ArticlePDF Available

Prediction of Heart Diseases using Support Vector Machine

Authors:
Yamala Sandhya at Swami Ramanandha tirtha institute of science and technology
Yamala Sandhya
  • Swami Ramanandha tirtha institute of science and technology
Download full-text PDF
Read full-text
Download citation

Figures

Figures - uploaded by Yamala Sandhya
Author content
All figure content in this area was uploaded by Yamala Sandhya
Content may be subject to copyright.
Content uploaded by Yamala Sandhya
Author content
All content in this area was uploaded by Yamala Sandhya on Mar 23, 2020
Content may be subject to copyright.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
126
©IJRASET: All Rights are Reserved
Prediction of Heart Diseases using Support Vector
Machine
Yamala Sandhya
Research scholar in Computer Science Engineering, Sreenidhi Institute of Science and Technology, Hyderabad (T.G), India
Abstract: Heart disease is the normal term used in the health industry. The meaning of the Heart disease is that the heart is not
working properly or normally. In the medical terminology the heart attack is a condition where the supply of the blood to the
organs of the body is blocked and then it will result into the blood clot. Now-a-days there are so many heart diseases like
Coronary Artery Disease, Congestive Heart Failure and Bad Heart Rhythms etc. There are so many number of people who are
suffering from the heart diseases. The heart diseases may or may not have the symptoms before it attack the people. So we need
to predict the heart diseases for the people it effect or not. Now-a-days so much number of people is died suddenly due to the
heart attack because the life style of the people is changed rapidly. In this research paper we use the Support Vector Machine
which is the Machine Learning algorithm. The support vector machine is a supervised learning method. In the research paper
the Support Vector Machine can predict the heart disease based on the given factors like sex, age, pulse rate etc. The machine
learning algorithm support vector machine used in this research paper will give the most accurate and reliable results when
compare to the other algorithms.
Keywords: Support Vector Machine, Machine learning, Heart diseases, Prediction, Symptoms.
I. INTRODUCTION
Now-a-days death of the people is increased due to the heart diseases. Heart Attack is the main reason for the death of the people.
There are so many diseases occur in the heart. There are so many reasons and factors which involve in the occurring of the heart
diseases. The death of the male is more than the female due to the heart diseases because of the smoking and drinking habit of the
male. The human life is mostly depending on the working functionality of the heart because heart supply the blood to the all the
organs of the body.
Heart diseases consist the High blood pressure, Heart attack, Heart value disease and Heart failure etc. In case of the heart diseases it
is important to predict the diseases in the early stages and take the treatment in early.
Fig 1: Heart diseases.
In this research paper we use the one of the Machine learning algorithm to predict the heart diseases in early stages based on the
factors like age, sex and blood pressure etc. The Support vector machine algorithm is provide the better accuracy and results when
compare to the other algorithms.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
127
©IJRASET: All Rights are Reserved
II. BACKGROUND WORK
There are two types of heart disease factors for risk. They are
1) Controllable factors.
2) Uncontrollable factors.
The Controllable factors are smoking, drinking, weight, blood pressure and cholesterol these can be controlled by the humans to
reduce the heart diseases.
The Uncontrollable factors are sex, age, history of the family. These cannot be controlled by the humans to reduce the heart diseases.
There are so many types of the heart diseases are present in the world. Some of the heart diseases are listed below.
Fig 2: Types of Heart diseases.
A. Congenital heart disease
The Congenital heart disease is type of heart disease that has been occurring in the heart since birth of people. Some of the examples
of congenital heart disease are:
1) Septal Defects: The septal defects have the hole between the two chambers of the heart of people.
2) Obstruction Defects: In the obstruction defects there is partial or total block of the flow of blood among the chambers of the
heart.
3) Cyanotic Heart Disease: The cyanotic heart disease has the shortage or less amount of the oxygen around the human body.
Fig 3: Congenial Heart disease.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
128
©IJRASET: All Rights are Reserved
B. Arrhythmia
Arrhythmia is occurring due to the changes in the normal heartbeat of the people.
Fig 4: Arrhythmia.
