An Intelligent Data Mining Framework For Predictive Decision-Making Using Explainable Artificial Intelligence

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

Integration of artificial intelligence into vital decision-making fields has led to the emergence of a demand for transparency and interpretability in the used predictive models. This research aims to present an intelligent data mining framework, which utilizes the combination of predictive modeling methods and Explainable Artificial Intelligence (XAI). The use of the suggested framework is meant to ensure transparent decision-making process by implementing such methods of predictive modeling as ensemble learning, including Random Forest, XGBoost, and Gradient Boosting along with the methods of SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) for multi-level explanation generation. Our research applies the intelligent data mining framework on the dataset related to healthcare and includes several classes of diseases, ensuring high performance of the model in terms of prediction along with generating actionable explanations for each prediction.