance Evaluation
illness expectation, instead of examining different of K-Means and Hierarchal Clustering in Terms of
information cleaning and pruning methods that plan Accuracy and Running Time”, Ph.D Dissertation,
and create a dataset reasonable for mining. For the Department of Computer Science and Engineering,
longer-term extension, extra machine learning Barkatullah University Institute of Technology, 2012
method will be utilized for the most useful [10] H. Kahramanli and N. Allahverdi, “Design of a
examination of the heart infections as well as for hybrid system for the diabetes and heart diseases,”
prior expectation of sicknesses with the goal that the Expert Systems with Applications, vol. 35, no. 1-2,
pace of the demise cases can be limited by the pp. 82-89,2000
realization about the illnesses.

REFERENCES

[1] H. B. F. David and S. A. Belcy, “Heart Disease

Prediction Using Data Mining Technques” ICTACT
Journal On Soft Computing, 2018, Vol: 09, Issue: 01
[2] X. Liu, X. Wang, Q. Su, M. Zhang, Y. Zhu,Q.
Wang, and Q. Wang, “A Hybrid Classification
System for Heart Disease Diagnosis Based on the
RFRS Method”, Computational and Mathematical
Methods in Medicine, Volume 2017, Article ID
8272091, 11 pages, DOI:
https://doi.org/10.1155/2017/8272091.
[3] C. B. C. Latha, S. C. Jeeva, “Improving the
accuracy of prediction of heart disease risk based on
ensemble classification techniques”, Informatics in
Medicine Unlocked 16,2019.
[4] C. Gazeloglu, “Prediction of heart disease by
classifying with feature selection and machine
learning methods”, Progress in Nutrition 2020; Vol.
22, N. 2: 660-670, DOI: 10.23751/pn.v22i2.9830.
[5] Heart Disease UCI,
https://www.kaggle.com/ronitf/heartdisease- uci,
Accessed Date: 20. June. 2020
[6] N. Guru, A. Dahiya and N. Rajpal, “Decision
Support System for Heart Disease Diagnosis using
Neural Network”, Delhi Business Review, Vol. 8,
No. 1, pp. 1-6, 2007.
[7] S. Palaniappan and R. Awang, “Intelligent Heart
Disease Prediction System using Data Mining
Techniques”, International Journal of Computer
Science and Network Security, Vol. 8, No. 8, pp. 1-6,
2008.
[8] S. B. Patil and Y.S. Kumaraswamy, “Intelligent
and Effective Heart Attack Prediction System using
Data Mining and Artificial Neural Network”,
European Journal of Scientific Research, Vol. 31, No.
4, pp. 642-656, 2009.

ISSN: 2347-8578 www.ijcstjournal.org Page 315