Pharmacovigilance

AI extracts adverse-event data from unstructured and semi-structured documents to support pharmacovigilance and earlier side-effect detection.

Business impact

• adverse-event processing time — The solution is intended to automate extraction from source documents, which supports faster processing, though no figure is reported.
• side-effect detection timing — The article says the approach helps spot drug-associated side effects earlier.

Data requirements

• adverse-event source documents (text) — The system pulls adverse-event data from unstructured and semi-structured documents.

AI methods and techniques

• optical character recognition — Used to extract adverse-event information from source documents.
• robotic process automation — Used to move adverse-event data through the processing workflow.
• natural language processing — Used to interpret information in unstructured documents.
• machine learning — Used as part of the PVAI solution to support adverse-event processing.

Industries

Real-world evidence

2 documented case studies on record.

Companies using this: Bayer, D & A MedLabs.