A semi-supervised learning approach to classify drug attributes in a pharmacy management database: A STROBE-compliant study

With the development of information and communication technology, it has become possible to improve pharmacy management system (PMS) using these technologies. Our study aims to enhance the accuracy of drug attribute classification and recommend appropriate medications to improve patient compliance and treatment outcomes through the use of a semi-supervised learning method combined with artificial intelligence (AI) technology. This study proposed a semi-supervised learning method that integrates various technologies such as PMS, electronic prescriptions, and inventory management with AI to process and analyzed drug data, which enabled dynamic inventory updates and precise drug distribution. The application of the semi-supervised learning method reduced the need for labeled data, enabled automatic identification and classification of drug attributes, and recommended suitable medications. This reduced medication errors and patient wait times, significantly enhancing the efficiency and accuracy of pharmacy drug distribution. Integrating the semi-supervised learning method and AI technology into PMS can effectively improve the accuracy of drug attribute classification and the relevance of medication recommendations. This not only helped improve patient treatment outcomes but also saved costs for hospitals and provided a feasible model for other healthcare institutions to utilize AI technology in improving drug management and patient care.