An Intelligent Risk Prediction System for Breast Cancer Using Fuzzy Temporal Rules

Online prediction of risk on breast cancer is a challenging task in the area of health care during the past decade. Since the existing statistical and data mining methods have limitations with respect to the prediction of breast cancer, there is a need for proposing more effective predictive models...

Full description

Saved in:
Bibliographic Details
Published in:National Academy science letters 2019-06, Vol.42 (3), p.227-232
Main Authors: Kanimozhi, U., Ganapathy, S., Manjula, D., Kannan, A.
Format: Article
Language:English
Subjects:
Breast cancer
Classification
Consultation
Data mining
Fuzzy systems
Health care
Health risks
History of Science
Humanities and Social Sciences
Internet
multidisciplinary
Occupational health
Prediction models
Risk
Science
Science (multidisciplinary)
Short Communication
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Online prediction of risk on breast cancer is a challenging task in the area of health care during the past decade. Since the existing statistical and data mining methods have limitations with respect to the prediction of breast cancer, there is a need for proposing more effective predictive models which can predict the breast cancer more effectively. In this paper, we propose a new intelligent online risk prediction model for predicting the breast cancer using fuzzy temporal rules more accurately. Moreover, this intelligent system determines the contributing attributes from the dataset using intelligent fuzzy temporal rules and also performs prediction by applying fuzzy rule-based classification with temporal constraints. Moreover, the rules are validated using a domain expert and the experiments conducted in this work using questionnaire, rule-based classification and consultation with domain expert have proved that the proposed system provides more accurate results for risk prediction than the other existing systems.
ISSN:0250-541X
2250-1754
DOI:10.1007/s40009-018-0732-0