Analysis of heart rate variability to predict patient age in a healthy population.

OBJECTIVES: To estimate age of healthy subjects by means of the heart rate variability (HRV) parameters thus assessing the potentiality of HRV indexes as a biomarker of age. METHODS: Long-term indexes of HRV in time domain, frequency domain and non-linear parameters were computed on 24-hour recordings in a dataset of 63 healthy subjects (age range 20-76 years old). Then, as interbeat dynamics markedly change with age, showing a reduced HRV in older subjects, we tried to capture age-related influence on HRV by principal component analysis and to predict the subject age by means of a feedforward neural network. RESULTS: The network provides good prediction of patient age, even if a slight overestimation in the younger subjects and a slight underestimation in the older ones were observed. In addition, the important contribution of non-linear indexes to prediction is underlined. CONCLUSIONS: HRV as a predictor of age may lead to the definition of a new biomarker of aging.