By: Dr. Seema Nair, Life Sciences Lead - Customer Success Team, CMT

The Pharmacovigilance (PV or PhV) process is among the most labor-intensive processes in the Pharma industry, with the added complexity of strict regulations and timelines, since it is all about drug safety. Traditionally, PV has been monitored by health care professionals, whose main task is to identify the adverse events reported and classify them based on the severity and create reports for regulatory authorities and suggest actions. In the recent past, the number of incidents reported has seen a spike due to the increase in the number of reporting channels, including social media, which makes the PV more laborious.

Both clinical and post-market PV pose a unique set of challenges that traditional tools and technologies struggle to meet, and this encouraged pharma companies to look for cost-effective and efficient options like RPA. Also, AI is being explored for operational efficiencies in the AE (Adverse Event) processing, and activities such as medical review, causality assessments, signal and risk management to name a few.

Intelligent RPA can simplify and accelerate the PV by automating the repetitive, rule-based tasks and help in checking the quality and accuracy of the reports created. RPA often needs to be complemented with Natural Language Processing (NLP), Image Processing, Optical Character Recognition (OCR), and rule-based prioritization techniques to process unstructured datasets for a more robust solution. Some of the popular areas where RPA has been used include:

• Acknowledgement emails and their follow up
• Source documents management
• Mapping WHO products
• Checking chronology of dates in reports
• Cross-verifying duplicate cases, completeness check

Roadmap to adoption of Intelligent RPA in PV
The industry adoption in the PV space is relatively slow because this is usually carried out in closed, core enterprise Safety Database (SDB), dominated with two major vendors – Oracle and ARIS Global. Also, this is subjected to frequent system upgrades, partly driven by changing regulatory requirements. Additionally, there is a lot of unstructured data input which warrants interventions to automate processing of complex documents. Despite the challenges, Intelligent RPA is arguably the most favored technology due to its competence and cost-efficiency proposition, and can lead to improvement in safety, compliance and overall quality.