Forecasting System for Heart Diseases: A Classification Approach

Journal of emerging technologies and innovative research, 2021

Data Mining is a methodology that use a variety of ways to uncover patterns or extract information from databases for use in decisionmaking and forecasting. In this study, an intelligent and effective method for predicting cardiac illness is examined utilising the Naive Bayes modelling technique. For the web-based application, the user must fill in the relevant values for the attributes. The data is retrieved from a database and is used to link training data to the value entered by the user. Traditional approaches cannot reliably detect cardiac illness, but this research can help clinicians make the best judgments possible. To diagnose heart illness, Naive Bayes is utilised for classification, and this method divides output data into no, low, average, high, and extremely high categories. As a result, two basic functions, categorization and prediction, are carried out. The accuracy of the system is determined by the method and database employed, and the Naive Bayes data categorization technique achieves a 98 percent accuracy. I.

Data Mining refers to using a variety of techniques to identify suggest of information or decision making knowledge in the database and extracting these in a way that they can put to use in areas such as decision support, predictions, forecasting and estimation. The healthcare industry collects huge amounts of healthcare data which, unfortunately, are not "mined" to discover hidden information for effective decision making. Discovering relations that connect variables in a database is the subject of data mining. This research has developed a Decision Support in Heart Disease Prediction System (DSHDPS) using data mining modeling technique, namely, Naïve Bayes. Using medical profiles such as age, sex, blood pressure and blood sugar it can predict the likelihood of patients getting a heart disease. It is implemented as web based questionnaire application. It can serve a training tool to train nurses and medical students to diagnose patients with heart disease.

CERN European Organization for Nuclear Research - Zenodo, 2022

As large amount of data is generated in medical organisations (hospitals,medical centers) but as this data is not properly used. There is a wealth of hidden information present in the datasets. This unused data can be converted into useful data. For this purpose we can use different data mining techniques. This paper presents a classifier approach for detection of heart disease and shows how Naive Bayes can be used for classification purpose. In our system, we will categories medical data into five categories namely no,low, average,high and very high.Also, if unknown sample comes then the system will predict the class label of that sample. Hence two basic functions namely classification (training) and prediction (testing) will be performed. Accuracy of the system is depends on algorithm and database used.

2012

The main objective of this research is to develop a n Intelligent System using data mining modeling tec hnique, namely, Naive Bayes. It is implemented as web based application in this user answers the predefined questions. It retrieves hidden data from stored database and compares the user values with trained data set. It can answer com plex queries for diagnosing heart disease and thus assist healthcare practitioners to make intelligent clinical decisio ns which traditional decision support systems cannot. By providing effec tive treatments, it also helps to reduce treatment costs.

2014

In this research, data mining techniques will helpful to handle the predictive model. Research will show the most effective parameter of the heart disease prediction which gets the scenario for least predictive value and most predictive value from the dataset. Initially need to identify the exact state of the user entering parameter which can be frequent item although random value of dataset in data modeling. Results show that unique strength which identifies the objectives of the defined mining goal and expert system. Some medical exponent attributes such as age, sex, blood pressure and blood sugar, glucose and some related factors can predict the likelihood of patients getting a heart disease with its exact probability. Basically this technique is expended on the defected and non-defected parameter which works as result class. The System can discover and extract hidden knowledge associated with diseases (heart attack) from a historical heart disease database.

International Journal of Advanced Trends in Computer Science and Engineering, 2020

The health care field provides enormous quantities of data that contain unseen pattern that can be useful for decisions. It is perplexing to orchestrate in an appropriate manner. Nature of the information association has been influenced because of improper administration of the information. Improvement in the measure of information needs some appropriate ways to concentrate and procedure information adequately and proficiently. This paper intended to develop a Decision Support System (DSS) for diagnosing cardiovascular diseases. The system used data mining technique, the Naïve Bayes Classification algorithm. This paper used Rapid Application Development (RAD) Software Life Cycle in designing and developing the system. The system was simulated, and its performance was evaluated in terms of accuracy using synthetic datasets namely, Cleveland and Statlog. Results showed that the system provided the adequate features for predicting heart diseases with an accuracy of 91% using the Cleveland dataset, 89% using the Statlog dataset and 90% using the combined instances of the two datasets. .

