No abstract

No abstract

The microbiome is now regarded as one of the hallmarks of cancer and several strategies to modify the gut microbiota to improve immune checkpoint inhibitor (ICI) activity are being evaluated in clinical trials. Preliminary data regarding the upper gastro-intestinal microbiota indicated that Helicobacter pylori seropositivity was associated with a negative prognosis in patients amenable to ICI. In 97 patients with advanced melanoma treated with ICI, we assessed the impact of H. pylori on outcomes and microbiome composition. We performed H. pylori serology and profiled the fecal microbiome with metagenomics sequencing. Among the 97 patients, 22% were H. pylori positive (Pos). H. pylori Pos patients had a significantly shorter overall survival ( p = .02 ) compared to H. pylori negative (Neg) patients. In addition, objective response rate and progression-free survival were decreased in H. pylori Pos patients. Metagenomics sequencing did not reveal any difference in diversity indexes between the H. pylori groups. At the taxa level, Eubacterium ventriosum, Mediterraneibacter (Ruminococcus) torques , and Dorea formicigenerans were increased in the H. pylori Pos group, while Alistipes finegoldii, Hungatella hathewayi and Blautia producta were over-represented in the H. pylori Neg group. In a second independent cohort of patients with NSCLC, diversity indexes were similar in both groups and Bacteroides xylanisolvens was increased in H. pylori Neg patients. Our results demonstrated that the negative impact of H. pylori on outcomes seem to be independent from the fecal microbiome composition. These findings warrant further validation and development of therapeutic strategies to eradicate H. pylori in immuno-oncology arena.

With the increasing use of immune checkpoint inhibitors (ICIs), there is an urgent need to identify biomarkers to stratify responders and non-responders using programmed death-ligand (PD-L1) expression, and to predict patient-specific outcomes such as progression free survival (PFS). The current study is aimed to determine the feasibility of building imaging-based predictive biomarkers for PD-L1 and PFS through systematically evaluating a combination of several machine learning algorithms with different feature selection methods. A retrospective, multicenter study of 385 advanced NSCLC patients amenable to ICIs was undertaken in two academic centers. Radiomic features extracted from pretreatment CT scans were used to build predictive models for PD-L1 and PFS (short-term vs. long-term survivors). We first employed the LASSO methodology followed by five feature selection methods and seven machine learning approaches to build the predictors. From our analyses, we found several combinations of feature selection methods and machine learning algorithms to achieve a similar performance. Logistic regression with ReliefF feature selection (AUC = 0.64, 0.59 in discovery and validation cohorts) and SVM with Anova F-test feature selection (AUC = 0.64, 0.63 in discovery and validation datasets) were the best-performing models to predict PD-L1 and PFS. This study elucidates the application of suitable feature selection approaches and machine learning algorithms to predict clinical endpoints using radiomics features. Through this study, we identified a subset of algorithms that should be considered in future investigations for building robust and clinically relevant predictive models.