MACHINE LEARNING CLASSIFICATION ON BLOOD PRESSURE VARIATION FOR THE RISK OF COGNITIVE IMPAIRMENT: A CROSS-SECTIONAL STUDY FROM A BLOOD PRESSURE MANAGEMENT COHORT IN HONG KONG

Abstract

Objective: The evidence for the association between blood pressure variability (BPV) with cognitive impairment is still uncertain in the Asia population. This study explored whether a machine learning classification on BPV is associated with cognitive impairment among the elderly in Hong Kong. Design and method: Random samples of 573 participants were selected from a community-based cohort for blood pressure management in July 2021. Participants regularly measured blood pressure. K-means clustering methods were applied to group the standard deviation of BPV into high, medium, and low variations. This method considered both systolic and diastolic blood pressure variations. For cognitive functions, participants were assessed by the shorted version of the Montreal Cognitive Assessment Version, i.e., 5-min MoCA (Hong Kong validated version). Mild cognitive impairment (MCI) was defined with adjustment of age and education according to the 5-min MoCA. BPV was defined as the standard deviation of systolic and diastolic blood pressure values. Logistic and quantile regression models were conducted to explore the association of MCI with systolic or diastolic BPV and a combined BPV classification. Odds ratios (OR) were adjusted for age, gender, educational background social economic status, and other medical histories, including hypertension, hyperlipidemia, diabetes, and stroke. Results: The 573 participants had a mean age of 72 years with 86% of females. The median follow-up period was eight months with a median number of 19 blood pressure records. Systolic BPV increases the risk of MCI (adjusted OR, 95% CI = 1.18, 1.05 to 1.31), but not diastolic BPV. The quantile regression found that the magnitude of association is more substantial among the population with lower cognitive function (Figure 1). With reference to the machine learning classification, participants with high BPV were shown to have a 5.5 times higher risk of MCI than those with low BPV. Conclusions: Participants with higher systolic BPV are shown to be associated with poorer cognitive function, and therefore, long-term management of blood pressure variability is also important to reduce the risk of cognitive impairment.