A smartwatch sphygmomanometer-based model for predicting short-term new-onset hypertension in individuals with high-normal blood pressure: a cohort study

ABSTRACT

Objectives

The objective was to utilize a smartwatch sphygmomanometer to predict new-onset hypertension within a short-term follow-up among individuals with high-normal blood pressure (HNBP).

Methods

This study consisted of 3180 participants in the training set and 1000 participants in the validation set. Participants underwent both ambulatory blood pressure monitoring (ABPM) and home blood pressure monitoring (HBPM) using a smartwatch sphygmomanometer. Multivariable Cox regressions were used to analyze cumulative events. A nomogram was constructed to predict new-onset hypertension. Discrimination and calibration were assessed using the C-index and calibration curve, respectively.

Results

Among the 3180 individuals with HNBP in the training set, 693 (21.8%) developed new-onset hypertension within a 6-month period. The nomogram for predicting new-onset hypertension had a C-index of 0.854 (95% CI, 0.843–0.867). The calibration curve demonstrated good agreement between the nomogram’s predicted probabilities and actual observations for short-term new-onset hypertension. In the validate dataset, during the 6-month follow-up, the nomogram had a good C-index of 0.917 (95% CI, 0.904–0.930) and a good calibration curve. As the score increased, the risk of new-onset hypertension significantly increased, with an HR of 8.415 (95% CI: 5.153–13.744, p = .000) for the middle-score vs. low-score groups and 86.824 (95% CI: 55.071–136.885, p = .000) for the high-score vs. low-score group.

Conclusions

This study provides evidence for the use of smartwatch sphygmomanometer to monitor blood pressure in individuals at high risk of developing new-onset hypertension in the near future.

Trial registration

ChiCTR2200057354

GRAPHICAL ABSTRACT

KEYWORDS:

• Smartwatch sphygmomanometer
• high-normal blood pressure
• new-onset hypertension
• prediction

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This study was supported by the National Key Research and Development Program to YD Chen (2020YFC1512305) and the Chinese National Natural Science Foundation of YQ Liu (82070434). All authors had no conflicts of interest to disclose.