Process Mining in Primary Care: Avoiding Adverse Events Due to Hazardous Prescribing

Research output: Contribution to journalArticle

  • External authors:
  • Eric Rojas
  • Owen Johnson


Process mining helps understand processes within healthcare. While often used in secondary care, there is little work using primary care data.
Serious adverse events that result from hazardous prescrib-ing are common and costly. For example, non-steroidal anti-inflammatory drugs (NSAIDs) and antiplatelets which can cause gastro-intestinal bleeds (GiBs). Prescribing typically occurs within primary care, therefore we used this setting to attempt process mining.
Certain patients should be prescribed gastro-protection alongside NSAIDs or antiplatelets. We extracted events (drug started, drug stopped, GiB) for understanding three prescrib-ing pathways, and applied process mining.
We found NSAIDs are often short-term prescriptions whereas antiplatelets are often long-term. This perhaps explains our finding that co-prescription of gastro-protection is more prevalent for antiplatelets than NSAIDs. We identified rea-sons why primary care data is harder to process mine and proposed solutions. Process mining primary care data is pos-sible and likely useful for improving patient safety and re-ducing costs.

Bibliographical metadata

Original languageEnglish
JournalStudies in Health Technology and Informatics
Publication statusAccepted/In press - 21 Aug 2019