Integrating Predictive Modeling in Pharmacy Practice: A Narrative Review of AI Applications and Implementation Challenges

Abstract

Background The integration of Artificial Intelligence (AI)–driven predictive modeling into pharmacy practice is expanding, offering opportunities to improve patient outcomes and optimize medication management. Advanced AI approaches, including machine learning (ML), deep learning (DL), and natural language processing (NLP), enable risk stratification, data-driven clinical decision-making, and interpretation of complex or unstructured clinical data.

Objectives This narrative review examines current and emerging applications of AI-based predictive modeling in pharmacy practice, highlighting their role in clinical decision support, medication safety, adherence prediction, personalized pharmacotherapy, polypharmacy management, operational efficiency, and public health planning, while identifying key challenges and future priorities.

Methods A literature search was conducted using PubMed, Scopus, and Google Scholar with keywords related to artificial intelligence, predictive modeling, and pharmacy practice. Peer-reviewed English-language articles were included, and reference lists were screened for additional relevant studies.

Results AI-driven predictive models support diverse pharmacy applications. ML and DL facilitate prediction of adverse drug events, optimization of pharmacotherapy, identification of non-adherence risk, and detection of high-risk polypharmacy, particularly in older adults. NLP strengthens pharmacovigilance and medication review by enabling analysis of unstructured clinical text. Operational applications include inventory forecasting and supply chain optimization, while population-level models support public health planning.