Development of a Remote Hypertension Monitoring and Risk Stratification Model Using Percentile Rank-Based Multi-Criteria Decision Making Algorithm
Domain:
healthcareRecord type:
Hypertension, a leading risk factor for cardiovascular diseases (CVDs), poses a significant
health challenge, particularly in low- and middle-income countries (LMICs), where
healthcare access and resources are limited. Existing remote hypertension monitoring and
risk stratification systems often face issues related to complexity, lack of interpretability,
and failure to account for the multifactorial nature of hypertension, limiting their practical
application. This study addresses these challenges by developing a remote hypertension
monitoring and risk stratification model using the Percentile Rank-Based Multi-criteria
Decision Making algorithm (PRBMCDM). The study aims to identify and prioritise
hypertension risk factors, design hypertension risk stratification model using PRBMCDM
algorithm, implement/stimulate the designed model and evaluate the model's performance
using standard metrics, including accuracy, precision, recall, F-score, and Area under the
Curve (AUC). Data were collected from public and private hospitals in Kogi Eastern
Senatorial District, Nigeria, and analysed using descriptive statistics and feature importance
techniques such as drop column importance. The PRBMCDM framework integrates
multiple health parameters, including age, gender, family history, hypertension grade, and
total cholesterol, to stratify patients into high, medium, and low-risk groups. The model
achieved high classification accuracy and demonstrated strong performance across risk
categories, with AUC values of 0.987, 0.987, and 0.968 for high, medium, and low-risk
groups, respectively. The findings highlight the model's ability to balance predictive
accuracy with clinical interpretability, making it suitable for resource-constrained settings.
Recommendations include the integration of PRBMCDM into healthcare systems, pilot
testing in clinical settings, and the incorporation of real-time data from Internet of Things
(IoT) devices to enhance its responsiveness. The study contributes to knowledge by offering
a comprehensive, interpretable, and effective solution for hypertension risk management,
with potential applications in other chronic diseases.