Current Volume 8
Hypertension remains a major public health concern, particularly in resource-constrained environments such as small teaching hospitals, where early diagnosis and effective management are critical yet often under-optimized. This study investigates the patterns and predictors of hypertension using statistical analysis and predictive modeling techniques to enhance clinical decision-making. Patient data were collected from a small teaching hospital over a defined period, focusing on demographic, lifestyle, and clinical variables. Descriptive statistics were employed to understand prevalence trends, while predictive models—such as logistic regression and decision trees—were developed to identify key risk factors and forecast the likelihood of hypertension occurrence. The models were evaluated using accuracy, sensitivity, specificity, and area under the ROC curve (AUC) to ensure reliability and applicability in real-world settings. Results revealed significant associations between hypertension and factors such as age, BMI, and family history. The predictive models demonstrated robust performance, offering potential integration into electronic health record systems for proactive screening. This study underscores the value of data-driven approaches in enhancing hypertension management, especially within the constraints of small hospital settings, and recommends further expansion of predictive tools for broader public health applications.
Predictive Modeling, Statistical Analysis, Hypertension Cases, Small Teaching Hospital
IRE Journals:
Adama Gaye
"Predictive Modeling and Statistical Analysis of Hypertension Cases at a Small Teaching Hospital" Iconic Research And Engineering Journals Volume 8 Issue 11 2025 Page 630-640
IEEE:
Adama Gaye
"Predictive Modeling and Statistical Analysis of Hypertension Cases at a Small Teaching Hospital" Iconic Research And Engineering Journals, 8(11)