pharma

Pharmacovigilance is the science and activities relating to the detection, assessment, understanding and prevention of adverse effects with pharmaceutical products. This surveillance starts once the drug is approved for market use, after successful clinical trial completion. Though PV processes can vary across organizations, there are certain requirements that are universal, such as signal detection, risk management, and adverse event reporting. Some of these processes often take up a significant amount of time and resources and are repetitive and manual.

A Deloitte survey shows that more and more pharma companies are investing in automation solutions for their pharmacovigilance processes. According to a study, 90% of companies’ goal is to slash case processing costs by automating and implementing AI in the process.

How is AI applied in PV?

Literature screening is one of the most time consuming parts of the PV process. It involves identifying articles that contain information about serious and non-serious adverse events associated with a particular medicinal product. However, doing this manually is extremely time consuming and labor intensive. Pharmaceutical companies struggle with retrieving and analyzing scientific and medical literature. One challenge they face is developing a good search strategy. Another is understanding and extracting information from the unstructured content found within the literature. Finally, they must convert the content into adverse event data so that it can be loaded into a safety database. Automating these processes with AI – which is only now becoming possible, thanks to improvements in NLP technology – can save them time and money, reduce the workload, increase efficiency and cut out human error. For example, AI can automatically identify the most relevant adverse events and extract and clean that data. 

Iris.ai Approach

With our Iris.ai tools you can automatically find the documents you need from any written text on the topic, such as research papers, patents, case reports, clinical trial reports, etc and extract all relevant information. Freeing up this time will enable PV professionals to spend time on more valuable-added tasks.

Problem

Our clients used to spend a lot of time on systematic review tasks. Diligence, attention to detail, and rigor is key, yet even at full focus human accuracy in these tasks is measured to 86%. Spending 80 hours narrowing down a reading list of 500 documents to the 40 key relevant ones, extracting all the relevant clinical data, writing a summary and a report – and repeating the full exercise on a yearly basis – is a time drain. That time is essential in preventing any more severe outcomes from adverse events.

Solution

With the Iris.ai Workspace, our clients can analyze the document set for entities (disease/drug/device), clinical data points, and contexts of interest and rapidly filter the sets down to the most relevant documents. Clinical data extraction is fully automated, populating orderly excel sheets with data from documents in seconds. Summaries for kicking off the meta-analysis are written by the machine. The review can be automated at regular intervals, and a compliance report generated.

Benefits

The Iris.ai tools can reduce the time for a systematic review for compliance or pharmacovigilance by up to 75%. The accuracy is on par with human performance (>85%). Contractors can take on more assignments at higher margins, while pharma companies can reduce the time they spend on these tasks.

Benefits of PV automation

As our customers have confirmed – in pharmacovigilance, partial automation can eliminate human error, reduce costs and time spent on paperwork. Automating pharmacovigilance helps pharmaceutical companies comply with drug safety regulations, raise reporting volumes and speed up the process.

Key Takeaways

In recent years, there has been a lot of discussion about how to effectively use AI for pharmacovigilance. It can be used for literature screening which includes identifying abstracts and articles that contain information about adverse effects and extracting them. AI can save them time and money, reduce the workload and increase efficiency. 

Sign up to our newsletter for more content about digitizing R&D.