Pre-treatment comorbidities, C-reactive protein and eosinophil count, and immune-related adverse events as predictors of survival with checkpoint inhibition for multiple tumour entities

A two-stage ensemble learning based prediction and grading model for PD-1/PD-L1 inhibitor-related cardiac adverse events: A multicenter retrospective study

BACKGROUND

Immune-related cardiac adverse events (ircAEs) caused by programmed cell death protein-1 (PD-1) and programmed death-ligand-1 (PD-L1) inhibitors can lead to fulminant and even fatal consequences. This study aims to develop a prediction and grading model for ircAEs, enabling graded management of patients.

METHODS

This study utilized medical record systems from two medical institutions to develop a prediction and grading model for ircAEs using ten machine learning algorithms and two variable screening methods. The model was developed based on a two-stage ensemble learning framework. In the first stage, the ircAEs and non-ircAEs cases were classified. In the second stage, ircAEs cases were grouped into grades 1-2 and 3-5. The experiments were evaluated using five-fold cross-validation. The model's prediction performance was assessed using accuracy, precision, recall, F1 value, Brier score, receiver operating characteristic curve area (AUC), and area under the precision-recall curve (AUPR).

RESULTS

615 patients were included in the study. 147 experienced ircAEs, and 44 experienced grade 3-5 ircAEs. The soft voting classifier trained using the variables screened by feature importance ranking performed better than other classifiers in both stages. The average AUC for the first and second stages is 84.18 % and 85.13 %, respectively. In the first stage, the three most important variables are N-terminal B-type natriuretic peptide (NT-proBNP), interleukin-2 (IL-2), and C-reactive protein (CRP). In the second stage, the patient's age, NT-proBNP, and left ventricular ejection fraction (LVEF) are the three most critical variables.

CONCLUSIONS

The prediction and grading model of ircAEs based on two-stage ensemble learning established in this study has good performance and potential clinical application.

Interleukin-7 Risk Allele, Lymphocyte Counts, and Autoantibodies for Prediction of Risk of Immune-Related Adverse Events in Patients Receiving Atezolizumab plus Bevacizumab Therapy for Unresectable Hepatocellular Carcinoma

INTRODUCTION

Atezolizumab plus bevacizumab (AB) therapy was the effective immune checkpoint inhibitor (ICI) for unresectable hepatocellular carcinoma (u-HCC). However, immune-related adverse events (irAEs) are common in patients receiving ICI therapies. Our research aimed to explore the risk factors for irAE development, with attention to interleukin-7 (IL-7) risk alleles, lymphocyte counts, and autoantibodies.

METHODS

Seventy-six patients receiving AB therapy for u-HCC were recruited. Single nucleotide polymorphism genotyping was done for the analysis of rs16906115 polymorphism near IL-7-expressing genes using 20 μL of stored buffy coat at baseline. The association between IL-7 risk alleles, lymphocyte counts, autoantibodies, and irAE development was investigated.

RESULTS

irAEs were found in 14 (18%) patients. The incidence of irAEs did not differ significantly between the groups showing IL-7 AG/AA and the GG group (p = 0.72). The incidence in the group with a lymphocyte count of 1,130/µL or more at baseline was higher than in that with a value below 1,130/µL (p = 0.0093). The group showing IL-7 AG/AA or lymphocyte count >1,130/μL had a higher irAE prevalence rate than the others (p = 0.019). IL-7 AG/AA or lymphocyte count >1,130/μL and positivity for autoantibodies at baseline were the prognostic factors for irAE development. irAE incidence could be stratified using a combination of IL-7 AG/AA or lymphocyte counts ≥1,130/µL and positive autoantibodies (p = 0.016).

CONCLUSION

Patients with IL-7 risk alleles, high lymphocyte counts, and autoantibodies at baseline may require careful monitoring for irAE development.

Eosinophilic granulocytes as a potential prognostic marker for cancer progression and therapeutic response in malignant melanoma

The importance of eosinophilic granulocytes in cancer has been widely discussed in recent years. The current study reviews the evidence on the role of eosinophilic granulocytes in melanoma as a prognostic marker for cancer progression and the efficacy of treatment with modern immune checkpoint inhibitors. A total of 33 human clinical studies were included in the review, with heterogeneous data due to differences in patients populations, study design and inclusion of small study groups. However, 28 of the 33 studies suggested that eosinophilic granulocytes could be used as a prognostic biomarker for outcome and/or potential response to systemic treatment and/or occurrence of adverse events in melanoma patients. Nevertheless, the exact role of eosinophils remains to be elucidated. Further prospective, larger and better controlled studies are warranted to clarify the significance of eosinophilic granulocytes in patients with melanoma, in more details.

Biomarkers for immune-related adverse events in cancer patients treated with immune checkpoint inhibitors

Although immune checkpoint inhibitors have greatly improved cancer therapy, they also cause immune-related adverse events, including a wide range of inflammatory side effects resulting from excessive immune activation. Types of immune-related adverse events are diverse and can occur in almost any organ, with different frequencies and severities. Furthermore, immune-related adverse events may occur within the first few weeks after treatment or even several months after treatment discontinuation. Predictive biomarkers include blood cell counts and cell surface markers, serum proteins, autoantibodies, cytokines/chemokines, germline genetic variations and gene expression profiles, human leukocyte antigen genotype, microRNAs and the gut microbiome. Given the inconsistencies in research results and limited practical utility, there is to date no established biomarker that can be used in routine clinical practice, and additional investigations are essential to demonstrate efficacy and subsequently facilitate integration into routine clinical use.

Association between pretreatment C-reactive protein level and survival in non-small cell lung cancer patients treated with immune checkpoint inhibitors: A meta-analysis

BACKGROUND

Current evidence suggests that C-reactive protein (CRP) levels may affect cancer prognosis. However, the effect of CRP has not been validated in immunotherapy recipients with non-small cell lung cancer (NSCLC). Therefore, we performed a meta-analysis to explore the prognostic value of CRP level in patients with NSCLC treated with immune checkpoint inhibitors.

METHODS

PubMed, Web of Science, Embase, and Scopus databases were systematically retrieved for eligible publications, and hazard ratios (HRs) with corresponding 95% confidence intervals (95%CIs) were extracted and merged to evaluate the correlation between pretreatment CRP levels and overall survival (OS) and progression-free survival (PFS). Subgroup and sensitivity analyses were conducted to confirm these findings.

RESULTS

Thirty-five cohorts consisting of 4698 patients were included in the primary analysis. Pooled results demonstrated that a higher pretreatment CRP level is associated with worse OS and PFS (OS: HR = 1.13, 95 %CI:1.09-1.18; PFS: HR = 1.16, 95 %CI:1.10-1.22). These findings remained robust after further statistical analyses.

CONCLUSION

Pretreatment CRP level could be a promising biomarker for NSCLC immunotherapy. However, prospective studies are required to validate these findings.