Accuracy of neuro-fuzzy logic and regression calculations in determining maximal lactate steady-state power output from incremental tests in humans

The aim of this study was to employ neuro-fuzzy logic and regression calculations to determine the accuracy of prediction of the power output ( P) of the maximal lactate steady-state (MLSS) on a cycle ergometer calculated from the results of incremental tests. A group of 17 male and 17 female sports students underwent two incremental tests (a 1 min test T(1): initial exercise intensity 0.2 W x kg(-1) increasing 0.2 W x kg(-1) every minute; a 3 min test T(3): initial exercise intensity 0.6 W x kg(-1) increasing 0.6 W x kg(-1) every 3 min) and at least four constant-intensity tests of 30 min duration. Two models for MLSS calculation were developed using the data from T(1) and T(3), a forward stepwise linear regression model (REG) and a neuro-fuzzy model (FUZ). A group of 26 randomly selected subjects (model group, MG) were used to generate the REG and the FUZ models. The data from the remaining 8 subjects (4 men and 4 women; verifying group, VG) were used to verify the REG and FUZ models. The precision of the MLSS calculation in MG produced a better correlation when using data from T(1) (REG r=0.95, FUZ r=0.99) than data from T(3) (REG r=0.88, FUZ r=0.98). Our calculation models were confirmed using data from VG for T(1) (REG r=0.97, FUZ r=0.98) as well as for T(3) (REG r=0.97, FUZ r=0.97). Based on our subject population of young, healthy sport students, our results suggest that a single incremental test may be used for prediction of P at the MLSS using a cycle ergometer. Furthermore, the results from T(1) yielded higher correlations compared to T(3). Calculations from REG were similar to FUZ but the precision of REG and FUZ was better compared to calculations derived using data from a single threshold.