Efficacy of Chemotherapy in Survival of Stage I Nasopharyngeal Carcinoma

Using machine learning algorithms to predict the prognosis of advanced nasopharyngeal carcinoma after intensity-modulated radiotherapy

BACKGROUND

The prognosis of advanced nasopharyngeal carcinoma (NPC) patients after intensity-modulated radiotherapy (IMRT) has not been well studied. We aimed to construct prognostic models for advanced NPC patients with stage III-IV after their first treatment with IMRT by using machine learning algorithms and to identify the most important predictors.

METHODS

A total of 427 patients treated in Meizhou People's Hospital in Guangdong province, China from January 1, 2013 to December 12, 2018 were enrolled in this study, with an average follow-up period of 7.16 years from July 2020 to March 2021. Candidate predictors were selected from demographics, clinical features, medical examinations and test results. Three machine learning algorithms were applied to construct advanced NPC prognostic models: logistic regression (LR), decision tree (DT), and random forest (RF). Area under the receiver operating characteristic curve (AUC) was used to evaluate the model performance. The important predictors of the optimal model for unfavourable prognosis were identified and ranked.

RESULTS

There were 50 (11.7%) NPC-related deaths observed in this study. The mean age of all participants was 49.39±11.29 years, of whom 299 (70.0%) were males. In general, RF showed the best predictive performance with the highest AUC (0.753, 95% CI: 0.609, 0.896), compared to LR (0.736, 95% confidence interval (CI): 0.590, 0.881), and DT (0.720, 95% CI: 0.520, 0.921). The six most important predictors identified by RF were Epstein-Barr virus deoxyribonucleic acid, aspartate aminotransferase, body mass index, age, blood glucose level, and alanine aminotransferase.

CONCLUSIONS

We proposed RF as a simple and accurate tool for the evaluation of the prognosis of advanced NPC patients after the treatment with IMRT in clinical settings.

Contribution of age at diagnosis to cancer-specific survival of nasopharyngeal carcinoma patients receiving radiotherapy

To assess age as a continuous variable for the prognosis of patients with nasopharyngeal carcinoma (NPC) receiving radiotherapy. Patients diagnosed with NPC between 2004 and 2016 were extracted from the Surveillance, Epidemiology, and End Results database. The X-tile was used to calculate the optimal cutoff values for age at diagnosis. Age at diagnosis was divided into subgroups based on the cutoff values. Cancer-specific survival (CSS) between age subgroups was assessed using the Kaplan-Meier method. The age cutoff values for CSS were 42 and 70 years. The 5-year CSS was 85.8%, 73.8%, and 67.1% for the ≤42, 43 to 70, and >70 subgroups. Multivariate regression analysis revealed that race, pathology, T stage, N stage, and age were independent prognostic factors. A nomogram based on the prognostic factors showed that the area under the receiver operating characteristic curve was 0.723 (95% confidence interval, 0.697-0.749). The calibration plots showed good agreement for the 5-year CSS between the predicted and actual observations. All patients were divided into 3 groups according to risk score stratification. Kaplan-Meier survival analyses showed that patients in the low-risk cohort had a greater 5-year CSS than those in the medium- and high-risk cohorts (P < .05). Age subgroups of ≤42, 43 to 70, and >70 years may be useful for determining the prognosis of patients with NPC.

Effects of CIK Cell Therapy Combined with Camrelizumab on the Quality of Life in Patients with Nasopharyngeal Carcinoma and Analysis of Prognostic Factors

Objective

To investigate the effects of CIK (cytokine-induced killer) cell therapy combined with camrelizumab on the quality of life in patients with nasopharyngeal carcinoma and prognostic factors.

Methods

In this retrospective study, the materials of 80 patients with nasopharyngeal carcinoma treated in our hospital (February 2017-February 2019) were retrospectively analyzed, and they were equalized into experimental group (n = 40) and control group (n = 40) according to the order of admission. Both groups received 200 mg of camrelizumab on day 1 combined with 10 mg of anrotinib from day 2 to day 4. The patients received the above program every 3 weeks and 4 treatment cycles. The experimental group also received CIK cell therapy simultaneously. The patients' quality of life, immune indexes, local control, metastasis, and survival rate were compared between the two groups, and the prognostic factors were analyzed by logistic analysis.

Results

Compared with the control group, the experimental group achieved much higher scores of physical well-being (18.38 ± 2.31), social/family well-being (16.40 ± 2.24), emotional well-being (15.35 ± 2.30), functional well-being (17.30 ± 2.20), and head and neck cancer subscale (15.40 ± 2.01, P < 0.001) and eminently better immune indexes (P < 0.001) after treatment. During the 24-month follow-up, there were 2 recurrent cases (5.0%) and 2 cases (5.0%) with distant metastasis among the 40 patients in the experimental group; there were 8 recurrent cases (20.0%) and 7 cases (17.5%) with distant metastasis among the 40 patients in the control group. In the experimental group, the median survival period was 18 months and the 2-year survival rate was 97.5% (39/40). In the control group, the median survival period was 14 months and the 2-year survival rate was 85.0% (34/40). Among the 80 patients, 7 cases (8.75%) died and 73 cases (91.25%) survived. After conducting the single-factor analysis, remarkable differences in the cases of IV stage, quality of life after treatment, and immune indexes after treatment between the survival group and the death group were observed (P < 0.05). According to the multiple-factor analysis, the clinical stage and immune indexes were identified as the prognostic factors.

Conclusion

CIK cell therapy combined with camrelizumab can enhance the life quality and immune function of the patients with nasopharyngeal carcinoma, thus improving their prognoses.