Characterization of unique pattern of immune cell profile in patients with nasopharyngeal carcinoma through flow cytometry and machine learning.

In patients with nasopharyngeal carcinoma (NPC), the alteration of immune responses in peripheral blood remains unclear. In this study, we established an immune cell profile for patients with NPC and used flow cytometry and machine learning (ML) to identify the characteristics of this profile. After isolation of circulating leukocytes, the proportions of 104 immune cell subsets were compared between NPC group and the healthy control group (HC). Data obtained from the immune cell profile were subjected to ML training to differentiate between the immune cell profiles of the NPC and HC groups. We observed that subjects in the NPC group presented higher proportions of T cells, memory B cells, short-lived plasma cells, IgG-positive B cells, regulatory T cells, MHC II+ T cells, CTLA4+ T cells and PD-1+ T cells than subjects in the HC group, indicating weaker and compromised cellular and humoral immune responses. ML revealed that monocytes, PD-1+ CD4 T cells, memory B cells, CTLA4+ CD4 Treg cells and PD-1+ CD8 T cells were strongly contributed to the difference in immune cell profiles between the NPC and HC groups. This alteration can be fundamental in developing novel immunotherapies for NPC.

Artificial intelligence-based immunoprofiling serves as a potentially predictive biomarker of nivolumab treatment for advanced hepatocellular carcinoma.

Immune checkpoint inhibitors (ICI) have been applied in treating advanced hepatocellular carcinoma (aHCC) patients, but few patients exhibit stable and lasting responses. Moreover, identifying aHCC patients suitable for ICI treatment is still challenged. This study aimed to evaluate whether dissecting peripheral immune cell subsets by Mann-Whitney U test and artificial intelligence (AI) algorithms could serve as predictive biomarkers of nivolumab treatment for aHCC. Disease control group carried significantly increased percentages of PD-L1+ monocytes, PD-L1+ CD8 T cells, PD-L1+ CD8 NKT cells, and decreased percentages of PD-L1+ CD8 NKT cells via Mann-Whitney U test. By recursive feature elimination method, five featured subsets (CD4 NKTreg, PD-1+ CD8 T cells, PD-1+ CD8 NKT cells, PD-L1+ CD8 T cells and PD-L1+ monocytes) were selected for AI training. The featured subsets were highly overlapping with ones identified via Mann-Whitney U test. Trained AI algorithms committed valuable AUC from 0.8417 to 0.875 to significantly separate disease control group from disease progression group, and SHAP value ranking also revealed PD-L1+ monocytes and PD-L1+ CD8 T cells exclusively and significantly contributed to this discrimination. In summary, the current study demonstrated that integrally analyzing immune cell profiling with AI algorithms could serve as predictive biomarkers of ICI treatment.