What is the clinical evidence from this study?

Study design: Observational. Population: Hypertension (n=66). Intervention: Vector Autoregressive (VAR) model prediction. Primary outcome: Accuracy of predicting blood pressure threshold breakthroughs.

January 1, 2023Open Access

Hypertension Monitoring by a Real Time Management System for Patients in Community and Its Data Mining by Vector Autoregressive Model

Key Result

A Vector Autoregressive model using 3 weeks of home blood pressure monitoring data predicted subsequent 1-week blood pressure threshold breakthroughs with an accuracy of 78.43% in the testing set.

Study Design

Type

Observational (n=66)

Multicenter

Structured PICO

Does a Vector Autoregressive (VAR) model accurately predict future systolic and diastolic blood pressure thresholds in hypertensive patients using home monitoring data?

Population

66 hypertensive adults capable of self-monitoring blood pressure provided 4-week episodes of home blood pressure data to train and test a predictive model.

Exposure

Vector Autoregressive (VAR) model using 3 weeks of home blood pressure measurements (mean of values from 6 AM to 10 AM) to predict systolic and diastolic blood pressures in the 4th week.

Outcome

Prediction accuracy of blood pressure thresholds (Mean Absolute Percentage Error [MAPE], sensitivity, specificity, and accuracy) for identifying positive segments (≥3 SBP >140 mmHg or DBP >90 mmHg in the 4th week).surrogate

A Vector Autoregressive model using 3 weeks of home blood pressure monitoring data can simultaneously predict future systolic and diastolic blood pressure thresholds with less than 10% mean absolute percentage error, enabling early warning for hypertensive patients.

Limitations

Limited amount of data could bias the representativeness of VAR models.
Lack of consideration for several temporal variables that affect blood pressure, such as diet, exercise, sleep, smoking, and drinking.
Only considered extreme urgent situations for positive segments, missing other various situations.

Abstract

Blood pressure has a 24-hour repetitive and regular variation which shows circadian rhythm. Using the multivariate time series analysis method of vector autoregressive model, we could realize the simultaneous prediction for both systolic and diastolic blood pressures. We choose blood pressure from 6 AM to 10 AM in 3 weeks as an episode to construct a prediction model. Missing values were imputed by regression models. Subsequently, we defined segments as positive or negative segments according to blood pressure measurements. The predictions were accomplished by vector autoregressive model (VAR). Both positive and negative segments were randomly selected from each patient to summarize the effect of prediction models. In this study, the MAPE (Mean Absolute Percentage Error) of systolic blood pressure and diastolic blood pressure were both less than 10%, indicating that the VAR model was adaptable in predicting the blood pressure of hypertensive patients. Based on VAR, we could provide early warning to breakthrough of blood pressure thresholds. The sensitivity, specificity, and accuracy for patients in the training sets were 77.50%, 81.58 %, and 79.49% respectively, and the sensitivity, specificity, and accuracy for patients in the training sets were 76.92%, 80.00% and 78.43% respectively. This research took information of both systolic and diastolic blood pressures at the same time to establish the VAR models and enabled simultaneous prediction for systolic and diastolic blood pressure.

Bookmark

View Full Paper