MEDERED: Medical Error Reduction Method for Drugs Prescription

Medicines play a pivotal role in healthcare and errors in medications certainly influence the quality and safety of healthcare. Currently, the healthcare industry is provided with various technologies that have enabled them to streamline and optimize the healthcare process. However, there are a number of factors that need to be synchronized further to obtain and enhance patient safety. In this research, an attempt is made to develop an intelligent method for smart diagnosis and medication prescription encompassing input, data process, and drug prescription output. The architectural design and prototype for the system model has a database that is referred to as Medical Health Record (MHR). The patient's medical history will be integrated with the prevailing symptoms in MHR. The MHR will help healthcare professionals to diagnose a particular disease based on his/her current symptoms, medical signs, and investigational data. Further, physician and pharmacist heuristic can be utilized for drug determination, drug allergy, adverse reaction, and possible drugdrug/herb/food interaction. The medical dataset was extracted from PubMed. This new AI based approach will re-engineer intelligent smart methods to develop quality healthcare in the most appropriate fashion. The learning results demonstrated an accuracy of 75.37%, providing a solid baseline for future model improvements.