There are so many reasons for occurring of the Arrhythmia to the people. They are:
1) Tachycardia: The tachycardia occurs due to the fast heartbeat rate.
2) Bradycardia: The Bradycardia occurs due to the slow heartbeat rate.
When the electrical impulses in the human body heart fail to coordinate the heartbeat rate of the heart then the arrhythmia is
occurred. The electrical impulses make the heart to maintain the heartbeat rate as constant in any condition. Changes in the heartbeat
rate are so common, and most of the people experience it.
C. Coronary Artery Disease
The main function of the coronary arteries is to supply of the nutrients to the muscle of the heart he heart and to circulation of the
blood through oxygen. The Coronary arteries can be damaged or diseased because of the cholesterol. The cholesterol causes the
coronary arteries to supply the fewer amounts of oxygen and nutrients to the body.
Fig 5: Coronary artery disease.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
129
©IJRASET: All Rights are Reserved
D. Heart failure
Fig 6: Heart failure.
The Heart failure is also known as the congestive heart failure, the main reason for heart failure is there is no proper circulation of
blood throughout the human body efficiently and effectively.
E. Heart Muscle Disease (Cardiomyopathy)
The Heart Muscle disease is also known as the Cardiomyopathy. The Heart muscle disease occurs due to when the walls of the
human heart are become thicker or enlargement of the heart. This disease is the main reason to less supply of the blood to the whole
human body and thus results into the failure of the heart.
Fig 7: Heart muscle disease.
F. Heart Valve Disease
Fig 8: Heart valve disease.
There are four valves for the Human heart. These four valves are responsible to pumping of the blood to the whole human body and
to provide that the heart keeps the forward flow of the blood in human heart.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
130
©IJRASET: All Rights are Reserved
III. PROPOSED WORK
Machine Learning: Machine learning most used technology in now-a-days. The machine learning is an approach to train the
machine to learn from the past experience or previous examples. There are three types of machine learning algorithms. They are:
1) Supervised Learning: In supervised learning the machine is learned from the data which have labels and tag values. By using
labeled data we can easily predict the newly entered data. The supervised learning algorithm is similar to the students which are
learning under supervision of teachers.
2) Unsupervised Learning: In unsupervised learning the machine is learned from the data which does not contain any labels or tag
values. In unsupervised learning we classify or group the data by observing the similarity or relationship between the other data.
3) Reinforcement Learning: The reinforcement learning algorithm is a one type of algorithm in which the machine is interacting
with its environment by performing some actions and analyzes the data.
4) Support Vector Machine: Support vector machine is the one of the machine learning algorithms. The support vector machine is
a supervised learning algorithm. The support vector machine is used to classify the given data. The algorithm uses a hyper plane
to differentiate the different classes. Support vector machine is also used for the regression analysis. SVM classify the both
linear and non-linear data.
The main aim of the SVM classifier is to find the hyper plane in an n-dimensional space.
Fig 9: SVM classifier.
In SVM classifier the main aim to determine the plane with the maximum margin between the two data classes.
Fig 10: hyper plane in 2D and 3D.
In this research paper we use the SVM to predict the heart diseases of people. The steps involved in the prediction of heart diseases
are:
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
131
©IJRASET: All Rights are Reserved
5) Data Set: For this research process to predict the heart diseases of people we take the attributes like sex, age, blood pressure,
chest pain, sugar levels of the people.
Table 1: Data set for heart disease prediction.
In the above dataset in Gender 1 indicates the “male” and 0 indicates the “female”. In Chest pain 1 indicates “typical angina”, 2
indicates “atypical angina”, 3 indicates “non- angina pain” and 4 indicates “asymptomatic”. In prediction value 0 means “No” and 1
means “yes”.
Data preprocessing: After collecting the dataset we need to preprocess the data. The data preprocessing is used to reduce the size of
the data, remove the noisy data, eliminate the data outliers, determine the relationships among the data, and perform the
normalization on data. From the data preprocessing step we can extract the data which is needed to prediction process.
Fig 11: Process of heart disease prediction.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
132
©IJRASET: All Rights are Reserved
The prediction process also be shown in a flow chat.
Fig 12: Flow Chart of heart disease prediction.
