Empowering Patient Care: A Novel Patient Drug Recommendation System Using Artificial Intelligence with Modified Learning Strategy

In the era of personalized medicine, the demand for efficient and accurate drug recommendation systems has escalated. This paper introduces a pioneering approach to enhance patient care through a novel Patient Drug Recommendation System (PDRS). Leveraging the power of machine learning (ML), specifically Cascaded Multi-Layer Perceptrons (MLP), our system aims to provide precise and personalized drug recommendations based on an extensive Drug Review Dataset. The proposed PDRS capitalizes on the inherent complexities of drug reviews, extracting valuable insights and patterns from patient feedback. The cascaded MLP architecture is designed to sequentially process and analyze diverse aspects of drug reviews, capturing nuanced information and correlations that may be overlooked by traditional recommendation systems. Our methodology involves preprocessing the drug review dataset to address noise and ensure data quality. Feature extraction techniques are applied to distill meaningful information, and the cascaded MLP model is trained using a robust set of labeled data. The system's performance is evaluated on various metrics, with a remarkable accuracy of 97%, signifying its efficacy in predicting suitable drug recommendations for patients. The cascaded MLP architecture demonstrates superior adaptability, allowing the system to comprehend intricate relationships between patients, drugs, and their respective effects. The achieved accuracy underscores the potential of our PDRS to revolutionize clinical decision-making, fostering a more personalized and efficient approach to prescribing medications.