#12 Improving signal detection with vigiGroup – Jim Barrett & Joe Mitchell

Statistical tools can not only cut through the noise in large
pharmacovigilance databases. They can also help identify more
clinically meaningful patterns in the data. Uppsala Monitoring
Centre’s Jim Barrett and Joe Mitchell explain how vigiGroup, a
novel clustering algorithm, can bring value to signal
detection.

Tune in to find out:


What the limits of traditional disproportionality analysis
are

How clustering algorithms can improve current signal
detection practices

How vigiGroup has helped monitor the safety of COVID-19
vaccines so far



Want to know more?


By applying vigiGroup to COVID-19 vaccine reports in
VigiBase, our Research team was able to identify a number of
potential safety signals. Find out more in this poster or in this
presentation. 

Details on how the vigiGroup method was developed and tested
can be found in the original publication in Artificial
Intelligence in Medicine.

Appendicitis was one of the possible safety signals for the
COVID-19 vaccines identified with vigiGroup.



For more on signal detection at Uppsala Monitoring Centre, visit
the Signal Work section on our website or listen to this
interview with Helena Sköld and Annette Rudolph on vaccine
pharmacovigilance.





Join the conversation on social mediaFollow us on
Facebook, LinkedIn, X, or Bluesky and share your thoughts about
the show with the hashtag #DrugSafetyMatters.

Got a story to share?We’re always looking for new
content and interesting people to interview. If you have a great
idea for a show, get in touch!

About UMCRead more about Uppsala Monitoring Centre
and how we work to advance medicines safety.