Now we have to predict the patient’s health condition. For this process we use The R tool to predict whether the patient has heart
disease or not. In this research paper we use the R tool to predict the heart diseases of the patients. The R is software used in the
machine learning to classify the data. We have to supply the data to R tool. Then our data will become as shown below.
Fig 13: Structure of Data set – Support Vector Machine in R
Then the our next step is to train and testing of the our data. In this research paper we use 70% of data for training process and 30%
data for testing process. The summary of the data is shown below.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
133
©IJRASET: All Rights are Reserved
IV. RESULT ANALYSIS
There are so many machine learning algorithms to check whether has heart disease or not for the people. In this research paper we
use the Support Vector Machine algorithm to predict the heart diseases of people. We take the SVM algorithm for the prediction
process because it will give the greater accuracy when compare to the other machine learning algorithms. The accuracy of the
algorithm is shown in graphical representation. The results of the given data are shown below in graphical format
Fig 14: Accuracy of SVM algorithm.
The SVM algorithm gives the better precision, recall values for the given data. The below table shows the precision, recall for the
both yes and no classes.
Table 2: Precision and Recall.
The graph representation of these precision, recall values are shown below.
Fig 15: Graph of the precision and recall.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
134
©IJRASET: All Rights are Reserved
Table 3: Comparison of various machine learning algorithms for prediction of heart disease.
Fig 16: Graphical representation of the performance evaluation.
Table 4: TP and FP rate of various algorithms.
Fig 17: Graphical representation of TP and FP rate of various machine learning algorithms to predict heart diseases.
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.177
Volume 8 Issue II Feb 2020- Available at www.ijraset.com
135
©IJRASET: All Rights are Reserved
V. CONCLUSION AND FUTURE WORK
There are so many machine learning techniques to detection and prediction of the heart diseases. In this paper we use the support
vector machine to predict and identify the heart diseases of patients. We compare the result of the support vector machine algorithm
with the other machine algorithms. The SVM algorithm gives the better accuracy, specificity and sensitivity when compare to the
other machine learning algorithms.
In the future the performance of the support vector machine can be improved by using the combination of the other methods and
pruning of the given data. We can use the other machine learning techniques to get the better accuracy.
REFERENCES
[1] M.Durairaj, K.Meena, A Hybrid Prediction System Using Rough Sets and Artificial Neural Networks‖, International Journal Of Innovative Technology &
Creative Engineering (ISSN: 2045-8711) VOL.1 NO.7 JULY 2011.
[2] K. Srinivas, B. Kavitha Rani and Dr. A. Govrdhan, Applications of Data Mining Techniques in Healthcare and Prediction of Heart Attacks‖ International
Journal on Computer Science and Engineering (2010).
[3] Kala John Kappiarukudil and ManeeshaVinodini Ramesh “Real-Time Monitoring and Detection of „„Heart Attack‟‟ Using Wireless Sensor Networks”, 2010
Fourth International Conference on Sensor Technologies and Applications ISSN:978-0-7695-40962/10IEEE,2010.
[4] Mai Shouman, Tim Turner, and Rob Stocker “Using Data Mining Technique in Heart Disease Diagnosis and Treatment”, 2012 JapanEgypt Conference on
Electronics, Communications and Computers ISSN:978-1-4673-0484-9/ IEEE,pp.173-177,2012. 3
[5] Vikas Chaurasia and Saurabh Pal “Data Mining Approach to Detect Heart Dieses”, International Journal of Advanced Computer Science and Information
Technology (IJACSIT) Vol. 2, No. 4, 2013, Page: 56-66, ISSN: 2296-1739.
[6] J Peter and K. Somasundaram, “An Empirical Study on Prediction of Heart Disease Using Classification DataMining Techniques”, Proceedings of IEEE
International Conference on Advances In Engineering, Science And Management (ICAESM), (2012), pp. 514-518.
[7] Machine learning based decision support systems (DSS) for heart disease diagnosis: a review. Online: 25 March 2017 DOI: 10.1007/s10462-01.
[8] Prerana T H M, Shivaprakash N C et al “Prediction of Heart Disease Using Machine Learning Algorithms- Naïve Bayes,Introduction to PAC Algorithm,
Comparison of Algorithms and HDPS”,Vol 3, PP: 90-99©IJSE, 2015.
