A game changer in the pharmaceutical industry
SELTA SQUARE automates a core process for drug safety monitoring using IBM RPA

Sometimes a small startup can make a huge impact.

In 2020, leading South Korean pharmaceutical R&D company Daewoong Pharmaceutical helped launch a new company that has the potential to innovate a critical process for the entire industry — and enhance consumer safety as a result.

The company is SELTA SQUARE, and the process it’s innovating is pharmacovigilance (PV), a legally mandated discipline for detecting and reporting adverse effects from drugs, then assessing, understanding and preventing those effects. PV must be performed not only during the clinical trials phase but through the whole lifetime of drugs as available products. It demands a great deal of effort and diligence from pharma producers.

SELTA SQUARE, however, has applied IBM® Robotic Process Automation (RPA) software and self-developed AI algorithms to run a first-of-its-kind, automated PV service that it is offering locally and globally. This could be a game changer for the way that pharma companies ensure consumer safety.

Accelerated Processes


SELTA SQUARE accelerated the PV process > 4x using IBM RPA

Faster Search


Searches that took 5 minutes each were reduced to 1 min 11 sec on average

We are just beginning to help organizations experience innovation through the value of this PV solution. 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. Min Kyung Shin CEO SELTA SQUARE
Critical but tedious work

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.

RPA boosts speed, humans boost quality

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.”

Potential for global innovation

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.

Next up:
View case study PDF Bureau voor Normalisatie (NBN)
Belgium’s NBN does more in less time with IBM Robotic Process Automation software
Read the case study
Deloitte streamlines report production with suite of RPA bots
Read the case study
System of Credit Unions of Brazil (Sicoob)
Sicoob radically boosts process efficiencies with IBM Robotic Process Automation software
Read the case study
Legal terms

© Copyright IBM Corporation 2022. IBM Corporation, New Orchard Road, Armonk, NY 10504

Produced in the United States of America, September 2022.

IBM, the IBM logo, ibm.com are trademarks of International Business Machines Corp., registered in many jurisdictions worldwide. Other product and service names might be trademarks of IBM or other companies. A current list of IBM trademarks is available on the web at “Copyright and trademark information” at www.ibm.com/legal/copytrade.

This document is current as of the initial date of publication and may be changed by IBM at any time. Not all offerings are available in every country in which IBM operates.

The performance data and client examples cited are presented for illustrative purposes only. Actual performance results may vary depending on specific configurations and operating conditions. THE INFORMATION IN THIS DOCUMENT IS PROVIDED “AS IS” WITHOUT ANY WARRANTY, EXPRESS OR IMPLIED, INCLUDING WITHOUT ANY WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND ANY WARRANTY OR CONDITION OF NON-INFRINGEMENT. IBM products are warranted according to the terms and conditions of the agreements under which they are provided.

The client is responsible for ensuring compliance with laws and regulations applicable to it. IBM does not provide legal advice or represent or warrant that its services or products will ensure that the client is in compliance with any law or regulation.