A game changer in the pharmaceutical industry

More medicines are being developed all the time. The number of new medicines entering the market globally from 2017 through 2021 exceeded the previous five-year period by 47% (link resides outside of ibm.com). And projections indicate further growth through 2026.

As new medicines are developed, even the most extensive clinical trials cannot account for every way that the medicines could interact with individuals and other drugs. That’s why PV is so important. It is the core process for drug safety.

But the information about drugs’ effects in the population — especially after they’ve been released to market — is complex and comes from myriad sources. Before using RPA, Daewoong Pharmaceutical’s PV team conducted a weekly PV process for more than 100 of the company’s products, including medicines for high-risk conditions, such as PRS inhibitors and pulmonary fibrosis treatments, where global data collection is essential to ensuring safety.

The process involved extensive searches — in global and national databases as well as less-structured sources like medical literature and case reports — seeking any data on adverse reactions and events, atypical lab results and more. And the team had to search on every product name as well as the names of each product’s active pharmaceutical ingredients (APIs). Fixed-dose combinations of multiple APIs sometimes require additional searches.

Along with the searches, PV personnel needed to take and save screenshots, download source documents, document search results and upload the data to a Daewoong Pharmaceutical server.

For each one of the 100 products, it normally took one team member a full workday to complete the PV process.

The opportunity for automation was clear, but a first attempt led to flawed results. The PV team used third-party RPA software to automate the search process. The software converted findings into Microsoft Excel spreadsheet data, and incompatibility between Excel and some data sources required manual rework and corrections, delaying reporting and offsetting the efficiency gains from the automation.

Nonetheless, the team knew they were on the right path. They just needed a better solution.

More than just a new iteration, the next version of the solution was a true innovation, and it led to the launch of SELTA SQUARE as its own company. SELTA SQUARE worked with IBM to replace the previous RPA software with IBM RPA and move the solution to the web, creating Korea’s first PV-as-a-service (PVaaS) system. “We knew we had something special,” says Min Kyung Shin, Chief Executive Officer (CEO) of SELTA SQUARE. “The web-based service could easily be provided to other companies. It was innovation too valuable to keep bottled up.”

SELTA SQUARE eliminated the data-incompatibility problem and achieved consistent performance by using the IBM RPA software to validate all data through the computerized system validation (CSV) process, which complies with industry regulations for ensuring data integrity, such as the US Food and Drug Administration’s FDA21 CFR Part 11 guidelines and the International Society for Pharmaceutical Engineering (ISPE) GAMP 5 guidelines.

The new accuracy meant that the team could fully realize the value of an automated system. Not only does the RPA solution perform the literature searches much faster than humans, it can also work around the clock — compounding the benefit. And it incorporates SELTA SQUARE’s AI to reduce the time spent on simple, repetitive tasks — such as detecting and eliminating duplicate findings. “First, IBM RPA searches the literature for the key terms, then SELTA SQUARE's AI Case Detector operates on the papers identified by the RPA search and highlights new safety information,” says Shin. “Human experts still decide how to act upon the information, now they just get to the key information much faster.”

The PV process is now more than four times faster than before, and the time saved is time that human staff use to enhance PV’s quality.

Shin explains: “Previously, it took about 5 minutes on average per search term just for literature searches. And according to our own investigation, other companies take similar time. The new RPA solution takes an average of only 1 minute and 11 seconds per search term — and it is done while you sleep. So PV specialists can now make medical decisions by looking at the retrieved literature, they no longer have to spend hours searching. Our team now focuses more on reviewing, evaluating and analyzing valid cases, and it’s improving the quality of overall literature monitoring.”

SELTA SQUARE officially launched its automated PVaaS service in July 2022. “We are just beginning to help organizations experience innovation through the value of this PV solution,” says Shin. “We can systematically handle many things in accordance with the constantly tightening PV regulations, and furthermore, we will contribute to providing safer medicines to people around the world.”

SELTA SQUARE (link resides outside of ibm.com) offers the pharmaceutical industry a new normal for pharmacovigilance. As the only company applying Industry 4.0 technology to PV, SELTA SQUARE provides a platform for the safety of pharmaceuticals to be monitored and assessed more systematically and scientifically. It works with its customers to increase PV efficiency, reduce cost, and save time for professionals to do higher-value work. As it moves forward, SELTA SQUARE expects to contribute to greater drug safety for more people.