Predictive value of 8-year blood pressure measures in intracerebral haemorrhage risk over 5 years

Abstract

Aims: The relationships between long-term blood pressure (BP) measures and intracerebral haemorrhage (ICH), as well as their predictive ability on ICH, are unclear. In this study, we aim to investigate the independent associations of multiple BP measures with subsequent 5-year ICH risk, as well as the incremental value of these measures over a single-point BP measurement in ICH risk prediction.

Methods and results: We included 12 398 participants from the China Kadoorie Biobank (CKB) who completed three surveys every 4-5 years. The following long-term BP measures were calculated: mean, minimum, maximum, standard deviation, coefficient of variation, average real variability, and cumulative BP exposure (cumBP). Cox proportional hazard models were used to examine the associations between these measures and ICH. The potential incremental value of these measures in ICH risk prediction was assessed using Harrell's C statistics, continuous net reclassification improvement (cNRI), and relative integrated discrimination improvement (rIDI). The hazard ratios (95% confidence intervals) of incident ICH associated with per standard deviation increase in cumulative systolic BP and cumulative diastolic BP were 1.62 (1.25-2.10) and 1.59 (1.23-2.07), respectively. When cumBP was added to the conventional 5-year ICH risk prediction model, the C-statistic change was 0.009 (-0.001, 0.019), the cNRI was 0.267 (0.070-0.464), and the rIDI was 18.2% (5.8-30.7%). Further subgroup analyses revealed a consistent increase in cNRI and rIDI in men, rural residents, and participants without diabetes. Other long-term BP measures showed no statistically significant associations with incident ICH and generally did not improve model performance.

Conclusion: The nearly 10-year cumBP was positively associated with an increased 5-year risk of ICH and could significantly improve risk reclassification for the ICH risk prediction model that included single-point BP measurement.

Keywords: Blood pressure variability; Cumulative blood pressure; Incremental value; Intracerebral haemorrhage; Long term; Risk prediction.

Figure 1

Study design and flow chart of the study participants.

Figure 2

Harrell’s C change for 5-year intracerebral haemorrhage risk prediction models by including both systolic blood pressure and diastolic blood pressure measures in all participants and by age, sex, area of residence, or prevalence of diabetes. Basic Cox models included age, systolic blood pressure, diastolic blood pressure, anti-hypertensive treatment, current daily smoking, prevalence of diabetes, and waist circumference at 2013–14 resurvey, and interactions between age and the other six predictors. For the analysis in participants without diabetes, the prevalence of diabetes was removed from the basic model. All models were stratified by sex and 10 study areas, except for the analysis by sex, in which the model was stratified only by 10 study areas. ARV, average real variability; CI, confidence interval; cumBP, cumulative blood pressure; CV, coefficient of variation; MAX, maximum; MIN, minimum; SD, standard deviation.