Cardiovascular risk prediction: a comparative study of Framingham and quantum neural network based approach
Authors Narain R, Saxena S, Goyal A
Received 10 March 2016
Accepted for publication 4 May 2016
Published 19 July 2016 Volume 2016:10 Pages 1259—1270
Checked for plagiarism Yes
Review by Single-blind
Peer reviewers approved by Dr Doris Leung
Peer reviewer comments 5
Editor who approved publication: Dr Johnny Chen
Renu Narain,1 Sanjai Saxena,1 Achal Kumar Goyal2
1Department of Biotechnology, Thapar University, Punjab, India; 2University Computer Center, Gurukul Kangri University, Haridwar, Uttarakhand, India
Purpose: Currently cardiovascular diseases (CVDs) are the main cause of death worldwide. Disease risk estimates can be used as prognostic information and support for treating CVDs. The commonly used Framingham risk score (FRS) for CVD prediction is outdated for the modern population, so FRS may not be accurate enough. In this paper, a novel CVD prediction system based on machine learning is proposed.
Methods: This study has been conducted with the data of 689 patients showing symptoms of CVD. Furthermore, the dataset of 5,209 CVD patients of the famous Framingham study has been used for validation purposes. Each patient’s parameters have been analyzed by physicians in order to make a diagnosis. The proposed system uses the quantum neural network for machine learning. This system learns and recognizes the pattern of CVD. The proposed system has been experimentally evaluated and compared with FRS.
Results: During testing, patients’ data in combination with the doctors’ diagnosis (predictions) are used for evaluation and validation. The proposed system achieved 98.57% accuracy in predicting the CVD risk. The CVD risk predictions by the proposed system, using the dataset of the Framingham study, confirmed the potential risk of death, deaths which actually occurred and had been recorded as due to myocardial infarction and coronary heart disease in the dataset of the Framingham study. The accuracy of the proposed system is significantly higher than FRS and other existing approaches.
Conclusion: The proposed system will serve as an excellent tool for a medical practitioner in predicting the risk of CVD. This system will be serving as an aid to medical practitioners for planning better medication and treatment strategies. An early diagnosis may be effectively made by using this system. An overall accuracy of 98.57% has been achieved in predicting the risk level. The accuracy is considerably higher compared to the other existing approaches. Thus, this system must be used instead of the well-known FRS.
Keywords: myocardial infarction, atherosclerosis, Framingham risk score, cardiovascular disease
This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at https://www.dovepress.com/terms.php and incorporate the Creative Commons Attribution - Non Commercial (unported, v3.0) License. By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms.Download Article [PDF] View Full Text [HTML][Machine readable]