Personalized therapeutic strategies and prognosis for advanced laryngeal squamous cell carcinoma: Insights from machine learning models

Purpose

Despite the development of diverse treatment options, there has been an increase in mortality rates for laryngeal squamous cell carcinoma (LSCC). Our research employed survival analysis and machine learning (ML) techniques to evaluate the impact of different therapeutic options on survival and to build a prognostic model for individualized clinical decisions in advanced LSCC.

Methods

The Surveillance, Epidemiology and End Results (SEER) database provided the data used for this study’s analysis. To identify the prognostic variables for patients with LSCC, we conducted Cox regression analysis and constructed prognostic models using five machine learning (ML) algorithms to predict 5-year survival. A method of validation that incorporated the area under the curve (AUC) of the receiver operating characteristic (ROC) curve was employed to validate the accuracy and reliability of the ML models. We also investigated the role of multiple therapeutic options using Kaplan Meier (K-M) survival analysis.

Results

The study included 7350 patients, of whom 2689 were diagnosed with glottic cancer (GC), 4349 with supraglottic (SuGC) and 312 with subglottic (SC). ML models identified age, sex, and stage as the most important factors that affect survival. In terms of treatment, bets survival therapeutic options for all anatomical sites was surgery and radiotherapy (RT).

Conclusion

Employing multimodal therapies such as surgery and radiotherapy is crucial for managing advanced-stage LSCC. Tailored approaches that consider prognostic factors such as age, sex, and tumor stage are necessary. Additionally, chemotherapy did not significantly impact overall survival, suggesting potential areas for improvement in LSCC management.