Abstract

Recurrence is still the main obstacle to the survival of laryngeal squamous cell carcinoma (LSCC) patients who have undergone a total laryngectomy. Previous models for recurrence prediction in patients with LSCC were based on pathological information, while the role of easily accessible inflammatory markers in the prognosis of LSCC patients has rarely been reported. This study sought to develop and validate a model to predict the risk of recurrence in LSCC patients who underwent total laryngectomy. A total of 204 LSCC patients who underwent a total laryngectomy were included in this retrospective cohort study. Demographics, pathology, and inflammatory markers of patients were collected. All the patients were randomly divided into a training set and a test set at a ratio of 4:1. Patients were followed up for 3 years after surgery or until death occurred during this period. The random-forest method was used to develop a predictive model. The performance of the model was evaluated by calculating the area under the receiver operating characteristic (ROC) curve (AUC) with the 95% confidence interval (CI), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Of the 204 LSCC patients, 56 (27.45%) patients had a recurrence. The random-forest prediction model was an all-factor model, and the most important predictors of the model were the albumin/globulin ratio (AGR), neutrophil/lymphocyte ratio (NLR), and platelet/lymphocyte ratio (PLR), with proportions of 0.121, 0.100, and 0.092, respectively. The AUCs of the model in predicting the recurrence of LSCC in the training set and the test set were 0.960 (95% CI, 0.931-0.989) and 0.721 (95% CI, 0.716-0.726), respectively. The sensitivity, specificity, accuracy, PPV, and NPV of the model in the test set were 0.750 (95% CI, 0.505-0.995), 0.690 (95% CI, 0.521-0.858), 0.707 (95% CI, 0.568-0.847), 0.500 (95% CI, 0.269-0.921), and 0.870 (95% CI, 0.732-1.000), respectively. A model to predict the risk of recurrence in LSCC patients who have undergone a total laryngectomy was established, and inflammatory markers AGR, NLR, and PLR play an important role in the predictive model.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call