The effect of risk factors, heredity and chronic diseases on property incidence of kidney disease

Nagah Bobtina; Intesar Elmasli; Ali Bubteina; Maryam Akhwater

المؤلفون

Nagah Bobtina Histology Department, Faculty of Medicine, University of Benghazi-Libya
Intesar Elmasli Department of Biology, Faculty of Education, University of Benghazi, Benghazi-Libya
Ali Bubteina BSc medical student, Faculty of Medicine, University of Benghazi-Libya
Maryam Akhwater Physical Department, Faculty of Sciences, University of Al-Maraj-Libya

الكلمات المفتاحية:

kidney disease، risk factors، age، gender، ABO blood group، heredity، chronic diseases

الملخص

Chronic kidney disease (CKD) poses a major global health challenge, affecting approximately 10% of the world's population. Early detection and intervention are essential to slow disease progression and improve patient outcomes. Understanding the key factors that increase an individual’s susceptibility to kidney dysfunction is vital for effective prevention and management strategies.

This study aims to investigate the influence of various demographic and clinical risk factors—including age, gender, ABO blood group, hereditary predisposition, and the presence of chronic illnesses—on the development and progression of kidney disease. It also explores the predictive capability of artificial neural networks (ANNs) in assessing future kidney disease risk based on patient data.

A total of 589 participants with renal impairment or a family history of kidney disease were surveyed. After data cleaning, 138 valid cases were analyzed using SPSS for statistical assessment, and ANN models were developed to evaluate the relative importance of input variables and predict disease outcomes.

The ANN model achieved a prediction accuracy of 97%. The most influential variables associated with kidney disease were the degree of familial relation, hereditary background, and specific medication usage. These factors demonstrated a significant impact on the predicted health condition of individuals at risk.

This study highlights the utility of machine learning approaches, particularly ANNs, in identifying and prioritizing kidney disease risk factors. The findings support the development of targeted screening and preventive strategies for high-risk populations.