Bianca Maria Salvatore*¹, Marcella Falcone¹, Duccio Micela² and Marco Giacomelli

¹DOC Generici, Italy
²JSB Solutions, Italy

*Corresponding Author: Bianca Maria Salvatore, DOC Generici, Italy.

Received: October 19, 2022; Published: November 14, 2022

Abstract

Pharmacovigilance (PhV) detects, assesses and prevents adverse events (AEs) and other drug-related problems by collecting, evaluating, and acting upon AEs. The volume of individual case safety reports (ICSRs) increases yearly. In this landscape, embracing assistive technologies at scale becomes necessary to obtain a higher yield of AEs, to maintain compliance, and transform the PhV professional work life.

In accordance with current legislation, MAHs that have requested the authorization of a medicinal product have the obligation to monitor the safety profile of this product also by monitoring scientific literature. This activity must be regulated within the MAH's PhV system and must be carried out on a weekly basis; therefore, a considerable use of resources and time is required for this process. The project focus on the application of Artificial Intelligence (AI) to a PhV process such as the screening of medical-scientific literature. The aim of the project is to measure how much artificial intelligence can understand, evaluate and order the contents of scientific articles in order to identify an ICSR. It will be calculating the precision and accuracy with which the AI processes the data and whether it is able to directly establish the relationship between ADR and drug.

The data used to train the cognitive service of IBM Watson Knowledge Studio were an annotated corpus consisting of 74 case reports from MedLine database (PUBMED). The model developed and validated was imported into IBM Watson Discovery and 151 new articles have been tested by query into a JSB SOLUTIONS interface.

By applying the model, on a total of 151 articles, after making the queries, a list of 79 articles have been shown. All the articles have been screened to verify if they were ICSR or studies. 71 were ICSRs where the correct substance and ADR were found, 8 were false positive.

As AI is introduced to pharmacovigilance, new skills and competencies are required, these competencies are not considered all-inclusive for the field of computer science but serve as an indication of what skills a professional should acquire to work with AI in pharmacovigilance. Drug safety officers should develop the ability to understand concepts of artificial intelligence, natural language processing, machine learning and deep learning; also, should work on how to interact with and identify issues with artificial intelligence.

 Keywords: MAH: Marketing-authorisation Holders; PhV: Pharmacovigilance; ICSR: Individual Case Safety Report; AI: Artificial Intelligence; ADR: Adverse Drug Reaction

References

1. WHO Policy Perspectives on Medicines. Looking at the Pharmacovigilance: ensuring the safe use of medicines. Geneva: World Health Organization (2009).
2. European Medicines Agency (EMA). Guideline on good pharmacovigilance practices (GVP) Module VI—collection, management and submission of reports of suspected adverse reactions to medicinal product (Rev 2).
3. ICH harmonized tripartite guideline. Post t-approval safety data management: definitions and standards for expedited reporting e2d.
4. D Abatemarco., et al. “Training Augmented Intelligent Capabilities for Pharmacovigilance: Applying Deep-learning Approaches to Individual Case Safety Report Processing”. Pharmaceutical Medicine 32 (2018): 391-401.
5. H Yang., et al. “Post-marketing drug safety surveillance using publicly available health consumer contributed content in social media”. ACM Transactions on Management Information Systems 5 (2014): 2–21.
6. J Schmider., et al. “Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing”. Clinical Pharmacology and Therapeutics4 (2019).
7. R Mockute., et al. “Artificial Intelligence Within Pharmacovigilance: A Means to Identify Cognitive Services and the Framework for Their Validation”. Pharmaceutical Medicine 33 (2019): 109-120.
8. K Danysz., et al. “Artificial Intelligence and the Future of the Drug Safety Professional”. Drug Safety 42 (2019): 491-497.

Citation

Citation: Bianca Maria Salvatore., et al. “Artificial Intelligence Applied to Pharmacovigilance: Evaluation of Critical Issues in Relation to Real Opportunities". Acta Scientific Pharmaceutical Sciences 6.12 (2022): 12-19.

Copyright

Copyright: © 2022 Bianca Maria Salvatore., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.