AI-Augmented Mathematical Modelling in Healthcare: A Review of Hybrid Approaches to Predictive and Decision Intelligence

This study presents an AI-augmented mathematical modelling framework that integrates data-driven learning with mechanistic structures to enhance predictive accuracy and decision intelligence in healthcare systems. Traditional mathematical models have been central to understanding disease dynamics and optimizing healthcare resources, yet they often struggle with real-world complexity and parameter uncertainty. By combining Artificial Intelligence (AI) with mechanistic modelling, this research demonstrates how hybrid frameworks can capture nonlinear, dynamic healthcare processes with greater precision. The paper examines deterministic, stochastic, and simulation-based approaches such as differential equations, Markov models, and agent-based modeling augmented through AI techniques for parameter estimation, state prediction, and adaptive control. Case studies in malaria forecasting, hospital resource planning, and personalized cancer treatment highlight the improved predictive performance and adaptability of these hybrid systems. Finally, the study addresses key challenges in addressing bias, and ethical governance, underscoring the need for transparency and fairness in AI-driven healthcare. The results indicate that AI-augmented modelling offers a promising pathway toward adaptive, interpretable, and ethically sound decision support systems that bridge mathematical theory and clinical practice.