• Korean Journal of Artificial Intelligence
• /
• v.6 no.2
• /
• pp.11-15
• /
• 2018

Breast cancer is one of the leading causes of cancer related death among women. So prediction of overall survival status is important into decided in adjuvant treatment. Deep belief network is a kind of artificial intelligence (AI). We intended to construct prediction model by deep belief network using associated clinicopathologic factors. 103881 cases were found in the Korean Breast Cancer Registry. After preprocessing of data, a total of 15733 cases were enrolled in this study. The median follow-up period was 82.4 months. In univariate analysis for overall survival (OS), the patients with advanced AJCC stage showed relatively high HR (HR=1.216 95% CI: 0.011-289.331, p=0.001). Based on results of univariate and multivariate analysis, input variables for learning model included 17 variables associated with overall survival rate. output was presented in one of two states: event or cencored. Individual sensitivity of training set and test set for predicting overall survival status were 89.6% and 91.2% respectively. And specificity of that were 49.4% and 48.9% respectively. So the accuracy of our study for predicting overall survival status was 82.78%. Prediction model based on Deep belief network appears to be effective in predicting overall survival status and, in particular, is expected to be applicable to decide on adjuvant treatment after surgical treatment.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.14
• /
• pp.5655-5661
• /
• 2015

Purpose: To assess the role of two adjuvant chemotherapy regimens, anthracycline-based and CMF on disease free survival and overall survival breast cancer patients by meta-analysis approach in Eastern Mediterranean and Asian countries to determine which is more effective and evaluate the appropriateness and efficiency of two different proposed statistical models. Materials and Methods: Survival curves were digitized and the survival proportions and times were extracted and modeled to appropriate covariates by two multivariate mixed effects models. Studies which reported disease free survival and overall survival curves for anthracycline-based or CMF as adjuvant chemotherapy that were published in English in the Eastern Mediterranean region and Asia were included in this systematic review. The two transformations of survival probabilities (Ln (-Ln(S)) and Ln(S/ (1-S))) as dependent variables were modeled by a multivariate mixed model to same covariates in order to have precise estimations with high power and appropriate interpretation of covariate effects. The analysis was carried out with SAS Proc MIXED and STATA software. Results: A total of 32 studies from the published literature were analysed, covering 4,092 patients who received anthracycline-based and 2,501 treated with CMF for the disease free survival and in order to analyze the overall survival, 13 studies reported the overall survival curves in which 2,050 cases were treated with anthracycline-based and 1,282 with CMF regimens. Conclusions: The findings illustrated that the model with dependent variable Ln (-Ln(S)) had more precise estimations of the covariate effects and showed significant difference between the effects of two adjuvant chemotherapy regimens. Anthracycline-based treatment gave better disease free survival and overall survival. As an IPD meta-analysis in the Italy the results of Angelo et al in 2011 also confirmed that anthracycline-based regimens were more effective for survival of breast cancer patients. The findings of Zare et al 2012 on disease free survival curves in Asia also provided similar evidence.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.7
• /
• pp.4325-4328
• /
• 2013

Introduction: The influence of season at diagnosis on cancer survival has been an intriguing issue for many years. Most studies have shown a possible correlation in between the seasonality and some cancer type survival. With short expected survival, lung cancer is an arena that still is in need of new prognostic factors and models. We aimed to investigate the effect of season of diagnosis on 3 months, 1 and 2 years survival rates and overall survival of non small cell lung cancer patients. Materials and Methods: The files of non small cell lung cancer patients that were stages IIIB and IV at diagnosis were reviewed retrospectively. According to diagnosis date, the patients were grouped into 4 season groups, autumn, winter, spring and summer. Results: A total of 279 advanced non small cell lung cancer patients' files were reviewed. Median overall survival was 15 months in the entire population. Overall 3 months, 1 and 2 years survival rates were 91.0%, 58.2% and 31.2% respectively. The season of diagnosis was significantly correlated with 3 months survival rates, being diagnosed in spring being associated with better survival. Also the season was significantly correlated with T stage of the disease. For 1 and 2 years survival rates and overall survival, the season of diagnosis was not significantly correlated. There was no correlation detected between season and overall survivals according to histological subtypes of non small cell lung cancer. Conclusion: As a new finding in advanced non small cell lung cancer patients, it can be concluded that being diagnosed in spring can be a favorable prognostic factor for short term survival.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.4
• /
• pp.1545-1549
• /
• 2014