[9] Salam Ismaeel, Ali Miri et al “Using the Extreme Learning Machine(ELM) technique for heart disease diagnosis”,IEEE Canada International Humanitarian
Technology Conference, DOI:10.1109/IHTC.2015.7238043, 03 September 2015.
[10] Salha M. Alzahani, Afnan Althopity, Ashwag Alghamdi, -“An Overview of Data Mining Techniques Applied for Heart Disease Diagnosis and Prediction”
Lecture Notes on Information Theory, Volume: 02, No. 04.
[11] H K Shifali, Dr. B. Srinivasu, Rajashekar Shastry, B N Ranga Swamy-“Mining of Medical Data to Identify Risk Factors of Heart Disease Using Frequent
Itemset”, International Research Journal of Engineering and Technology (IRJET),Volume: 04 Issue: 01.
[12] Prof. Mamta Sharma 1, Farheen Khan2, Vishnupriya Ravichandran “Comparing Data Mining Techniques Used For Heart Disease”, International Research
Journal of Engineering and Technology, Volume: 04 Issue: 06
[13] Abhishek Taneja - “Heart Disease Prediction System Using Data Mining Techniques”, oriental journal of computer science & technology, Volume: 06
[14] Priya R Patil -“Automated Diagnosis of Heart Disease using Data Mining Techniques".
[15] Aditi Gavhane, Gouthami Kokkula, Isha Pandya, Prof. Kailas Devadkar (PhD) ” Prediction of Heart Disease Using Machine Learning” Proceedings of the 2nd
International conference on Electronics, Communication and Aerospace Technology (ICECA 2018) IEEE Conference Record # 42487; IEEE Xplore
ISBN:978-1-5386-0965-1.
[16] 1Cincy Raju, 2Philipsy E, 3Siji Chacko, 4L Padma Suresh, 5Deepa Rajan S ” A Survey on Predicting Heart Disease using Data Mining Techniques” Proc.
IEEE Conference on Emerging Devices and Smart Systems (ICEDSS 2018) 2-3 March 2018, Mahendra Engineering College, Tamilnadu, India.
... These methods make it easy to conduct comprehensive genetic data analysis, forecast knowledge pandemics, and study medical records more thoroughly. Researchers have used machine learning algorithms such as Decision trees [1], Support vector machines [2], and Naive bayes to predict heart disease [3]. However, one of the common problems with machine learning is the high dimensionality of data, which can lead to overfitting and require a large amount of memory. ...
... The accuracy of the developed CNN-based model is 95%, the precision is 94% and f1-score is 95%. This result shows a great improvement to previous machine learning model using support vector machine [2]. Table 3. ...
Development and Performance Evaluation of a Heart Disease Prediction Model Using Convolutional Neural Network
Article
Full-text available
  • Mar 2024
Heart disease is a leading cause of mortality globally and its prevalence is increasing year after year. Recent statistics from the World Health Organization show that about 17.9 million individuals are embattled with heart diseases annually and people under the age of 70 account for one-third of these deaths. Hence, there is need to intensify research on early heart disease prediction and artificial intelligence-based heart disease prediction systems. Previous heart disease prediction systems using machine learning techniques are unable to manage large amount of data, resulting in poor prediction accuracy. Hence, this research employs Convolutional Neural Networks, a deep learning approach for prediction of heart diseases. The dataset for training and testing the model was obtained from a government owned hospital in Nigeria and Kaggle. The resulting system was evaluated using precision, recall, f1-score and accuracy metrics. The results obtained are: 0.94, 0.95, 0.95 and 0.95 for precision, recall, f1-score and accuracy respectively. This show that the CNN-based model responded very well to the prediction of heart diseases for both negative and positive classes. The results obtained were also compared to some selected machine-learning models like Random Forest, Naïve Bayes, KNN and Logistic Regression and results show that the developed model achieved a significant improvement over the methods considered. Therefore, convolutional neural network is more suitable for heart disease prediction than some state-of-the-art machine-learning models. The contribution to knowledge of this research is the use of Afrocentric dataset for heart disease prediction. Future research should consider increasing the data size for model training to achieve improved accuracy.
