ObjectiveTo compare the short- and long-term efficacy of surgery and endoscopy in the treatment of early esophageal cancer by a systematic review and meta-analysis.MethodsWe extracted data independently from The Cochrane Library, PubMed, EMbase, Web of Science for studies comparing surgery with endoscopy from 2010 to 2020. The primary outcomes including R0 resection rate, long-term overall survival (OS), disease-specific survival (DSS), major complications, recurrence, hospital stay and cost. Meta-analysis was performed using RevMan 5.3 and Engauge Digitizer was used to extract survival curves from relevant literature, and relevant data were calculated based on statistical methods. ResultsA total of 17 studies involving 3 705 patients were included. It was found that patients in the surgery group had a higher R0 resection rate compared with the endoscopic group (OR=0.13, 95%CI 0.07 to 0.27, P<0.001, I2=6%). The total complications rate of resection of esophageal cancer was higher than that of the endoscopic group (OR=0.28, 95%CI 0.16 to 0.50, P<0.001, I2=68%). The length of hospitalization in the endoscopic group was obviously shorter than that in the surgery group (MD=–8.28, 95%CI –12.44 to –4.13, P<0.001, I2=96%). The distant recurrence rate (OR=0.58, 95%CI 0.24 to 1.41, P=0.230, I2=0%) and the local recurrence rate after resection (OR=1.74, 95%CI 0.66 to 4.59, P=0.260, I2=40%) in the endoscopic group was similar to those of the surgery group. There was no significant difference in 5 year-OS rate between the two groups (HR=0.86, 95%CI 0.67 to 1.11, P=0.25, I2=0%), which was subdivided into two groups: adenocarcinoma (HR=0.55, 95%CI 0.15 to 2.05, P=0.37, I2=0%) and squamous cell carcinoma (HR=0.68, 95%CI 0.46 to 1.01, P=0.06, I2=0%), showing that there was no difference between the two subgroups. There was no significant difference in the DSS rate (HR=0.72, 95%CI 0.49 to 1.05, P=0.090, I2=0%) between the two groups. The cost of the surgery group was significantly higher than that of the endoscopic group (MD=–12.97, 95%CI –18.02 to –7.92, P<0.001, I2=93%).ConclusionThe evidence shows that endotherapy may be an effective treatment for early esophageal neoplasm when considering the long-term outcomes whether it is squamous or adenocarcinoma, even though it is not as effective as surgery in the short-term efficacy.
ObjectiveTo explore the application value of machine learning models in predicting postoperative survival of patients with thoracic squamous esophageal cancer. MethodsThe clinical data of 369 patients with thoracic esophageal squamous carcinoma who underwent radical esophageal cancer surgery at the Department of Thoracic Surgery of Northern Jiangsu People's Hospital from January 2014 to September 2015 were retrospectively analyzed. There were 279 (75.6%) males and 90 (24.4%) females aged 41-78 years. The patients were randomly divided into a training set (259 patients) and a test set (110 patients) with a ratio of 7 : 3. Variable screening was performed by selecting the best subset of features. Six machine learning models were constructed on this basis and validated in an independent test set. The performance of the models' predictions was evaluated by area under the curve (AUC), accuracy and logarithmic loss, and the fit of the models was reflected by calibration curves. The best model was selected as the final model. Risk stratification was performed using X-tile, and survival analysis was performed using the Kaplan-Meier method with log-rank test. ResultsThe 5-year postoperative survival rate of the patients was 67.5%. All clinicopathological characteristics of patients between the two groups in the training and test sets were not statistically different (P>0.05). A total of seven variables, including hypertension, history of smoking, history of alcohol consumption, degree of tissue differentiation, pN stage, vascular invasion and nerve invasion, were included for modelling. The AUC values for each model in the independent test set were: decision tree (AUC=0.796), support vector machine (AUC=0.829), random forest (AUC=0.831), logistic regression (AUC=0.838), gradient boosting machine (AUC=0.846), and XGBoost (AUC=0.853). The XGBoost model was finally selected as the best model, and risk stratification was performed on the training and test sets. Patients in the training and test sets were divided into a low risk group, an intermediate risk group and a high risk group, respectively. In both data sets, the differences in surgical prognosis among three groups were statistically significant (P<0.001). ConclusionMachine learning models have high value in predicting postoperative prognosis of thoracic squamous esophageal cancer. The XGBoost model outperforms common machine learning methods in predicting 5-year survival of patients with thoracic squamous esophageal cancer, and it has high utility and reliability.
The dramatically increasing high-resolution medical images provide a great deal of useful information for cancer diagnosis, and play an essential role in assisting radiologists by offering more objective decisions. In order to utilize the information accurately and efficiently, researchers are focusing on computer-aided diagnosis (CAD) in cancer imaging. In recent years, deep learning as a state-of-the-art machine learning technique has contributed to a great progress in this field. This review covers the reports about deep learning based CAD systems in cancer imaging. We found that deep learning has outperformed conventional machine learning techniques in both tumor segmentation and classification, and that the technique may bring about a breakthrough in CAD of cancer with great prospect in the future clinical practice.