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

Area of Science:

• Health Informatics
• Artificial Intelligence in Healthcare
• Pharmacy Management Systems

Background:

• Information and communication technology advancements enable improvements in pharmacy management systems (PMS).
• Accurate drug attribute classification and medication recommendations are crucial for patient compliance and treatment outcomes.

Purpose of the Study:

• To enhance drug attribute classification accuracy and medication recommendation relevance.
• To improve patient compliance and treatment outcomes using AI and semi-supervised learning in PMS.

Main Methods:

• Integration of semi-supervised learning with artificial intelligence (AI) technology within PMS.
• Utilizing AI to process and analyze drug data from PMS, electronic prescriptions, and inventory management.
• Leveraging semi-supervised learning to reduce reliance on labeled data for drug attribute classification.

Main Results:

• Achieved dynamic inventory updates and precise drug distribution.
• Enabled automatic identification and classification of drug attributes.
• Reduced medication errors and patient wait times, enhancing pharmacy efficiency and accuracy.

Conclusions:

• Integrating AI and semi-supervised learning into PMS significantly improves drug classification and medication recommendations.
• Enhanced patient treatment outcomes and reduced healthcare costs.
• Provides a model for healthcare institutions to adopt AI for improved drug management and patient care.