Improved prediction of immune checkpoint blockade efficacy across multiple cancer types

Only a fraction of patients with cancer respond to immune checkpoint blockade (ICB) treatment, but current decision-making procedures have limited accuracy. In this study, we developed a machine learning model to predict ICB response by integrating genomic, molecular, demographic and clinical data f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nature biotechnology Jg. 40; H. 4; S. 499 - 506
Hauptverfasser: Chowell, Diego, Yoo, Seong-Keun, Valero, Cristina, Pastore, Alessandro, Krishna, Chirag, Lee, Mark, Hoen, Douglas, Shi, Hongyu, Kelly, Daniel W., Patel, Neal, Makarov, Vladimir, Ma, Xiaoxiao, Vuong, Lynda, Sabio, Erich Y., Weiss, Kate, Kuo, Fengshen, Lenz, Tobias L., Samstein, Robert M., Riaz, Nadeem, Adusumilli, Prasad S., Balachandran, Vinod P., Plitas, George, Ari Hakimi, A., Abdel-Wahab, Omar, Shoushtari, Alexander N., Postow, Michael A., Motzer, Robert J., Ladanyi, Marc, Zehir, Ahmet, Berger, Michael F., Gönen, Mithat, Morris, Luc G. T., Weinhold, Nils, Chan, Timothy A.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York Nature Publishing Group US 01.04.2022
Nature Publishing Group
Schlagworte:
631/114/2413
631/67/69
692/53/2421
692/699/67
Agriculture
Bioinformatics
Biomarkers, Tumor - genetics
Biomedical and Life Sciences
Biomedical Engineering/Biotechnology
Biomedicine
Biotechnology
Cancer
Clinical decision making
Decision making
Genomics
Humans
Immune checkpoint
Immune Checkpoint Inhibitors - therapeutic use
Immunotherapy
Immunotherapy - methods
Life Sciences
Machine learning
Mutation
Neoplasms - drug therapy
Neoplasms - genetics
Patients
Predictions
Retrospective Studies
Survival
Tumors
ISSN:1087-0156, 1546-1696, 1546-1696
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Only a fraction of patients with cancer respond to immune checkpoint blockade (ICB) treatment, but current decision-making procedures have limited accuracy. In this study, we developed a machine learning model to predict ICB response by integrating genomic, molecular, demographic and clinical data from a comprehensively curated cohort (MSK-IMPACT) with 1,479 patients treated with ICB across 16 different cancer types. In a retrospective analysis, the model achieved high sensitivity and specificity in predicting clinical response to immunotherapy and predicted both overall survival and progression-free survival in the test data across different cancer types. Our model significantly outperformed predictions based on tumor mutational burden, which was recently approved by the U.S. Food and Drug Administration for this purpose 1 . Additionally, the model provides quantitative assessments of the model features that are most salient for the predictions. We anticipate that this approach will substantially improve clinical decision-making in immunotherapy and inform future interventions. A combination of genomic and clinical features improves predictions of response to immune checkpoint blockade.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
D.C., S.-K.Y., C.V., A.P., L.G.T.M., N.W. and T.A.C conceived and designed the study. D.C. and S.-K.Y. developed the machine learning model. D.C., S.-K.Y., C.V., A.P., C.K., M.L., D.H., H.S., D.W.K., N.P., V.M., K.W., T.L., R.M.S., N.R., P.S.A., V.P.B., G.P., A.A.H., A.N.S., M.A.P., R.J.M, M.L., A.Z., M.F.B., L.G.T.M. and N.W. acquired, analyzed or interpreted the data. M.G. provided statistical advice. All authors critically revised the manuscript for important intellectual content. L.G.T.M., N.W. and T.A.C. supervised the study.
Author contributions
ISSN:1087-0156
1546-1696
1546-1696
DOI:10.1038/s41587-021-01070-8