Objective:To explore the feasibility of selecting appropriate respiratory motion management strategies for patients undergoing stereotactic radiotherapy for liver cancer using chi-square feature testing and machine learning techniques.Methods:A retrospective analysis was conducted on 95 liver cancer patients who underwent respiratory motion evaluation at Xiangya Hospital of Central South University between March 2022 and August 2024. Chi-square testing was used to screen features related to respiratory motion evaluation in liver cancer patients. Based on these features, predictive models were constructed using 4 machine learning classification algorithms: support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), and adaptive boosting (AdaBoost). The predictive performance of these models was evaluated using accuracy, sensitivity, specificity, F1 value, and area under the curve (AUC).Results:The accuracy values for the SVM, RF, GBDT and AdaBoost models were 0.75, 0.75, 0.70, and 0.82, respectively. The sensitivity values were 0.82, 0.82, 0.64, and 0.82, respectively. The specificity values were 0.63, 0.63, 0.63, and 0.75, respectively. The F1 scores were 0.78, 0.78, 0.67, and 0.82, respectively. The AUC values were 0.85, 0.80, 0.76, and 0.85, respectively.Conclusions:The predictive models constructed by combining chi-square feature testing and machine learning methods can effectively predict the selection of respiratory motion management strategies. Among the models, the AdaBoost model demonstrated the best predictive performance for selecting respiratory motion management strategies.

Objective:To explore the feasibility of selecting appropriate respiratory motion management strategies for patients undergoing stereotactic radiotherapy for liver cancer using chi-square feature testing and machine learning techniques.Methods:A retrospective analysis was conducted on 95 liver cancer patients who underwent respiratory motion evaluation at Xiangya Hospital of Central South University between March 2022 and August 2024. Chi-square testing was used to screen features related to respiratory motion evaluation in liver cancer patients. Based on these features, predictive models were constructed using 4 machine learning classification algorithms: support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), and adaptive boosting (AdaBoost). The predictive performance of these models was evaluated using accuracy, sensitivity, specificity, F1 value, and area under the curve (AUC).Results:The accuracy values for the SVM, RF, GBDT and AdaBoost models were 0.75, 0.75, 0.70, and 0.82, respectively. The sensitivity values were 0.82, 0.82, 0.64, and 0.82, respectively. The specificity values were 0.63, 0.63, 0.63, and 0.75, respectively. The F1 scores were 0.78, 0.78, 0.67, and 0.82, respectively. The AUC values were 0.85, 0.80, 0.76, and 0.85, respectively.Conclusions:The predictive models constructed by combining chi-square feature testing and machine learning methods can effectively predict the selection of respiratory motion management strategies. Among the models, the AdaBoost model demonstrated the best predictive performance for selecting respiratory motion management strategies.

Objective:To study the significance of induction chemotherapy and subsequent comprehensive therapy for overall survival rate (OS) and larynx dysfunction-free survival rate (LDFS) in patients with advanced hypopharyngeal carcinoma.Methods:Patients who met the inclusion criteria with the diagnoses of advanced hypopharyngeal carcinoma between 2011 and 2017 received 2 or 3 cycles of TPF regimen induction chemotherapy. Patients who attained complete response (CR) received radical chemotherapy. Patients who attained partial response (PR) and the reduction of tumor volume was more than 70% were defined as large PR and received concurrent chemoradiotherapy. When the tumor volume reduction of PR patients was less than 70%, they were defined as small PR. (CR+large PR) group was defined as effective group. Patients who did not reach CR and large PR were defined as uneffective group and underwent radical surgery and received adjuvant radiotherapy as appropriate after the surgery. The end points of the study were OS, progression-free survival (PFS) and LDFS. Chi-square (χ 2) test was used for correlation analysis. Survival analysis was performed by the Kaplan-Meier method with a Log-rank test. Cox proportional hazards model was used for univariate and multivariate survival analysis. Results:A total of 260 patients were enrolled in the study. The follow-up period ranged from 5 to 83 months, with an average of 24.7 months. The 3-year and 5-year OS rate was 46.0% and 32.6%, respectively. The 3-year and 5-year PFS rate was 41.0% and 26.6%, respectively. The 3-year and 5-year LDFS rate was 37.9% and 24.8%, respectively. Poor outcome of induction chemotherapy, advanced N stage, strong positive Ki-67 immunohistochemistry (all P<0.001) were negative prognostic factors. The advanced clinical stage was positively related to the poor outcome of induction chemotherapy ( P=0.015). There was no significant difference in OS and PFS between the large PR group and the small PR group (all P>0.005). Conclusion:TPF regimen induction chemotherapy and subsequent comprehensive therapy for patients with advanced hypopharyngeal carcinoma may improve the quality of life of patients, with high OS rate and LDFS rate.

Objective To study the relation between expressions of transforming growth factor ?1 (TGF-?1), transforming growth factor receptor type Ⅰ (T?RⅠ) and cell proliferation, cell cycle in gallbladder carcinomas, to disclose the mechanism of TGF-?1 and T?RⅠin the gallbladder carcinogenesis,and to evaluate their values in the prognosis of gallbladder carcinomas. Methods Thirty five gallbladder carcinomas age (57.94? 4.61) years, 14 male cases and 21 female cases comprised 32 adenocarcinomas, 2 adenosquamous carcinoma and 1 squamous cell carcinomas. Formalin fixed, paraffin embedded sections from gallbladder carcinomas were immunostained with TGF-?1, T?RⅠ, PCNA, cyclin E antibodies by immunochemical assays. Gallbladder adenoma and chronic cholecystitis were collected as non-malignant controls. Patients of gallbladder carcinomas were followed up. Results Positive immunostaining rate of TGF-?1 was 57.14% in gallbladder carcinomas, which was significantly higher than that in gallbladder adenomas and chronic cholecystitis (P

Objective To investigate the expression of tumor growth tactor ?1 (TGF-?1) and p27 in gallbladder carcinoma and their relation to the development of the carcinoma. Methods The expression of TGF-?1 and p27 in 36 cases of gallbladder carcinoma was detected by SP immunohistochemical staining. Twenty cases of chronic cholecystitis were collected as control. Results The positive rate of TGF-?1 (63.9%) was higher than that of the control (10.0%), P