JMIR Publications

ABSTRACT

Background:

Whether the benefits of identical physical activity (PA) patterns for hypertensive patients vary according to an individual’s characteristics has not been adequately studied.

Objective:

The aim of this study was to investigate whether an individual’s characteristics modify the associations between PA patterns and patient prognosis.

Methods:

Four PA patterns were derived from accelerometer-based data: active weekend warrior (WW), active regular, active light PA (LPA), and inactive. Outcome was all-cause mortality. A machine learning model to predict the optimal PA pattern for individual patients was trained in the UK Biobank (UKB) cohort and externally validated in the National Health and Nutrition Examination Survey (NHANES) cohort, which was subsequently integrated into a web-based application.

Results:

A total of 60619 UKB adults and 3378 NHANES individuals were enrolled. The area under the receiver operating characteristic curve of our prediction model was 0.843 (95%CI, 0.822-0.863) at 8 years. The predicted optimal PA patterns in the UKB cohort were: active WW for 22816 participants (37.6%), consisting mainly of older men (≥61 years old); active regular PA for the 23634 (39.0%) relatively younger participants (<61 years old); and active LPA for the 14168 participants (23.4%), predominantly older females (≥61 years) with less sedentary time (<3574 minutes/week). Cox regression analysis suggested that individuals whose current PA pattern aligned with the predicted optimal ones may have a reduced mortality risk by an average of 24% (HR, 0.76 [95%CI, 0.69-0.83]) than those with inconsistent patterns.

Conclusions:

Our findings may help patients with hypertension to obtain individualized recommendations for PA patterns based on their specific characteristics, thereby improving their prognosis.