BioModels

This is a Random Forest algorithm-based machine learning model called RF16, which incorporates a total of 16 genomic, molecular, demographic, and clinical features to predict the immunotherapy response for a patient. The model assigns a value of 0 for NonResponder and 1 for Responder. Please be aware that the column names in the GitHub code and the downloaded dataset from the publication may vary. Users are advised to make minor adjustments to either the code or the dataset to ensure compatibility. The curated version of the model has modified the column names in the training code to align with the dataset. GitHub repository: https://github.com/CCF-ChanLab/MSK-IMPACT-IO

• Improved prediction of immune checkpoint blockade efficacy across multiple cancer types.
• Diego Chowell, Seong-Keun Yoo, Cristina Valero, Alessandro Pastore, Chirag Krishna, Mark Lee, Douglas Hoen, Hongyu Shi, Daniel W Kelly, Neal Patel, Vladimir Makarov, Xiaoxiao Ma, Lynda Vuong, Erich Y Sabio, Kate Weiss, Fengshen Kuo, Tobias L Lenz, Robert M Samstein, Nadeem Riaz, Prasad S Adusumilli, Vinod P Balachandran, George Plitas, A Ari Hakimi, Omar Abdel-Wahab, Alexander N Shoushtari, Michael A Postow, Robert J Motzer, Marc Ladanyi, Ahmet Zehir, Michael F Berger, Mithat Gönen, Luc G T Morris, Nils Weinhold, Timothy A Chan
• Nature biotechnology , 4/ 2022 , Volume 40 , Issue 4 , pages: 499-506 , PubMed ID: 34725502
Affiliation: Human Oncology and Pathogenesis Program, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Abstract: 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 purpose¹. 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.