Prediction of clinical response to checkpoint blockade immunotherapy is improved with ensembling - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

Prediction of clinical response to checkpoint blockade immunotherapy is improved with ensembling

Résumé

Predicting clinical response to checkpoint blockade immunotherapy is a major challenge in oncology. In the case of melanoma, we show how prediction is improved with the use of averaging, a simple ensembling method in machine learning. We report +3.7 percent improvement of the best response predictor (from AUC=0.81 to AUC=0.84), on a clinical dataset of 70 patients.
Fichier principal
Vignette du fichier
immuno_paper_new.pdf (48.63 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02123700 , version 1 (08-05-2019)

Identifiants

  • HAL Id : hal-02123700 , version 1

Citer

Mostapha Benhenda. Prediction of clinical response to checkpoint blockade immunotherapy is improved with ensembling. 2019. ⟨hal-02123700⟩
213 Consultations
356 Téléchargements

Partager

Gmail Facebook X LinkedIn More