View
... Figure 1. Symptoms of heart attack [6]. ...
Enhanced Myocardial Infarction Prediction Using Machine Learning Algorithms and Gender-Specific Insights
Article
Full-text available
  • May 2024
A serious medical condition called myocardial infarction (MI), sometimes referred to as a "heart attack," is caused by disruptions in the blood supply to the myocardium. This research examines the efficacy of machine learning (ML) algorithms in forecasting myocardial infarction (MI) using a dataset of 350 records. The study identifies key risk factors for predicting myocardial infarction (MI), such as elevated cholesterol levels, diabetes, advanced age, overall health status, mental well-being, obesity, physical activity, smoking habits, hypertension, and depression. Significantly, gender does not manifest as a predictor of myocardial infarction (MI) when employing various classification methods. The research achieves high accuracy rates of 89.32%, 87.53%, 81.29%, and 76.59% using different machine learning algorithms, including Deep Belief Network (DBN), C4.5, Random Forest (RF), and Bayesian Network (BN), respectively. Algorithm-specific rule sets identify correlations, with the C4.5 algorithm revealing interesting connections between smoking habits and protection against myocardial infarction (MI). Performance metrics like accuracy, precision, sensitivity, and specificity attest to the effectiveness of the proposed technique. The results demonstrate the superior performance of the DBN algorithm, surpassing other algorithms in terms of accuracy (89.32%), precision (84.04%), sensitivity (86.63%), and specificity (82.45%). This paper provides crucial insights into predictive modeling for myocardial infarction (MI), highlighting the importance of various risk factors and advanced machine learning (ML) algorithms. The results offer clinicians and researchers a strong foundation for comprehending and potentially averting myocardial infarction, relying on personalized patient profiles. This paper has the potential to significantly contribute to the field by applying ensemble classifiers and machine learning models to forecast gender-specific myocardial infarctions. As a result, diagnostic precision and patient outcomes could be revolutionized.
View
View
View
Enhanced cardiovascular disease prediction through self-improved Aquila optimized feature selection in quantum neural network & LSTM model
Article
Full-text available
  • Jun 2024
Introduction Cardiovascular disease (CVD) stands as a pervasive catalyst for illness and mortality on a global scale, underscoring the imperative for sophisticated prediction methodologies within the ambit of healthcare data analysis. The vast volume of medical data available necessitates effective data mining techniques to extract valuable insights for decision-making and prediction. While machine learning algorithms are commonly employed for CVD diagnosis and prediction, the high dimensionality of datasets poses a performance challenge. Methods This research paper presents a novel hybrid model for predicting CVD, focusing on an optimal feature set. The proposed model encompasses four main stages namely: preprocessing, feature extraction, feature selection (FS), and classification. Initially, data preprocessing eliminates missing and duplicate values. Subsequently, feature extraction is performed to address dimensionality issues, utilizing measures such as central tendency, qualitative variation, degree of dispersion, and symmetrical uncertainty. FS is optimized using the self-improved Aquila optimization approach. Finally, a hybridized model combining long short-term memory and a quantum neural network is trained using the selected features. An algorithm is devised to optimize the LSTM model’s weights. Performance evaluation of the proposed approach is conducted against existing models using specific performance measures. Results Far dataset-1, accuracy-96.69%, sensitivity-96.62%, specifity-96.77%, precision-96.03%, recall-97.86%, F1-score-96.84%, MCC-96.37%, NPV-96.25%, FPR-3.2%, FNR-3.37% and for dataset-2, accuracy-95.54%, sensitivity-95.86%, specifity-94.51%, precision-96.03%, F1-score-96.94%, MCC-93.03%, NPV-94.66%, FPR-5.4%, FNR-4.1%. The findings of this study contribute to improved CVD prediction by utilizing an efficient hybrid model with an optimized feature set. Discussion We have proven that our method accurately predicts cardiovascular disease (CVD) with unmatched precision by conducting extensive experiments and validating our methodology on a large dataset of patient demographics and clinical factors. QNN and LSTM frameworks with Aquila feature tuning increase forecast accuracy and reveal cardiovascular risk-related physiological pathways. Our research shows how advanced computational tools may alter sickness prediction and management, contributing to the emerging field of machine learning in healthcare. Our research used a revolutionary methodology and produced significant advances in cardiovascular disease prediction.
