Artificial neural networks based Internet hypertension prediction tool development and validation

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.