International Research Journal of Innovations in Engineering and Technology (IRJIET)
ISSN (online): 2581-3048
Volume 8, Issue 9, pp 194-197, September-2024
https://doi.org/10.47001/IRJIET/2024.809024
© 2024-2017 IRJIET All Rights Reserved www.irjiet.com 194
Enhancing Drug Safety: AIs Role in Pharmacovigilance
and Adverse Event Reporting
Hannah Alex
School of Pharmacy, University of Pittsburgh, USA
Abstract - The role of pharmacovigilance (PV) in
healthcare is to optimize the safety and efficacy of the
delivery of pharmaceutical drugs and medical equipment.
The increasingly dynamic nature of adverse drug reactions
and pharmacovigilance has rendered traditional
approaches susceptible to the underreporting of ADRs.
Subsequently, the integration of Artificial intelligence in
adverse drug reaction reporting is an outstanding
technological advancement in pharmacovigilance.
Therefore, this critical analysis applied a systematic
literature review to comprehend the extensive role of AI in
Pharmacovigilance. The research findings acknowledged
that AI technologies such as machine learning, deep
learning, and natural learning processing (NLP) have
automated PV, leading to enhanced signal detection,
analysis of unstructured data, risk assessment, and
regulatory compliance.
Keywords: Pharmacovigilance (PV), natural learning
processing, adverse drug reactions (ADR), signal detection,
deep learning, Artificial intelligence, and machine learning.
I. INTRODUCTION
In a field as complex as medicine, the role of AI is
inevitable. Pharmacovigilance (PV) and Adverse Event
Reporting (AER) are meant to help physicians “do no harm”
(Bate and Stegmann 20). These concepts are dedicated to
monitoring the impacts of pharmacological drugs after
licensure and involve continuous surveillance of the side
effects, besides analyzing voluminous scopes of data to find
existing and developing unknown side effects (Vickers-Smith
et al. 203). Therefore, the voluminous scope of data, high
degree of uncertainty, and need to learn from data justify the
relevance and applicability of AI in PV and AER.
Subsequently, this analysis applies a systematic literature
methodology to extensively and critically evaluate the role of
AI in Pharmacovigilance and Adverse Event Reporting
(AER).
II. LITERATURE REVIEW
Existing studies have also compared the effectiveness of
AI-based and traditional approaches in PV, monitoring and
reporting of Adverse drug reactions. For example, in
predictive analytics tasks such as identifying complex patterns
in Symptoms data and pharmacoepidemiology, AI-based
approaches were more reliable than traditional PV methods
(Bate and Stegmann 23). Notably, a systematic review of 44
studies was undertaken by Sessa et al. to compare the
application of AI and traditional approaches for tasks such as
predicting the occurrence or severity of Adverse drug
responses and propensity scores (p.121). For instance, despite
not performing quality assessments for studies, AI
outperformed traditional mechanisms in 50% of the studies
Multiple studies have also attempted to demonstrate the
complexity and costs involved in individual case safety reports
(ICSRs) to justify the implementation of AI in PV and AER.
For example, a 2021 GSK study concluded that the estimated
average cost of processing an individual case report was $33
and even higher across pharmaceutical companies (Beninger
et al. 1229; Stergiopoulos et al. 506). In 2021, Navitaspvnet
and pvconnect also conducted an annual survey of
pharmaceutical companies' cost per ICSR processing (Bate
and Stegmann 23). The findings showed the median was
US$86 for Pvnet and $345 in Pvconnect’s survey (Bate and
Stegmann 24). Consequently, such processing costs have
increased the allure of AI automation regardless of the high
initial implementation costs.
Besides, the evolving nature of the pharmaceutical
landscape is characterized by the increased volume and
complexity of the new drugs and therapeutics available
annually. The continuous introduction of different drugs has
also increased the scope of advanced events reported,
prompting the need for technological integration for quality,
real-time, convenient and automated drug safety monitoring.
For example, Patel et al. point out a 300% increase in the
adverse events reported by the FDA Adverse Event Reporting
System (FAERS) between 2009 and 2019, further increasing
to 2.2 million AE reports by 2021.
III. PROPOSED METHODOLOGY
The proposed research methodology was a systematic
literature review of research articles published between 2010
and 2024. This proposed methodology has also been
previously adopted in similar studies examining the role of AI
in PV, such as those by Sessa et al. and Bate and Stegmann.