Purpose Radical surgery is the most important treatment modality in gastric cancer. Preoperative or postoperative radiation therapy (RT) and perioperative chemotherapy are the treatment options that should be added to surgery. This study aimed to evaluate the overall survival (OS) and recurrence patterns by machine learning in gastric cancer cases undergoing RT. Methods and Materials Between 2012 and 2019, the OS and recurrence patterns of 75 gastric cancer cases receiving RT ± chemotherapy at the Department of Radiation Oncology were evaluated by machine learning. Logistic regression, multilayer perceptron, XGBoost, support vector classification, random forest, and Gaussian Naive Bayes (GNB) algorithms were used to predict OS, hematogenous distant metastases, and peritoneal metastases. After the correlation analysis, the backward feature selection was performed as the variable selection method, and the variables with P values less than .005 were selected. Results Over the median 23-month follow-up, recurrence was seen in 33 cases, and 36 patients died. The median OS was 23 (min: 7; max: 82) months, and the disease-free survival was 18 (min: 5, max: 80) months. The most common recurrence pattern was hematogenous distant metastasis, followed by peritoneal metastasis. In this study, the most successful algorithms in the prediction of OS, distant metastases, and peritoneal metastases were found to be GNB with an accuracy of 81% (95% confidence interval [CI], 0.65-0.97, area under the curve [AUC]: 0.89), XGBoost with 86% accuracy (95% CI, 0.74-0.97, AUC: 0.86), and random forest with 97% accuracy (95% CI, 0.92-1.00, AUC: 0.97), respectively. Conclusions In gastric cancer, GNB, XGBoost, and random forest algorithms were determined to be the most successful algorithms for predicting OS, distant metastases, and peritoneal metastases, respectively. To determine the most accurate algorithm and perhaps make personalized treatments applicable, more precise machine learning studies are needed with an increased number of cases in the coming years.
OS was found longer in female patients with sMPMN (P < 0.05), and in all group with mMPMN (P < 0.005).
Background and Aim: Although the prognosis of nasopharyngeal cancer largely depends on a classification based on the tumor-lymph node metastasis staging system, patients at the same stage may have different clinical outcomes. This study aimed to evaluate the survival prognosis of nasopharyngeal cancer using machine learning. Settings and Design: Original, retrospective. Materials and Methods: A total of 72 patients with a diagnosis of nasopharyngeal cancer who received radiotherapy ± chemotherapy were included in the study. The contribution of patient, tumor, and treatment characteristics to the survival prognosis was evaluated by machine learning using the following techniques: logistic regression, artificial neural network, XGBoost, support-vector clustering, random forest, and Gaussian Naive Bayes. Results: In the analysis of the data set, correlation analysis, and binary logistic regression analyses were applied. Of the 18 independent variables, 10 were found to be effective in predicting nasopharyngeal cancer-related mortality: age, weight loss, initial neutrophil/lymphocyte ratio, initial lactate dehydrogenase, initial hemoglobin, radiotherapy duration, tumor diameter, number of concurrent chemotherapy cycles, and T and N stages. Gaussian Naive Bayes was determined as the best algorithm to evaluate the prognosis of machine learning techniques (accuracy rate: 88%, area under the curve score: 0.91, confidence interval: 0.68-1, sensitivity: 75%, specificity: 100%). Conclusion: Many factors affect prognosis in cancer, and machine learning algorithms can be used to determine which factors have a greater effect on survival prognosis, which then allows further research into these factors. In the current study, Gaussian Naive Bayes was identified as the best algorithm for the evaluation of prognosis of nasopharyngeal cancer.
Background: It is standard treatment to combine chemotherapy (CT) and thoracic radiotherapy (TRT) in treating patients with limited stage small cell lung cancer (LS-SCLC). However, optimal timing of TRT is unclear. We here evaluated the survival impact of early versus late TRT in patients with LS-SCLC. Materials and Methods: Follow-up was retrospectively analyzed for seventy consecutive LS-SCLC patients who had successfully completed chemo-TRT between January 2006 and January 2012. Patients received TRT after either 1 to 2 cycles of CT (early TRT) or after 3 to 6 cycles of CT (late TRT). Survival and response rates were evaluated using the Kaplan-Meier method and comparisons were made using the multivariate Cox regression test. Results: Median follow-up was 24 (5 to 57) months. Carboplatin+etoposide was the most frequent induction CT (59%). Median overall, disease free, and metastasis free survivals in all patients were 15 (5 to 57), 5 (0 to 48) and 11 (3 to 57) months respectively. Late TRT was superior to early TRT group in terms of response rate (p=0.05). 3 year overall survival (OS) rates in late versus early TRT groups were 31% versus 17%, respectively (p=0.03). Early TRT (p=0.03), and incomplete response to TRT (p=0.004) were negative predictors of OS. Significant positive prognostic factors for distant metastasis free survival were late TRT (p=0.03), and use of PCI (p=0.01). Use of carboplatin versus cisplatin for induction CT had no significant impact on OS (p=0.634), DFS (p=0.727), and MFS (p=0.309). Conclusions: Late TRT appeared to be superior to early TRT in LS-SCLC treatment in terms of complete response, OS and DMFS. Carboplatin or cisplatin can be combined with etoposide in the induction CT owing to similar survival outcomes.
Nasopharyngeal cancer's presentation and prognosis are variable. Even patients with the same clinical stage can have very different prognoses. The aim of the present study was to investigate clinical outcomes and prognosis, especially the effects of neutrophil/lymphocyte ratio (NLR), of non-metastatic nasopharyngeal carcinoma (NPC) in patients receiving radiotherapy (RT)±chemotherapy (CT) between March 2006 and August 2017 in the Eskişehir Osmangazi University Medical Faculty of Radiation Oncology Department. METHODS Sixty-two patients with non-metastatic NPC treated with RT±CT were retrospectively evaluated. Patient characteristics, such as age, gender, Karnofsky Performance Status (KPS), T phase, N phase, tumor, lymph node, and metastasis phase, histopathologic subgroup, tumor size, NLR, and hemoglobin value, and treatment characteristics, such as concurrent/adjuvant CT status, RT intermission time, and RT total time, were investigated. RESULTS Median overall survival (OS) was 55 (10-134) months, whereas median disease-free survival was 44 (6-129) months. The median duration of local control was 48 (6-129) months. Eleven (17.7%) patients developed distant metastases. Distant metastases were detected in 6 (9.7%) patients who had local control. Statistically significant results were obtained between general survival and sex (p=0.015), KPS (p<0.001), and NLR (p<0.001). Distant metastases were found to be significantly higher in male cases, and all 11 metastatic cases were male (Fisher's exact test, p=0.012). CONCLUSION Patients with high NLR had lower OS, and pretreatment NLR value may be a guide in determining which patients should receive more aggressive treatment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.