Impaired cardiorespiratory fitness (CRF) is closely linked to chronic illness and associated with adverse events. The American College of Sports Medicine (ACSM) regression equations (ACSM equations) developed to estimate oxygen uptake have known limitations leading to well-documented overestimation of CRF, especially at higher work rates. Thus, there is a need to explore alternative equations to more accurately predict CRF. We assessed maximal oxygen uptake (VO₂ max) obtained directly by open-circuit spirometry in 7,983 apparently healthy subjects who participated in the Fitness Registry and the Importance of Exercise National Database (FRIEND). We randomly sampled 70% of the participants from each of the following age categories: <40, 40 to 50, 50 to 70, and ≥70 and used the remaining 30% for validation. Multivariable linear regression analysis was applied to identify the most relevant variables and construct the best prediction model for VO₂ max. Treadmill speed and treadmill speed × grade were considered in the final model as predictors of measured VO₂ max and the following equation was generated: VO₂ max in ml O₂/kg/min = speed (m/min) × (0.17 + fractional grade × 0.79) + 3.5. The FRIEND equation predicted VO₂ max with an overall error >4 times lower than the error associated with the traditional ACSM equations (5.1 ± 18.3% vs 21.4 ± 24.9%, respectively). Overestimation associated with the ACSM equation was accentuated when different protocols were considered separately. In conclusion, The FRIEND equation predicts VO₂ max more precisely than the traditional ACSM equations with an overall error >4 times lower than that associated with the ACSM equations.