JMIR Publications

ABSTRACT

Background:

Low cardiorespiratory fitness (CRF) is an independent predictor of morbidity and mortality. Most healthcare settings use some type of electronic health record system (EHRs). However, many EHRs do not have CRF, or physical activity data collected, thereby limiting the types of investigations and analyses that can be done.

Objective:

Develop a nonexercise equation without physical activity to estimate and classify CRF (in METs) using variables commonly available in EHRs.

Methods:

Participants were 42,676 healthy adults (21.4% women) from the Aerobics Center Longitudinal Study examined from 1974 to 2005. Nonexercise estimated CRF (NEECRF) was based on sex, age, measured body mass index, measured resting heart rate, measured resting blood pressure, and smoking status. A maximal treadmill test measured CRF.

Results:

After conducting nonlinear feature augmentation, separate linear regression models were used for males and females to calculate correlation and regression coefficients. Cross-classification of actual and estimated CRF was performed using the lowest tertile as the low-fit category. R’s were 0.70 (mean deviation 1.33) and 0.65 (MD 1.23) for men and women, respectively. The models explained 48% (standard error of the estimate 1.70) and 42% (SEE 1.56) variance in CRF for men and women. Correct category classification for low CRF was found in 77.2% of men and 74.9% of women.

Conclusions:

The regression models developed in the present study provided useful estimation and classification of CRF in a large population of men and women. The models may provide a valid method for estimating CRF derived from EHRs.