2019

The Healthcare exchange generally clinical diagnosis is ended commonly by doctor's knowledge and practice. Computer Aided Decision Support System plays a major task in the medical field. Data mining provides the methodology and technology to modify these rises of data into valuable data for decision making. By utilizing data mining techniques it requires less time for the prediction of the diseases with more accuracy. Among the expanding research on coronary diseases predicting system, it has happened significant to classifications the exploration results and gives readers with a layout of the current coronary diseases forecast strategies in every discussion. Data mining tools can respond to exchange addresses that expectedly being used much time over riding to decide. In this paper we study different papers in which at least one algorithm of data mining used for the prediction of coronary diseases. As of the study it is observed that Naïve Bayes Technique increase the accuracy ...

Nowadays, the healthcare sector is one of the areas where huge data are daily generated. However, most of the generated data are not properly exploited. Important encapsulated data are currently in the data sets. Therefore, the encapsulated data can be analyzed and put into useful data. Data mining is a very challenging task for the researchers to make diseases prediction from the huge medical databases. To succeed in dealing with this issue, researchers apply data mining techniques such as classification, clustering, association rules and so on. The main objective of this research is to predict heart diseases by the use of classification algorithms namely Naïve Bayes and Support Vector Machine in order to compare them on the basis of the performance factors i.e. probabilities and classification accuracy. In this paper, we also developed a computer-based clinical Decision support system that can assist medical professionals to predict heart disease status based on the clinical data of the patients using Naïve Bayes Algorithm. It is a web-based user-friendly system implemented on ASP.NET platform with C# and python for the data analysis. From the experimental results, it is observed that the performance of Naïve Bayes is better than the other Algorithm.

2019

The healthcare industry is a vast field with a plethora of data about patients,added to the huge medical records every passing day. In terms of science, this industry is 'information rich' yet 'knowledge poor'. However, data mining with its various analytical tools and techniques plays a major role in reducing the use of cumbersome tests used on patients to detect a disease. The aim of this paper is to employ and analyze different data mining techniques for the prediction of heart disease in a patient through extraction of interesting patterns from the dataset using vital parameters. This paper strives to bring out the methodology and implementation of these techniques-Artificial Neural Networks, Decision Tree and Naive Bayes and stress upon the results and conclusion induced on the basis of accuracy and time complexity. By far, the observations reveal that Artificial Neural Networks outperformed Naive Bayes and Decision Tree. Keywords Heart disease Á Prediction Á Neural networks Á Decision tree Á Naive Bayes Á Classification 2 Objective This paper aims towards concluding the most efficient technique among Neural Networks, Decision Tree and Naive Bayes employed for the prediction of heart disease on the basis of accuracy or prediction rate and time complexity. It also accounts for the methodology or implementation tools used for each of them. 3 Methodology The prediction system in this work is implemented using data mining techniques namely,ANN,Decision Tree and Naive Bayes on C# and Python platform. Using medical & Ritika Chadha

International Journal of Engineering Sciences & Research Technology, 2013

As large amount of data is generated in medical organisations (hospitals,medical centers)but as this data is not properly used. There is a wealth of hidden information present in the datasets. This unused data can be converted into useful data. For this purpose we can use different data mining techniques. This paper presents a classifier approach for detection of heart disease and shows how support vector machine(SVM) and Naive Bayes can be used for classification purpose. In our system, we will categories medical data into five categories namely no, low, average,high and very high. Also, if unknown sample comes then the system will predict the class label of that sample. Hence two basic functions namely classification (training) and prediction (testing) will be performed. Accuracy of the system is depends on algorithm and database used.