Identification of a serum proteomic biomarker panel using diagnosis specific ensemble learning and symptoms for early pancreatic cancer detection.
Alexander NeyNuno R NenéEva SedlakPilar AcedoOleg BlyussHarry J WhitwellEithne CostelloAleksandra Gentry-MaharajNorman R WilliamsUsha MenonGiuseppe K FusaiAlexey ZaikinStephen P PereiraPublished in: PLoS computational biology (2024)
Our ensemble modelling technique outperformed CA19-9, individual biomarkers and indices developed with prevailing algorithms in distinguishing patients with non-specific but concerning symptoms from those with PDAC, with implications for improving its early detection in individuals at risk.