Developing a risk score for pancreatic cancer diagnosis

Using machine learning techniques applied to linked routine data: a pilot study

This project on pancreatic cancer initiated in 2019, with an award from the Pancreatic Cancer Research Fund.  The aim is to use historic GP and hospital data to identify patients who are most likely to have early stage pancreatic cancer. We are using machine learning techniques to understand if there are combinations of particular health problems, illnesses, or symptoms experienced only by patients who are later diagnosed. Ultimately, improving the triage of these patients means that targeted diagnostic tests could lead to the pancreatic cancer being diagnosed earlier and treated more effectively.

ESMO WCGIC 2020 | Machine learning techniques in pancreatic cancer screening | VJOncology

Machine learning techniques in pancreatic cancer screening presented at 2020 ESMO WCGIC and published in Annals of Oncology | ESMO World GI press release

For an ‘In Focus’ Blog Post published online by AJMC please click here.

This research has now been published in PLOS ONE:
Malhotra A, Rachet B, Bonaventure A, Pereira SP, Woods LM (2021) Can we screen for pancreatic cancer? Identifying a sub-population of patients at high risk of subsequent diagnosis using machine learning techniques applied to primary care data. PLOS ONE 16(6): e0251876.

For the related infographic go here or click on the image below.

Project Staff

Dr. Laura Woods

Principal Investigator
Associate Professor in Epidemiology

Dr. Ananya Malhotra

Research Fellow