External validation of VO_2max prediction models based on recreational and elite endurance athletes

In recent years, numerous prognostic models have been developed to predict VO_2max. Nevertheless, their accuracy in endurance athletes (EA) stays mostly unvalidated. This study aimed to compare predicted VO_2max (pVO_2max) with directly measured VO_2max by assessing the transferability of the currently available prediction models based on their R², calibration-in-the-large, and calibration slope. 5,260 healthy adult EA underwent a maximal exertion cardiopulmonary exercise test (CPET) (84.76% male; age 34.6±9.5 yrs.; VO_2max 52.97±7.39 mL∙min^-1∙kg^-1, BMI 23.59±2.73 kg∙m^-2). 13 models have been selected to establish pVO_2max. Participants were classified into four endurance subgroups (high-, recreational-, low- trained, and “transition”) and four age subgroups (18-30, 31-45, 46-60, and ≥61 yrs.). Validation was performed according to TRIPOD guidelines. pVO_2max was low-to-moderately associated with direct CPET measurements (p>0.05). Models with the highest accuracy were for males on a cycle ergometer (CE) (Kokkinos R² = 0.64), females on CE (Kokkinos R² = 0.65), males on a treadmill (TE) (Wasserman R² = 0.26), females on TE (Wasserman R² = 0.30). However, selected models underestimated pVO2max for younger and higher trained EA and overestimated for older and lower trained EA. All equations demonstrated merely moderate accuracy and should only be used as a supplemental method for physicians to estimate CRF in EA. It is necessary to derive new models on EA populations to include routinely in clinical practice and sports diagnostic.