Artificial neural networks based Internet hypertension prediction tool development and validation

Authors:
Sebastian Polak;Aleksander Mendyk
Affiliations:
Department of Pharmacoepidemiology and Pharmacoeconomics, Medical College, Faculty of Pharmacy, Jagiellonian University, Medyczna 9 Street, 30-688 Kraków, Poland;Department of Pharmaceutical Technology and Biopharmaceutics, Medical College, Faculty of Pharmacy, Jagiellonian University, Medyczna 9 Street, 30-688 Kraków, Poland
Venue:
Applied Soft Computing
Year:
2008

Citing 2
Cited 2

Introduction to the theory of neural computation

Introduction to the theory of neural computation
Artificial intelligence technology as a tool for initial GDM screening

Expert Systems with Applications: An International Journal

A comparison of traditional and Simple Artificial Immune System (SAIS) techniques in consumer credit scoring

International Journal of Artificial Intelligence and Soft Computing
A case-based classifier for hypertension detection

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The objective of the study was to improve and validate previously prepared, artificial neural networks (ANNs) based system of high blood pressure risk prediction. Based on simple demographic data system is able to estimate the risk of hypertension. Database for the model construction was obtained from Centers for Disease Control-National Center for Health Statistics (CDC-NCHS). Best generalization results were found to be close to 75%-expressed as the total classification rate. Java applet was designed to be the interface between ANN system and end user. The validation procedure (years 1987-2000) acknowledged above 70% effectiveness of the system.