An Algorithm as a Biomarker for Response to Immune Checkpoint Inhibitor Therapy
Menée à partir de données portant sur 446 patients atteints d'un cancer du poumon non à petites cellules de stade avancé traité par inhibiteur de point de contrôle immunitaire (durée médiane de suivi : 38,1 mois) puis validée à partir de données portant sur 239 patients supplémentaires (durée médiane de suivi : 43,3 mois), cette étude multicentrique évalue l'association entre le niveau d'infiltration de la tumeur par les lymphocytes, déterminé à l'aide d'un algorithme d'apprentissage automatique utilisant des images histologiques standard, et la réponse au traitement
A negotiating strategy that leaders use is to ask, “What would it take?” In light of the weak predictive biomarkers used for immune checkpoint inhibitor (ICI) therapy, it may be time to ask the pathologist “What would it take to provide us with a quantitative tumor infiltrating lymphocyte (TIL) score for each patient with non–small-cell lung cancer?” In this issue of JAMA Oncology, Rakaee et al describe a new biomarker associated with response to ICI based on an objective, open-source, machine learning (ML) method using QuPath software to count TILs in lung cancer. They note that TIL has potential to improve selection of responders to ICI and that ML-TIL is easily obtained, accurate, and reproducible. They created an ML-TIL algorithm and then tested it on a training set to show how TIL count is associated with response to programmed cell death (PD) 1/PD ligand 1 axis single-agent ICI therapy. This was shown in 2 large, retrospective non–small-cell lung cancer cohorts in the training set/validation set format. They also showed that the ML-TIL is particularly valuable in PD ligand 1–negative patients and has a stronger association with outcomes than tumor mutation burden.
JAMA Oncology , éditorial en libre accès, 2021