Precision Pharmacology: Deep Learning Infused Ontological Framework with E-GRU Enhancement for Tailored Medicine Prescriptions

Technology significantly influences patient care, positioning medicine prescription as a vital area of research. Ontology, a growing discipline in the semantic web, enables hierarchical domain representation, allowing finer data access. Deep Learning (DL) supports pattern recognition in Electronic Health Records (EHR), which include patient demographics and diagnosis histories. Prescribing medications with minimal adverse effects is crucial, especially for patients requiring multiple drugs, as interactions can result in more complex conditions. This paper introduces an integrated approach that combines Ontology with DL neural networks to improve prescription accuracy. We propose NexusOpti, a model featuring an Enhanced Gated Recurrent Unit (E-GRU) layer. To understand drug–disease interactions, hierarchical data are extracted from the International Classification of Diseases (ICD) Ontology and Anatomical Therapeutic Chemical (ATC) Ontology. These structured data are processed using a self-attention mechanism to enhance recommendation precision. This integration not only addresses data security concerns but also improves the accuracy of medicine recommendations. The model was evaluated using key metrics such as hit ratio and normalized discounted cumulative gain (NDCG). Evaluation results show that NexusOpti outperforms existing methods, achieving a 13% improvement in performance. These findings highlight the model’s effectiveness in advancing personalized, safer, and data-driven medication prescriptions.