Skip to main content
Dryad logo

Deep learning to estimate durable clinical benefit and prognosis from patients with non-small cell lung cancer treated with PD-1/PD-L1 blockade

Citation

Jie, Peng (2022), Deep learning to estimate durable clinical benefit and prognosis from patients with non-small cell lung cancer treated with PD-1/PD-L1 blockade, Dryad, Dataset, https://doi.org/10.5061/dryad.hdr7sqvmf

Abstract

Different biomarkers based on genomics variants have been used to predict the response of patients treated with PD-1/programmed death receptor 1 ligand (PD-L1) blockade. We aimed to use deep-learning algorithm to estimate clinical benefit in patients with non-small-cell lung cancer (NSCLC) before immunotherapy. Peripheral blood samples or tumor tissues of 915 patients from three independent centers were profiled by whole-exome sequencing or next-generation sequencing. Based on convolutional neural network (CNN) and three conventional machine learning (cML) methods, we used multi-panels to train the models for predicting the durable clinical benefit (DCB) and combined them to develop a nomogram model for predicting prognosis. In the three cohorts, the CNN achieved the highest area under the curve of predicting DCB among cML, PD-L1 expression, and tumor mutational burden (area under the curve [AUC] = 0.965, 95% confidence interval [CI]: 0.949–0.978, P < 0.001; AUC =0.965, 95% CI: 0.940–0.989, P < 0.001; AUC = 0.959, 95% CI: 0.942–0.976, P < 0.001, respectively). Patients with CNN-high had longer progression-free survival (PFS) and overall survival (OS) than patients with CNN-low in the three cohorts. Subgroup analysis confirmed the efficient predictive ability of CNN. Combining three cML methods (CNN, SVM, and RF) yielded a robust comprehensive nomogram for predicting PFS and OS in the three cohorts (each P < 0.001). The proposed deep-learning method based on mutational genes revealed the potential value of clinical benefit prediction in patients with NSCLC and provides novel insights for combined machine learning in PD-1/PD-L1 blockade.

Funding

National Natural Science Foundation of China, Award: 82060327