Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study.

BACKGROUND: Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying cancer biology. We aimed to investigate the application of deep learning on chest CT scans to derive an imaging signature of response to immune checkpoint inhibitors and evaluate its added value in the clinical context. METHODS: In this retrospective modelling study, 976 patients with metastatic, EGFR/ALK negative NSCLC treated with immune checkpoint inhibitors at MD Anderson and Stanford were enrolled from Jan 1, 2014, to Feb 29, 2020. We built and tested an ensemble deep learning model on pretreatment CTs (Deep-CT) to predict overall survival and progression-free survival after treatment with immune checkpoint inhibitors. We also evaluated the added predictive value of the Deep-CT model in the context of existing clinicopathological and radiological metrics. FINDINGS: Our Deep-CT model demonstrated robust stratification of patient survival of the MD Anderson testing set, which was validated in the external Stanford set. The performance of the Deep-CT model remained significant on subgroup analyses stratified by PD-L1, histology, age, sex, and race. In univariate analysis, Deep-CT outperformed the conventional risk factors, including histology, smoking status, and PD-L1 expression, and remained an independent predictor after multivariate adjustment. Integrating the Deep-CT model with conventional risk factors demonstrated significantly improved prediction performance, with overall survival C-index increases from 0·70 (clinical model) to 0·75 (composite model) during testing. On the other hand, the deep learning risk scores correlated with some radiomics features, but radiomics alone could not reach the performance level of deep learning, indicating that the deep learning model effectively captured additional imaging patterns beyond known radiomics features. INTERPRETATION: This proof-of-concept study shows that automated profiling of radiographic scans through deep learning can provide orthogonal information independent of existing clinicopathological biomarkers, bringing the goal of precision immunotherapy for patients with NSCLC closer. FUNDING: National Institutes of Health, Mark Foundation Damon Runyon Foundation Physician Scientist Award, MD Anderson Strategic Initiative Development Program, MD Anderson Lung Moon Shot Program, Andrea Mugnaini, and Edward L C Smith.

PARP Inhibitors: Extending Benefit Beyond BRCA-Mutant Cancers.

A mounting body of evidence now indicates that PARP inhibitors have the potential to be used as a foundation for both monotherapy and combination strategies across a wide spectrum of molecular backgrounds and tumor types. Although PARP inhibitors as a class display many similarities, critical differences in structure can translate into differences in tolerability and antitumor activity that have important implications for the clinic. Furthermore, while PARP inhibitors have demonstrated a clear role in treating tumors with underlying homologous recombination deficiencies, there is now biological and early clinical evidence to support their use in other molecular subsets of cancer, including tumors associated with high levels of replication stress such as small-cell lung cancer. In this article, we highlight the key similarities and differences between individual PARP inhibitors and their implications for the clinic. We discuss data that currently support clinical strategies for extending the benefit of PARP inhibitors beyond BRCA-mutant cancers, toward broader populations of patients through the use of novel biomarkers of homologous recombination repair deficiency (HRD), as well as predictive biomarkers rooted in mechanisms of sensitivity outside of HRD. We also explore the potential application of PARP inhibitors in earlier treatment settings, including neoadjuvant, adjuvant, and even chemoprevention approaches. Finally, we focus on promising combination therapeutic strategies, such as those with other DNA damage response (DDR) inhibitors such as ATR inhibitors, immune checkpoint inhibitors, and non-DDR-targeted agents that induce "chemical BRCAness."