Authors : Asoke K. Talukder, Erwin Selg, Ryan Fernandez, Tony D. S. Raj, Abijeet V. Waghmare, Roland E. Haas
Publication Year : 2022
Unintended toxic effects of a medication occur due to drug-drug interactions (DDI) and drug-disease interactions (DDSI). It is the fourth leading cause of death in the US. To overcome this crisis, we have constructed the Drugomics knowledge graphs comprising DDI and DDSI interactions mined from Drugs@FDA, FAERS (FDA Adverse Events Reporting System), PubMed, literature, DailyMed, drug ontology, and other biomedical data sources. We used Artificial Intelligence and Augmented Intelligence (AI&AI) to translocate this actionable DDI and DDSI knowledge into a network and stored it in a Neo4j property graph database in a cloud for anytime-anywhere access. For the first time, we present here an AI-driven Evidence-Based Clinical Decision Support (AIdEB-CDS) system that accepts human understandable plain text inputs and extracts knowledge from knowledge graphs to offer the right therapeutics for the right disease for the right person at the right time at any Point-of-Care. This functions like a physicians’ brain digital twin to reduce clinical errors, reduce medication errors, and increase general health equity at a reduced cost. This will eliminate the patient harm caused by drug interactions.
https://link.springer.com/chapter/10.1007/978-3-031-24094-2_10