<![CDATA[Lung cancer remains one of the most prevalent and deadly types of cancer worldwide, especially in developing countries with high smoking rates and limited early detection resources. This study aims to develop a computational mathematical model for predicting lung cancer risk using multiple linear regression. The model focuses on two primary factors: genetic predisposition and exposure to passive smoking, which are among the most significant determinants of lung cancer. An observational analytic design was employed using secondary data obtained from cancer registries, hospital records, and national health survey datasets. Computational data preprocessing techniques, including data cleaning, missing value imputation, and variable normalization, were applied to ensure model accuracy and reliability. The regression analysis revealed that both genetic predisposition and passive smoking significantly increased the lung cancer risk score, with regression coefficients of 0.24 and 0.48, respectively. The findings indicate that passive smoking has a greater impact on lung cancer risk compared to genetic factors. The final model demonstrated a coefficient of determination (R²) 0.72 indicates that 72% of the variation in risk can be explained by the combination of these two variables. This finding suggests that environmental factors have a more dominant influence than lifestyle factors on increasing lung cancer risk. This computational model provides a practical tool for early detection and risk stratification, supporting public health policies aimed at tobacco control and targeted screening programs to reduce lung cancer incidence and mortality]]>
