Automation Potential in: Adverse Event Reporting
An Adverse Event (AE) is described as “any untoward medical occurrence” in a patient receiving a medicine. These events include everything from so called “non-serious” side effects such as nausea to more serious events such as reports of malignancy. Our client dealt with more than 100,000 of these per year, which is a mandatory legal responsibility.
It’s estimated that large pharmaceutical companies process between 500-700,000 adverse event cases each year and that the processing of these cases equates to around half of output from Pharmacovigilance teams. These cases often come from a variety of different systems and the data varies in quality, structure and format.
Automation Impact Evaluation
Most pharmaceuticals have a CRM in place to track AE cases which come in through various channels. These cases are typically reliant on doctors, clinical specialists etc entering the right amount of detail into cases, so specialists can determine if a case was deemed to have an adverse effect. The problem arises that with different language and descriptions used as well as personal bias as to the severity of an issue, it can be very difficult for pharmacovigilance teams to assess which cases are priority.
Through a combination of machine learning and RPA (Robotic Process Automation) organisations can develop a framework of keywords that will be most likely associated with an AE cases. The bot can then identify these words against background factors such as age, sex, underlying conditions, additional medication and medical history. Using these two factors a bot would then give a percentage, with the higher the percentage, the more likely it was an AE case. As time goes on and the bot analyses more and more cases its accuracy would increase.
This use case demonstrates the way in which technology should be inputted. Automation will never be able to take away the job of the highly trained pharmacovigilance team, but it can make them more efficient and ensure tat they effectively prioritise their work.
Our client dealt with more than 100,000 AE cases per year, a mandatory legal responsibility.
We were able to develop a framework that included keywords often associated with AE cases, as well as background factors such as age, sex, underlying conditions, additional medication, medical history. Each day the bot would extract the information and highlight the cases to the expert that were most likely to be adverse events.
The original success rate of the bot was 70%, but as more information was fed into the system and the parameters could be adjusted this rose to 89% and meant more of the specialist time was spent dealing with the right cases.