Prognostic value of preoperative hematological markers in patients with glioblastoma multiforme and construction of random survival forest model

Sequential Evaluation of Hematology Markers as a Prognostic Factor in Glioblastoma Patients

In our study, we investigated the prognostic significance of hematological markers-NLR (Neutrophil-to-Lymphocyte Ratio), PLR (Platelet-to-Lymphocyte Ratio), and RDW-CV (Red Blood Cell Distribution Width-Coefficient of Variation)-in 117 glioblastoma patients. The data collected from January 2016 to December 2018 included demographics, clinical scores, and treatment regimens. Unlike previous research, which often examined these markers solely before surgery, our unique approach analyzed them at multiple stages: preoperative, postoperative, and before adjuvant therapies. We correlated these markers with the overall survival (OS) and progression-free survival (PFS) using statistical tools, including ANOVA, Cox regression, and Kaplan-Meier survival analyses, employing SPSS version 29.0. Our findings revealed notable variations in the NLR, PLR, and RDW-CV across different treatment stages. The NLR and PLR decreased after surgery, with some stabilization post-STUPP phase (NLR: p = 0.007, η2p = 0.06; PLR: p = 0.001, η2p = 0.23), while the RDW-CV increased post-surgery and during subsequent treatments (RDW-CV: p < 0.001, η2p = 0.67). Importantly, we observed significant differences between the preoperative phase and other treatment phases. Additionally, a higher NLR and RDW-CV at the second-line treatment and disease progression were associated with an increased risk of death (NLR at 2nd line: HR = 1.03, p = 0.029; RDW-CV at progression: HR = 1.14, p = 0.004). We proposed specific marker cut-offs that demonstrated significant associations with survival outcomes when applied to Kaplan-Meier survival curves (NLR at 2nd line < 5: p < 0.017; RDW-CV at progression < 15: p = 0.007). An elevated NLR and RDW-CV at later treatment stages correlated with poorer OS and PFS. No significant preoperative differences were detected. These biomarkers may serve as non-invasive tools for glioblastoma management.

Systemic and local immunosuppression in glioblastoma and its prognostic significance

The effectiveness of tumor therapy, especially immunotherapy and oncolytic virotherapy, critically depends on the activity of the host immune cells. However, various local and systemic mechanisms of immunosuppression operate in cancer patients. Tumor-associated immunosuppression involves deregulation of many components of immunity, including a decrease in the number of T lymphocytes (lymphopenia), an increase in the levels or ratios of circulating and tumor-infiltrating immunosuppressive subsets [e.g., macrophages, microglia, myeloid-derived suppressor cells (MDSCs), and regulatory T cells (Tregs)], as well as defective functions of subsets of antigen-presenting, helper and effector immune cell due to altered expression of various soluble and membrane proteins (receptors, costimulatory molecules, and cytokines). In this review, we specifically focus on data from patients with glioblastoma/glioma before standard chemoradiotherapy. We discuss glioblastoma-related immunosuppression at baseline and the prognostic significance of different subsets of circulating and tumor-infiltrating immune cells (lymphocytes, CD4+ and CD8+ T cells, Tregs, natural killer (NK) cells, neutrophils, macrophages, MDSCs, and dendritic cells), including neutrophil-to-lymphocyte ratio (NLR), focus on the immune landscape and prognostic significance of isocitrate dehydrogenase (IDH)-mutant gliomas, proneural, classical and mesenchymal molecular subtypes, and highlight the features of immune surveillance in the brain. All attempts to identify a reliable prognostic immune marker in glioblastoma tissue have led to contradictory results, which can be explained, among other things, by the unprecedented level of spatial heterogeneity of the immune infiltrate and the significant phenotypic diversity and (dys)functional states of immune subpopulations. High NLR is one of the most repeatedly confirmed independent prognostic factors for shorter overall survival in patients with glioblastoma and carcinoma, and its combination with other markers of the immune response or systemic inflammation significantly improves the accuracy of prediction; however, more prospective studies are needed to confirm the prognostic/predictive power of NLR. We call for the inclusion of dynamic assessment of NLR and other blood inflammatory markers (e.g., absolute/total lymphocyte count, platelet-to-lymphocyte ratio, lymphocyte-to-monocyte ratio, systemic immune-inflammation index, and systemic immune response index) in all neuro-oncology studies for rigorous evaluation and comparison of their individual and combinatorial prognostic/predictive significance and relative superiority.

