Identifying significant features and data mining techniques in predicting cardiovascular disease / Mohammad Shafenoor Amin

• Auteur principal: Mohammad Shafenoor , Amin
• Format: Thèse
• Publié: 2018
• Sujets: QA76 Computer software; TA Engineering (General). Civil engineering (General)

Cardiovascular disease is one of the biggest cause for morbidity and mortality among the population of the world. Prediction of cardiovascular disease since regarded as one of the most important subject in the section of clinical data analysis. The amount of data in the healthcare industry is huge. This raw data is needed to be processed to make certain decision on various information. Data mining turns a large collection of data into knowledge. Therefore, the use of data mining in healthcare is obvious. A very high number of researches are conducted on this issue. Nonetheless, a very few has given attention towards the significant features that plays a vital role in predicting cardiovascular disease. Researchers have often focused towards the diagnosis by using different algorithms, sometimes even using the hybrid algorithm. Nonetheless, they have failed to generate an acceptable accuracy in prediction because of using wrong feature selection methods. It has been confirmed that correct features can be more effective when it comes to predicting cardiovascular disease at a very early stage. The problem of finding just the correct combination were addressed in some researches but still lacking effective attempts to improve the accuracy of prediction. A thorough analysis of the features needs to be conducted to select a combination of significant features that can increase the accuracy of the prediction. This research aims to identify significant features and data mining techniques that can improve the accuracy of predicting cardiovascular disease. This research predicts the cardiovascular disease using the identified significant features and data mining techniques. The significant features and techniques were evaluated and achieved accuracy of 87.41%.