Risk Assessment Score and Chi-Square Automatic Interaction Detection Algorithm for Hypertension Among Africans:...

Area of Science:

• Cardiovascular Health
• Epidemiology
• Biostatistics

Background:

• Hypertension is a significant public health concern, particularly in African populations.
• Developing effective tools for early hypertension detection is crucial for primary prevention strategies.

Purpose of the Study:

• To develop and validate a novel risk-scoring model for hypertension among African adults.
• To identify key risk factors associated with hypertension in the study population.

Main Methods:

• A logistic regression model was developed using 4413 stroke-free controls.
• The dataset was split into training (80%) and testing (20%) sets.
• Risk factors were weighted to create a probability risk score (0-1); model accuracy was assessed using receiver operating characteristic (ROC) analysis and decision tree prediction.

Main Results:

• Eight factors significantly associated with hypertension included diabetes, age ≥65 years, high waist circumference, BMI ≥30 kg/m², lack of formal education, urban residence, family history of cardiovascular diseases, and dyslipidemia.
• A probability risk score of ≥0.60 was adopted.
• The model demonstrated good performance with an ROC of 64% in the test dataset; decision tree analysis showed a predictive accuracy of 67.7% (training) and 64.6% (testing).

Conclusions:

• The developed risk-scoring model accurately discriminates individuals with hypertension.
• This tool can facilitate early identification of at-risk African individuals for primary hypertension prevention.