View
View
View
View
Congestive Heart Failure Prediction Using Artificial Intelligence
Chapter
Full-text available
  • Oct 2023
One of the main reasons people for hospitalization of adults over the age of 65 is heart failure (HF) or congestive heart failure (CHF). CHF affects millions of people globally and is among the primary causes of death. Heart failure means the heart is doing less work (pumping less blood) than usual. It may be due to increased pressure in the heart, which gradually leave the heart too weak hence a slower rate of blood flowing through the body. Before it’s too late, heart failure can be prevented by analyzing and controlling the conditions that can cause it. In this work, we use Cardiovascular Health Study (CHS) dataset and compare five different machine learning techniques to predict congestive heart failure (CHF). For feature selection, we employ the decision tree (DT) C4.5 method and the Predictive Mean Matching (PMM) method for missing data imputation. From the different ways applied, our proposed method gives the optimal result.
View
EMPLOYMENT OF THE SELECTIVE MACHINE LEARNING ALGORITHM FOR THE EARLY AND EFFECTIVE DETECTION AND DIAGNOSIS OF CARDIOVASCULAR DISEASE
Article
  • Jan 2021
Heart and blood artery dysfunction is the root cause of cardiovascular disease, which includes coronary heart disease, cerebrovascular disease, peripheral arterial disease, rheumatic heart disease, deep vein thrombosis, and pulmonary embolism. A model for using a machine-learning algorithm to find cardiovascular diseases is presented in this paper. Utilized the agile methodology in this research, planning, requirements analysis, designing, coding, testing, and documentation are all carried out simultaneously throughout the stages of the production process. Using four distinct machine learning algorithms—a Support Vector Classifier, a K-Nearest Neighbors Classifier, a Random Forest Classifier, and a Decision Tree Classifier—the patient dataset is used to train the model in this paper. An algorithm will make the predictions, resulting in the most accurate results. Flask, a web-based implementation of this model, was used to make a prediction, the user must fill in 13 inputs on the web. Flask and the Python programming language are used to implement the model and the machine learning algorithms. We use a K-Nearest Neighbors Classifier algorithm after considering all four machine learning algorithms. The prediction has a good accuracy of 85.83 per cent, which is good for any model.
View
View
Using the Extreme Learning Machine (ELM) Technique for Heart Disease Diagnosis
Conference Paper
Full-text available
  • May 2015
One of the most important applications of machine learning systems is the diagnosis of heart disease which affect the lives of millions of people. Patients suffering from heart disease have lot of independent factors such as age, sex, serum cholesterol, blood sugar, etc. in common which can be used very effectively for diagnosis. In this paper an Extreme Learning Machine (ELM) algorithm is used to model these factors. The proposed system can replace a costly medical check-ups with a warning system for patients of the probable presence of heart disease. The system is implemented on real data collected by the Cleveland Clinic Foundation where around 300 patients information has been collected. Simulation results show this architecture has about 80% accuracy in determining heart disease.
View
A Hybrid Prediction System Using Rough Sets and Artificial Neural Networks
Article
Full-text available
This paper illustrates a hybrid prediction system consists of Rough Set Theory (RST) and Artificial Neural Network (ANN) for processing medical data. In the process of developing a new data mining technique and software to aid efficient solutions for medical data analysis, we propose a hybrid tool that incorporates RST and ANN to make efficient data analysis and suggestive predictions. In the experiments, we used spermatological data set for predicting quality of animal semen. The data set used in the experiments is subjected to quantize and normalize, and use this as a reflection of the internal system state. The RST is used as a tool for reducing and choosing the most relevant sets of internal states for predicting the semen fertilization potential. Chosen optimal data set is input to constructed neural network with supervised learning algorithm for the prediction of semen quality. This paper demonstrates that the RST is an effective pre-processing tool for reducing the number of input vector to ANN without reducing the basic knowledge of the information system in order to increase prediction accuracy of the proposed system. The resulting system is a hybrid prediction system for medical database called an Intelligent Rough Neural Network System (IRNNS).
