Predicting coronary disease risk based on short-term RR interval measurements: a neural network approach

Coronary heart disease is a multifactorial disease and it remains the most common cause of death in many countries. Heart rate variability has been us ed for non-invasive measurement of parasympathetic activity and prediction of cardiac death. Patterns of heart rate variability associated with respir atory sinus arrhythmia have recently been considered as possible indicators of coronary heart disease risk in asymptomatic subjects. The aim of this w ork is to detect individuals at varying risk of coronary heart disease base d on short-term heart rate variability measurements under controlled respir ation. Artificial neural networks are used to recognise Poincare-plot-encod ed heart rate variability patterns related to coronary heart disease risk. The results indicate a relatively coarse binary representation of Poincare plots could be superior to an analogue encoding which, in principle, carrie s more information. (C) 1999 Elsevier Science B.V. All rights reserved.