What question did this study set out to answer?

The research aims to evaluate the predictive performance of CT models for PD-L1 status in non-small cell lung cancer.

April 1, 2026Radiology0 citations

Independent Testing of Published CT Models for PD-L1 Status in Non–Small Cell Lung Cancer

RORobert O’SheaKing's College London CHCarolyn Anne Kirby HorstKing's College London TMThubeena ManickavasagarRoyal Marsden NHS Foundation Trust

Key Points

The research aims to evaluate the predictive performance of CT models for PD-L1 status in non-small cell lung cancer.
Conducted independent testing of published CT predictive models.
Assessed discrimination of PD-L1 expression at clinically relevant thresholds.
Focused on patients with resectable non-small cell lung cancer.
CT models successfully discriminated PD-L1 expression in the tested group.
Predictive performance was found to be lower than originally published values.

Abstract

In independent testing, CT predictive models discriminated programmed death ligand-1 expression in patients with resectable non–small cell lung cancer at clinically relevant thresholds, but predictive performance was lower than initially published.

AI से पूछें

Bookmark

View Full Paper