View
Data Mining Approach to Detect Heart Diseases
Article
Full-text available
  • Nov 2013
Globally, heart diseases are the number one cause of death. About 80% of deaths occurred in low- and middle income countries. If current trends are allowed to continue, by 2030 an estimated 23.6 million people will die from cardiovascular disease (mainly from heart attacks and strokes). The healthcare industry gathers enormous amounts of heart disease data which, unfortunately, are not “mined” to discover hidden information for effective decision making. The reduction of blood and oxygen supply to the heart leads to heart disease. However, there is a lack of effective analysis tools to discover hidden relationships and trends in data. This research paper intends to provide a survey of current techniques of knowledge discovery in databases using data mining techniques which will be useful for medical practitioners to take effective decision. The objective of this research work is to predict more accurately the presence of heart disease with reduced number of attributes. Originally, thirteen attributes were involved in predicting the heart disease. Thirteen attributes are reduced to 11 attributes. Three classifiers like Naive Bayes, J48 Decision Tree and Bagging algorithm are used to predict the diagnosis of patients with the same accuracy as obtained before the reduction of number of attributes. In our studies 10- fold cross validation method was used to measure the unbiased estimate of these prediction models.
View
View
View
View
Using data mining techniques in heart disease diagnosis and treatment
Article
  • Mar 2012
The availability of huge amounts of medical data leads to the need for powerful data analysis tools to extract useful knowledge. Researchers have long been concerned with applying statistical and data mining tools to improve data analysis on large data sets. Disease diagnosis is one of the applications where data mining tools are proving successful results. Heart disease is the leading cause of death all over the world in the past ten years. Several researchers are using statistical and data mining tools to help health care professionals in the diagnosis of heart disease. Using single data mining technique in the diagnosis of heart disease has been comprehensively investigated showing acceptable levels of accuracy. Recently, researchers have been investigating the effect of hybridizing more than one technique showing enhanced results in the diagnosis of heart disease. However, using data mining techniques to identify a suitable treatment for heart disease patients has received less attention. This paper identifies gaps in the research on heart disease diagnosis and treatment and proposes a model to systematically close those gaps to discover if applying data mining techniques to heart disease treatment data can provide as reliable performance as that achieved in diagnosing heart disease.
View
An empirical study on prediction of heart disease using classification data mining techniques
Article
  • Jan 2012
In this research paper, the use of pattern recognition and data mining techniques into risk prediction models in the clinical domain of cardiovascular medicine is proposed. The data is to be modelled and classified by using classification data mining technique. Some of the limitations of the conventional medical scoring systems are that there is a presence of intrinsic linear combinations of variables in the input set and hence they are not adept at modelling nonlinear complex interactions in medical domains. This limitation is handled in this research by use of classification models which can implicitly detect complex nonlinear relationships between dependent and independent variables as well as the ability to detect all possible interactions between predictor variables.
View
Real-Time Monitoring and Detection of Heart Attack Using Wireless Sensor Networks
Conference Paper
  • Aug 2010
The main purpose of this research work is to develop a wireless sensor network system that can continuously monitor and detect cardiovascular disease experienced in patients at remote areas. A wearable wireless sensor system (WWSS) is designed to continuously capture and transmit the ECG signals to the patient's mobile phone. The fastest alert will be issued to doctors, relatives, and hospitals, using the proposed data processing algorithm implemented in the patients mobile phone. The complete data from WWSS will also be transmitted to a central station, which provides a service to the doctor to view his patient's record and provide his prescription remotely, on his request. A heterogeneous wireless network design is also proposed for the continuous transmission from WWSS to a Central Data Center (CDC). The proposed system is integrated with a dynamic data collection algorithm that collects the ECG signals at regular intervals, according to the health risk perceived in each patient. Employment of this system will contribute in reducing heart diseases, leading to death of a patient, and also act as an effective health care service to patients in rural area. This continuous monitoring system will provide effective, efficient, and fast health care service to patients at risk, even if the doctor, relatives are not near the patient and also during the non availability of the cellular network.
View