Comparison between standard short-term, very-short and ultra-short-term heart rate variability analysis in healthy subjects during exercise testing

Purpose: Stepwise exercise testing, with workload increasing every two minutes, determines progressive changes of autonomic nervous system (ANS) adaptations that might affect stationarity during the intervals sampled for Standard Short term (SST) heart rate variability analysis (HRVa) according to ESC guidelines. To quantify such transients short-lasting changes very-short (VST) and ultra-short term (UST) analysis (HRVa) might be more appropriate, but have not been validated so far. The study aimed to evaluate, in healthy subjects (HS), the information provided by VST and UST HRVa in comparison with SSTHRVa, during exercise testing. Methods: 12-lead ECG recorded in 25 HS, before, at each workload step and during recovery after maximal exercise testing with a bicycle ergometer (workload increasing by 25 watts, every two minutes). The coefficients of variation (CV) and of reproducibility (CR) and the Pearson correlation (R2) of the same linear [time-domain (TD) and frequency-domain (FD)] and nonlinear (NL) HRV parameters, computed from SST (5-minutes), VST (60-seconds) and UST (30-seconds) intervals with Kubios HRV 2.1, (Biosignal Analysis and Medical Imaging Group, Department of Physics, University of Kuopio, Finland), were evaluated. VST and UST intervals were selected at the end of each step. Results: SSTHRVa was appropriate only at rest, before exercise and in the recovery phase. A significant correlation was found among parameters estimated from 5-minutes, 60- and 30-seconds time intervals (Pearson R² range: 0.42 -0.98, p< 0.05 – 0.000001), except for a certain degree of variability of frequency peaks estimated with the Fast Fourier transform. At peak workload only VST and USTHRVa parameters were significantly correlated (R² range: 0.6 -0.99, p< 0.01 – 0.000001), whereas the 5-minute interval was too long and averaged ther consecutive workload steps. At peak exercise, the CV and the CR of LF/HF, estimated from 60- and 30-seconds time-intervals were 9.3 and 0.54, respectively, thus almost optimal. Among NL methods, only the Poincaré plot was calculable in all conditions. Instead recurrence plot, detrended fluctuation, approximate entropy, sample entropy and correlation dimension parameters required at least 40-seconds intervals, unless heart rate exceeded 100 bpm. Discussion: The good correlation among HRV parameters estimated at rest from 5-minutes, 60- and 30-seconds time intervals proves that VST or UST HRVa are a feasible option to evaluate changes of cardiac autonomic modulation induced by stepwise exercise testing when time-variant HRVa is unavailable.