Background: Published studies on clinical outcome of helical tomotherapy for lung cancer are limited. The purpose of this study was to evaluate clinical outcomes and treatment-related toxicity in inoperable non-small cell lung cancer (NSCLC) patients treated with helical tomotherapy in Korea. Materials and Methods: Twenty-seven patients with NSCLC were included in this retrospective study. Radiotherapy was performed using helical tomotherapy with a daily dose of 2.1-3 Gy delivered at 5 fractions per week resulting in a total dose of 62.5-69.3 Gy. We assessed radiation-related lung and esophageal toxicity, and analyzed overall survival, locoregional recurrence-free survival, distant metastasis-free survival, and prognostic factors for overall survival. Results: The median follow-up period was 28.9 months (range, 10.1-69.4). The median overall survival time was 28.9 months, and 1-, 2-, and 3-year overall survival rates were 96.2%, 92.0%, and 60.0%. The median locoregional recurrence-free survival time was 24.3 months, and 1-, 2-, and 3-year locoregional recurrence-free survival rates were 85.2%, 64.5%, and 50.3%. The median distant metastasis-free survival time was 26.7 months, and 1-, 2-, and 3-year distant metastasis-free survival rates were 92.3%, 83.9%, and 65.3%, respectively. Gross tumor volume was the most significant prognostic factor for overall survival. No grade 4 or more toxicity was observed. Conclusions: Helical tomotherapy in patients with inoperable NSCLC resulted in high survival rates with an acceptable level of toxicity, suggesting it is an effective treatment option in patients with medically inoperable NSCLC.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.3
• /
• pp.1019-1024
• /
• 2015

Background: Survival of breast cancer patients depends on a number of factors which are not only prognostic but are also predictive. A number of studies have been carried out worldwide to find out prognostic and predictive significance of different clinicopathological and molecular variables in breast cancer. This study was carried out at Nuclear Medicine, Oncology and Radiotherapy Institute (NORI), Islamabad, to find out the impact of different factors on overall survival of breast cancer patients coming from Northern Pakistan. Materials and Methods: This observational retrospective study was carried out in the Oncology Department of NORI Hospital. A total of 2,666 patients were included. Data were entered into SPSS 20. Multinomial logistic regression analysis was performed to determine associations of different variables with overall survival. P values <0.05 were considered significant. Results: The mean age of the patients was 47.6 years, 49.5% being postmenopausal. Some 1,708 were ER positive and 1,615 were PR positive, while Her 2 neu oncogene positivity was found in 683. A total of 1,237 presented with skin involvement and 426 had chest wall involvement. Some 1,663 had > 5cm tumors. Lymph node involvement was detected in 2,131. Overall survival was less than 5 years in 669 patients, only 324 surviving for more than 10 years, and in the remainder overall survival was in the range of 5-10 years. Conclusions: Tumor size, lymph node metastases, receptor status, her 2 neu positivity, skin involvement, and chest wall involvement have significant effects whereas age and menopausal status have no significant effect on overall survival of breast cancer patients in Pakistan.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.12
• /
• pp.4861-4864
• /
• 2014

Background: The Ewing's sarcoma family is a group of small round cell tumors which accounts for 10-15% of all primary bone neoplasms. The aim of this study was to evaluate the survival of Ewing's sarcoma patients in our province and to determine of influencing factors. Materials and Methods: All patients with documented Ewing's sarcoma/primitive neuroectodermal tumor(PNET) family pathology were enrolled in this study during a period of eight years. For all of them local and systemic therapy were carried out. Overall and event free survival and prognostic factors were evaluated. Results: Thirty two patients were enrolled in the study. The median age was 17.5 years. Twenty (65.2%) were male and 9 (28.1%) were aged 14 years or less. Mean disease free survival was 26.8 (95%CI; 13.8-39.9) months and five year disease free survival was 26%. Mean overall survival was 38.7 months (95%CI; 25.9-50.6) and median overall survival was 24 months. Five year overall survival was 25%. From the variables evaluated, only presence of metastatic disease at presentation (p value=0. 028) and complete response (p value =0. 006) had significant relations to overall survival. Conclusions: Survival of Ewing's sarcoma in our province is disappointing. It seems to be mostly due to less effective treatment. Administration of adequate chemotherapy dosage, resection of tumor with negative margins and precise assessment of irradiation volume may prove helpful.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.11
• /
• pp.5681-5685
• /
• 2012

Three kinds of survival rates are generally used depending on the purpose of the investigation: overall, cause-specific, and relative. The differences among these 3 survival rates are derived from their respective formulas; however, reports based on actual cancer registry data are few because of incomplete information and short follow-up duration recorded on cancer registration. The aim of this study was to numerically and visually compare these 3 survival rates on the basis of data from the Nagasaki Prefecture Cancer Registry. Subjects were patients diagnosed with cancer and registered in the registry between 1999 and 2003. We calculated the proportion of cause of death and 5-year survival rates. For lung, liver, or advanced stage cancers, the proportions of cancer-related death were high and the differences in survival rates were small. For prostate or early stage cancers, the proportions of death from other causes were high and the differences in survival rates were large. We concluded that the differences among the 3 survival rates increased when the proportion of death from other causes increased.

