Evaluation of cardiorespiratory coupling (CRC) usually requires the simultaneous recording of heart period (HP) variability, derived from the electrocardiogram (ECG), and respiration. ECG-derived respiration (ECGDR) exploits the cardiac axis movement due to respiration to estimate respiratory activity directly from the ECG. Since CRC indexes could theoretically be computed using ECGDR, a comparison with results obtained through a more precise monitoring of respiratory activity such as the respiratory flow (RF) is warranted. Therefore, a mixed unpredictability index (MUPI) of HP variability from respiratory dynamics, computed via local k-nearest-neighbor approach, was calculated using ECGDR and RF in patients with preserved functional capacity (PFC) and with reduced functional capacity (RFC) before and after cardiopulmonary exercise test (CPET) protocol. Respiratory rate was also computed from the two respiratory series in all experimental conditions. The MUPI computed from RF was found to be significantly increased in PFC patients after CPET protocol (0.37±0.24 vs 0.55±0.25, p=0.004), while no effect could be observed when considering the ECGDR (0.36±0.24 vs 0.46±0.26) or RFC cohort. Moreover, the correlation between the two MUPI indexes was limited (Spearman's r=0.457, p=3.99E‒4), while correlation between the respiratory rates estimated with the two approaches was much stronger (Spearman's r=0.827, p=7.11E‒15). We conclude that, while ECGDR is a useful tool for the estimation of respiratory rate, the computation of modern indexes of CRC explicitly accounting for causality and nonlinearities, such as MUPI, might require more direct measures of respiration to detect differences across groups and experimental conditions. Furthermore, MUPI, as derived from RF, was shown to be useful to assess the effect of a CPET protocol on CRC and, more remarkably, this effect is different in PFC and RFC groups.