Early identification of high-risk patients is one of the most important responsibilities of community nursing because timely intervention reduces disease progression, hospitalization, healthcare costs, and mortality. Traditional risk assessment methods often rely on manual scoring systems and subjective clinical judgment, which may fail to detect subtle relationships among multiple patient characteristics. Recent advances in Artificial Intelligence (AI) and statistical learning provide opportunities to develop intelligent Clinical Decision Support Systems (CDSS) capable of accurately identifying individuals at high risk.

The present study proposes an AI-based Statistical Clinical Decision Support Model integrating classical statistical techniques and machine learning algorithms for early detection of high-risk patients in community nursing settings. The proposed framework combines logistic regression, Random Forest, Gradient Boosting, and Artificial Neural Networks with statistical feature selection techniques. Community health records containing demographic, clinical, behavioral, socioeconomic, and environmental variables are used for model development.

The model performance is evaluated using Accuracy, Sensitivity, Specificity, Precision, Recall, F1-score, ROC-AUC, and calibration statistics. Explainable Artificial Intelligence (XAI) methods such as SHAP values are incorporated to improve transparency and support nursing decision-making. The proposed model is expected to assist community nurses in identifying vulnerable patients earlier, prioritizing home visits, optimizing resource allocation, and improving preventive healthcare outcomes.