Cardiovascular risk prediction: a comparative study of Framingham and quantum neural network based approach

Cardiovascular risk prediction: a comparative study of Framingham and quantum neural network based approach

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 The commonly used Framingham risk score (FRS) for CVD prediction is outdated for the modern population, so FRS may not be accura...

Full description

Saved in:
Bibliographic Details
Published in:Patient preference and adherence Vol. 10; pp. 1259 - 1270
Main Authors: Narain, Renu, Saxena, Sanjai, Goyal, Achal Kumar
Format: Journal Article
Language:English
Published: New Zealand Dove Medical Press Limited 01-01-2016
Dove Medical Press
Subjects:
Artificial neural networks
Atherosclerosis
Cardiovascular diseases
Comparative analysis
Comparative literature
Coronary heart disease
Death
Diseases
Heart attack
Heart diseases
Machine learning
Medical research
Novels
Original Research
Physicians
Risk factors
India
atherosclerosis
cardiovascular disease
Framingham risk score
myocardial infarction
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 The commonly used Framingham risk score (FRS) for CVD prediction is outdated for the modern population, so FRS may not be accurate enough.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. 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. 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. 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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1177-889X
1177-889X
DOI:10.2147/PPA.S108203