Prognostic value of pretreatment lymphocyte-to-monocyte ratio in patients with glioma: a meta-analysis

BACKGROUND

Many studies have explored the prognostic role of the lymphocyte-to-monocyte ratio (LMR) in patients with glioma, but the results have been inconsistent. We therefore conducted the current meta-analysis to identify the accurate prognostic effect of LMR in glioma.

METHODS

The electronic databases of PubMed, Web of Science, Embase, and Cochrane Library were thoroughly searched from inception to July 25, 2023. The pooled hazard ratios (HRs) and 95% confidence intervals (CIs) were calculated to estimate the prognostic role of LMR for glioma.

RESULTS

A total of 16 studies comprising 3,407 patients were included in this meta-analysis. A low LMR was significantly associated with worse overall survival (OS) (HR = 1.35, 95% CI = 1.13-1.61, p = 0.001) in glioma. However, there was no significant correlation between LMR and progression-free survival (PFS) (HR = 1.20, 95% CI = 0.75-1.91, p = 0.442) in glioma patients. Subgroup analysis indicated that a low LMR was significantly associated with inferior OS and PFS in glioma when using a cutoff value of ≤ 3.7 or when patients received mixed treatment.

CONCLUSIONS

This meta-analysis demonstrated that a low LMR was significantly associated with poor OS in glioma. There was no significant correlation between LMR and PFS in glioma patients. The LMR could be a promising and cost-effective prognostic biomarker in patients with glioma in clinical practice.

Interpretable machine learning model based on the systemic inflammation response index and ultrasound features can predict central lymph node metastasis in cN0T1-T2 papillary thyroid carcinoma

Background

It is arguable whether individuals with T1-T2 papillary thyroid cancer (PTC) who have a clinically negative (cN0) diagnosis should undergo prophylactic central lymph node dissection (pCLND) on a routine basis. Many inflammatory indices, including the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), monocyte-to-lymphocyte ratio (MLR), and systemic immune-inflammatory index (SII), have been reported in PTC. However, the associations between the systemic inflammation response index (SIRI) and the risk of central lymph node metastasis (CLNM) remain unclear.

Methods

Retrospective research involving 1,394 individuals with cN0T1-T2 PTC was carried out, and the included patients were randomly allocated into training (70%) and testing (30%) subgroups. The preoperative inflammatory indices and ultrasound (US) features were used to train the models. To assess the forecasting factors as well as drawing nomograms, the least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were utilized. Then eight interpretable models based on machine learning (ML) algorithms were constructed, including decision tree (DT), K-nearest neighbor (KNN), support vector machine (SVM), artificial neural network (ANN), random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost). The performance of the models was evaluated by incorporating the area under the precision-recall curve (auPR) and the area under the receiver operating characteristic curve (auROC), as well as other conventional metrics. The interpretability of the optimum model was illustrated via the shapley additive explanations (SHAP) approach.

Results

Younger age, larger tumor size, capsular invasion, location (lower and isthmus), unclear margin, microcalcifications, color Doppler flow imaging (CDFI) blood flow, and higher SIRI (≥0.77) were independent positive predictors of CLNM, whereas female sex and Hashimoto thyroiditis were independent negative predictors, and nomograms were subsequently constructed. Taking into account both the auROC and auPR, the RF algorithm showed the best performance, and superiority to XGBoost, CatBoost and ANN. In addition, the role of key variables was visualized in the SHAP plot.

Conclusions

An interpretable ML model based on the SIRI and US features can be used to predict CLNM in individuals with cN0T1-T2 PTC.