Prognostic nomogram based on immune scores for laryngeal squamous cell cancer

A novel staging system based on deep learning for overall survival in patients with esophageal squamous cell carcinoma

PURPOSE

We developed DeepSurv, a deep learning approach for predicting overall survival (OS) in patients with esophageal squamous cell carcinoma (ESCC). We validated and visualized the novel staging system based on DeepSurv using data from multiple cohorts.

METHODS

Totally 6020 ESCC patients diagnosed from January 2010 to December 2018 were included in the present study from the Surveillance, Epidemiology, and End Results database (SEER), randomly assigned to the training and test cohorts. We developed, validated and visualized a deep learning model that included 16 prognostic factors; then a novel staging system was further constructed based on the total risk score derived from the deep learning model. The classification performance at 3-year and 5-year OS was assessed by the receiver-operating characteristic (ROC) curve. Calibration curve and the Harrell's concordance index (C-index) were also used to comprehensively assess the predictive performance of the deep learning model. Decision curve analysis (DCA) was utilized to assess the clinical utility of the novel staging system.

RESULTS

A more applicable and accurate deep learning model was established, which outperformed the traditional nomogram in predicting OS in the test cohort (C-index: 0.732 [95% CI 0.714-0.750] versus 0.671 [95% CI 0.647-0.695]). The ROC curves at 3-year and 5-year OS for the model also showed good discrimination ability in the test cohort (Area Under the Curve [AUC] at 3-/5-year OS = 0.805/0.825). Moreover, using our novel staging system, we observed a clear survival difference among different risk groups (P < 0.001) and a significant positive net benefit in the DCA.

CONCLUSIONS

A novel deep learning-based staging system was constructed for patients with ESCC, which performed a significant discriminability for survival probability. Moreover, an easy-to-use web-based tool based on the deep learning model was also implemented, offering convenience for personalized survival prediction. We developed a deep learning-based system that stages patients with ESCC according to their survival probability. We also created a web-based tool that uses this system to predict individual survival outcomes.

Ferroptosis-related genes for predicting prognosis of patients with laryngeal squamous cell carcinoma

BACKGROUND

Previous studies reported that ferroptosis-related genes can regulate the process of tumor cell changes by regulating iron metabolism. However, the prognostic value of ferroptosis-related genes in LC remains to be further elucidated.

METHODS

Ferroptosis-related gene expression profiles of coexisting ferroptosis-related genes were extracted from both cohorts (TCGA and GSE27020) for eligible analysis. LASSO Cox regression was utilized to build an optimum ferroptosis-related prognostic model. Kaplan-Meier curve was performed by log-rank test, and time-dependent ROC curve was constructed to evaluate the predictive power of this signature in both cohorts. GO and KEGG enrichment analysis was used to investigate the potential mechanism of differential enrichment signal pathways.

RESULTS

112 LC patients from the TCGA cohort and 108 LC patients with clinical information from the GEO cohorts were eventually included in the study. Three ferroptosis-related genes were identified as an independent risk factor to establish the prognostic risk score. Kaplan-Meier curve represented that patients with high-risk group favors with worse OS than their low-risk group (P = 0.04). The good performance of the gene signature for predicting OS was evaluated by area under the curve (AUC) of time-dependent ROC curves achieved 0.74 at 3 years, and 0.70 at 5 years. Similar performance has been proved in the external validation cohort. GO and KEGG enrichment analysis have been performed to explore the signaling pathways and underlying mechanisms were significantly active in LC patients.

CONCLUSION

In summary, our study developed a ferroptosis-related model that could be an effective biomarker to predict the prognosis of laryngeal cancer.

Circulating immune parameters-based nomogram for predicting malignancy in laryngeal neoplasm

BACKGROUND

Malignancy prediction remains important to preoperative diagnosis and postoperative follow-up in laryngeal neoplasm.

AIM

To evaluate the circulating immune population and develop a nomogram for prediction of malignancy in patients with laryngeal neoplasm.

METHODS

A primary cohort of 156 patients was divided into laryngeal benign lesion, premalignant lesion and malignant lesion groups. Peripheral blood from patients was measured by blood routine test and flow cytometry. A nomogram was developed and applied to a validation cohort containing 55 consecutive patients.

RESULTS

Age, gender and seven circulating immune parameters exhibited significant differences between laryngeal benign lesion and premalignant lesion. The nomogram incorporated predictors, including gender, age, smoke index, proportions of monocytes, CD8+ T cells, CD4+ T cells, B cells and CD4/CD8+ T cell ratio. It showed good discrimination between laryngeal premalignant lesion and malignant lesion, with a C-index of 0.844 for the primary cohort. Application of this nomogram in the validation cohort (C-index, 0.804) still had good discrimination and good calibration. Decision curve analysis revealed that the nomogram was clinically useful.

CONCLUSION

This novel nomogram, incorporating both clinical risk factors and circulating immune parameters, could be appropriately applied in preoperative individualized prediction of malignancy in patients with laryngeal neoplasm.