Enhancing the Patient Safety by using the Explainable Artificial Intelligence in Pharmacovigilance
Ganesh S A1, Megha Rani Raigond2
1Department of CSE Visvesvaraya Technological University Kalaburagi, Karnataka India
2Department of CSE Visvesvaraya Technological University Kalaburagi, Karnataka India
Abstract - The Artificial intelligence is a technology in pharmacovigilance (PV) and in explainable artificial intelligence used a tree-based approach (Random Forest Classifier) that enhances the artificial intelligence. Though there have been many previous attempts to select papers, with a total of 781 papers being confirmed, only 25 of them manually met the selection criteria. Side-effects of drugs and interaction studies. Adverse drug reaction (ADR) is widely concerned for public health issue. ADRs are one of most common causes to withdraw some drugs from market. Prescription event monitoring (PEM) is an important approach to detect the adverse drug reactions. The main problem to deal with this method is how to extract the side-effects from medical events (drug reactions), which are collected from day-to-day clinical practice which is extracted from big medical data from the Health Improvement Network database, is created to characterize the medical events for the patients who take drugs. The detected adverse drug reactions are based on computerized methods further investigation is needed. In this project it provides the side-effects of medicines(drugs) to be aware of tablets they were using in their daily life based on the real data it performs and the data is collected from recent medical healthcare. This project's goal is to determine uses and providing the adverse drug reaction or side-effects of medicines and studies in employing XAI in the pharmacovigilance (PV) domain. While artificial intelligence (AI) is being utilized extensively in drugs safety for the patient by XAI. AI model goals align with the patient safety goals to reduce harmfulness of drug to the data addressing security and privacy concerns for patient, the accuracy of this XAI project is 82 %.
Key Words: predict the drugs for patients safety, by using the tree-based algorithm (random forest classifier).
