The system applies machine learning techniques, including XGBoost classification and regression, to predict disease risks and estimate onset age from SNP variations. While SMOTE corrects class imbalance to enhance generalization for uncommon situations, data pretreatment includes one-hot encoding, feature scaling, and dimensionality reduction with Truncated SVD. Through the identification of significant SNPs influencing illness risk scores, SHAP achieves explainability. Structured disease progression analysis is supported by PCA and K-Means clustering, which group SNPs with comparable patterns. A Markov Model provides insights into progression throughout time by simulating changes from healthy to at-risk or diagnostic stages. Heat maps that visualize transition probabilities improve knowledge of SNP-disease connections, improving prediction accuracy and facilitating early intervention. This integrated system combines explainability, progression modeling, and prediction to assist healthcare providers in creating preventive programs.