• Journal of Korean Neurosurgical Society
• /
• v.60 no.6
• /
• pp.661-666
• /
• 2017

Objective : Atypical meningioma is rare tumor and there is no accurate guide line for optimal treatment. This retrospective study analyzed the prognostic factors, the effect of different methods of treatments and the behavior of atypical meningioma. Methods : Thirty six patients were diagnosed as atypical meningioma, among 273 patients who were given a diagnosis of meningioma in the period of 2002 to 2015. Age, gender, tumor location, Ki 67, Simpson grade and treatment received were analyzed. We studied the correlation between these factors with recurrence, overall survival rate and progression free survival. Results : Median overall survival time and progression free survival time are 60 and 53 (months). Better survival rate was observed for patients less than 50 years old but with no statistical significance (p=0.322). And patients with total resection compared with subtotal resection also showed better survival rate but no statistical significance (p=0.744). Patients with a tumor located in skull base compared with patients with a tumor located in brain convexity and parasagittal showed better progression free survival (p=0.048). Total resection is associated with longer progression-free survival than incomplete resection (p=0.018). Conclusion : We confirmed that Simpson grade was significant factor for statistically affect to progression free survival in univariate analysis. In case of skull base atypical tumor, it is analyzed that it has more recurrence than tumor located elsewhere. Overall survival was not affected statistically by patient age, gender, tumor location, Ki 67, Simpson grade and treatment received in this study.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.17
• /
• pp.7987-7990
• /
• 2015

Chronic lymphocytic leukemia (CLL)is the most common leukemia in adults in Western countries but is relatively rare in Asia. Immune hemolytic anemia, Evan's syndrome, lymphadenopathy, organomegaly and B symptoms are the main complaints of patients in CLL. The present retrospective analysis evaluated a group of 109 patients with CLL over a 9-year period, studying correlations between sex, age and overall survival. The patients were hospitalized in the Clinic of Hematology and Oncology, Kermanshah, Iran, between 2006 and 2014. Data analysis for sex and age was performed using IBM SPSS19 and overall survival was plotted by Kaplan-Meier plot, Log-rank test in Graph Pad prism 5 Software for five-year periods. The mean age of diagnosis for CLL patients was 60.73 years, 59.6% male. Survival rate patients was 64% and mean overall survival was 38.5 months. In the Rai system, fourteen patients (12.8%) had stage III and twenty eight patients (25.7%) had stage IV. Most frequent clinical features in patients with CLL were lymphadenopathy (38.7%) and organomegaly (34%), respectively. There is not relationship between sex and age in patients but overall survival rate in females was higher than in males. In Asian countries, CLL is more in male and in age above 60 years. Complaints about lymphadenopathy and virus infection are prevalent.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.17
• /
• pp.7463-7466
• /
• 2015

Aims: To analyse the predictors of recurrence, disease free survival and overall survival in cases with endometrial cancer. Materials and Methods: A total of 152 women diagnosed with endometrial cancer were screened using a prospectively collected database including age, smoking history, menopausal status, body mass index, CA125, systemic disorders, tumor histology, tumor grade, lymphovascular space invasion, tumor diameter, cervical involvement, myometrial invasion, adnexal metastases, positive cytology, serosal involvement, other pelvic metastases, type of surgery, fertility sparing approach to assess their ability to predict recurrence, disease free survival and overall survival. Results: In ROC analyses tumor diameter was a significant predictor of recurrence (AUC:0.771, P<0.001). The optimal cut off value was 3.75 with 82% sensitivity and 63% specificity. In correlation analyses tumor grade (r=0.267, p=0.001), tumor diameter (r=0.297, p<0.001) and the serosal involvement (r=0.464, p<0.001) were found to significantly correlate with the recurrence. In Cox regression analyses when some different combinations of variables included in the model which are found to be significantly associated with the presence of recurrence, tumor diameter was found to be a significant confounder for disease free survival (OR=1.2(95 CI,1.016-1.394, P=0.031). On Cox regression for overall survival only serosal involvement was found to be a significant predictor (OR=20.8 (95 % CI 2.4-179.2, P=0.006). In univariate analysis of tumor diameter > 3.75 cm and the recurrence, there was 14 (21.9 %) cases with recurrence in group with high tumor diameter where as only 3 (3.4 %) cases group with smaller tumor size (Odds ratio:7.9 (95 %CI 2.2-28.9, p<0.001). Conclusions: Although most of the significantly correlated variables are part of the FIGO staging, tumor diameter was also found to be predictor for recurrence with higher values than generally accepted.