• Journal of Korean Neurosurgical Society
• /
• v.67 no.1
• /
• pp.94-102
• /
• 2024

Objective : The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML). Methods : Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR). Results : We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables. Conclusion : The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

• Radiation Oncology Journal
• /
• v.21 no.4
• /
• pp.261-268
• /
• 2003

Purpose: To report the results of curative treatment for patients with tonsil cancer by retrospective analysis. Materials and Methods: From Jan. 1995 till Dec. 2000, 27 patients with squamous cell carcinoma of the tonsil received curative treatment at Samsung Medical Center. Therapeutic decision was made through multidisciplinary conference, and curative radiation therapy was favored when, (1) the patient's condition was not fit for general anesthesia and surgery, (2) the patient refused surgery, (3) complete resection was presumed impossible, or (4) too severe disability was expected after surgery. Surgery was the main local modality in 17 patients (S$\pm$RT group), and radiation therapy in 10 (RT$\pm$CT group). The median follow-up period was 41 months. Results: AJCC stages were I/II in four, III in two, and IV in 21 patients. The 5-year disease-free survival rate was 73.3$\%$ in all patients, 70.6$\%$ in the S$\pm$RT group, and 77.8$\%$ in the RT$\pm$CT group. Treatment failure occurred in seven patients, all with stage III/IV, and all the failures occurred within 24 months of the start of treatment. Five patients among the S$\pm$CT group developed treatment failures; 2 local, 2 regional, and 1 distant (crude rate=29.4$\%$). Two patients among the RT$\pm$CT group developed failures; 1 synchronous local and regional, and 1 distant (crude rate=20.0$\%$). The 5-year overall survival rate was 77.0$\%$ in all patients, 80.9$\%$ in the S$\pm$RT group, and 70.0$\%$ in the RT$\pm$CT group. Conclusion: We could achieve favorable results that were comparable to previously reported data with respect to both the rates of local control and of survival by applying S$\pm$RT and RT$\pm$CT. RT$\pm$CT is judged to be an alternative option that can avoid the functional disability after surgical resection.