• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.255-266
• /
• 2021

The purpose of this study is to compare the effects of treatment on stage III stomach cancer data obtained from the SEER program of the National Cancer Institute and to identify the significant risk factors for the survival rates of stage III stomach cancer. Since the proportional hazards assumption was violated for treatment, we used the restricted mean survival time as an alternative to the proportional hazards model. The restricted mean survival time was estimated using pseudo-observations, and the effects of treatment were compared using a test statistic based on the estimated restricted mean survival times. We conducted the regression analysis using a generalized linear model to investigate the significant predictors for the restricted mean survival time of patients with stage III stomach cancer. We found that there was a significant difference between the restricted mean survival times of treatment groups. Age at diagnosis, race, substage, grade, tumor size, surgery, and treatment were significant predictors for the restricted mean survival time of patients with stage III stomach cancer. Surgery was the most significant predictor for increasing the restricted mean survival time of patients with stage III stomach cancer.

• The Korean Journal of Applied Statistics
• /
• v.23 no.3
• /
• pp.521-531
• /
• 2010

Interval-censored observations are common in medical and epidemiologic studies; however, limited studies exist due to the complexity and special structure of interval-censoring. This paper introduces the imputation method and the self consistency method in the interval-censored data. We propose a new method of generating random numbers under an interval-censoring set-up. Through simulation studies we compare two methods under various simulation schemes in the sense of the mean squared error for estimating the median survival time and the mean integrated squared error for estimating the survival function. Under a moderate censoring percentage, the mean imputation method showed a better performance than the self-consistency method in estimating the median survival time and the survival function.

• Archives of Plastic Surgery
• /
• v.38 no.5
• /
• pp.636-641
• /
• 2011

Purpose: There are multiple dependent variables commonly attributed to survival of replanted digits. The ischemia time is thought to be a clinically relevant factor. However, controversy exists as large hand centers have reported successful replant outcomes independent of ischemic time. In this study, we present a single institution experience on the effect of ischemia time on the survival of completely amputated digits. Methods: A retrospective review of a single institution experience was performed. This cohort included all comers who had suffered complete amputation of a digit (Zone 2-4) and underwent replantation from 2003 to 2009. Demographic information as well as injury mechanism, ischemic time, and replantation outcome were recorded for each patient. Chi-square was used to analyze the result. Results: Mean age was 35.5 years old (2-69). Mean replantation survival was 89.5% (37/317). Survival rates were 94, 88, and 88% in respective groups of 0~6, 6~12, of > 12 hours of ischemia time. In chi-square analysis, there was no difference with $p$ value of 0.257. No other independent patient factors showed statistically significant relationship to replant survival rate. In the group with longest ischemia time (12~18 hours) replant survival rate was 88% (37/42). Conclusion: Prolonged ischemia time is commonly believed to be a contributing factor for replant survival. However, our experience has shown that survival rate is uniform up to 18 hours of ischemia.

• Journal of Korean Neurosurgical Society
• /
• v.29 no.11
• /
• pp.1445-1450
• /
• 2000

Objectives : The Objective of this study was to analyze the prognostic factors affecting survival in the patients with glioblastomas. Methods : We retrospectively studied 55 consecutive patients with glioblastomas who were admitted to neurosurgery department from January 1988 to March 1998. Fifteen pateients were excluded from the analysis because of follow-up loss and surgical motality. There were 24 male and 16 female patients, with a mean age of 51 years. Surgery consisted of biopsy in 4(10.0%) patients, subtotal resection in 9(22.5%) patients and gross total resection in 27(67.5%) patients. Nine(22.5%) patients received second operation. Twenty-eight(70%) received postoperative radiation therapy. Various levels of radiation dose were used, 6,000 rad over 7 weeks in most cases. The variable factors were examined for their relationship with survival ; age at the time of diagnosis, gender, duration of neurological symptoms, preoperative neurological state(Karnofsky performance score), extent of surgical resection, location of tumor, reoperation, and postoperative radiotherapy and chemotherapy. Result : The mean survival time was 55 weeks, three(7.5%) of the 40 patients survived more than two years. Survival time with biopsy only cases was 24 weeks, for those with subtotal resection 43 weeks, and for those with gross total resection 67 weeks. A mean survival time from the time of reoperation was 42 weeks. Statistically significant survival factors in glioblastoma were extent of surgical resection, postoperative radiotherapy and reoperation. Summary : Results of our series support the views that the extent of surgery, reoperation and postoperative radiation are important prognostic factors. We also recommend radical tumor removal, postoperative radiotherapy and reoperation, if possible.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.5
• /
• pp.1151-1160
• /
• 2014

In DNA microarray studies, the number of genes far exceeds the number of samples and the gene expression measures are highly correlated. Partial least squares regression (PLSR) is one of the popular methods for dimensional reduction and known to be useful for the classifications of microarray data by several studies. In this study, we suggest a modified version of the partial least squares regression to analyze gene expression data with survival information. The method is designed as a new gene selection method using PLSR with an iterative procedure of imputing censored survival time. Mean square error of prediction criterion is used to determine the dimension of the model. To visualize the data, plot for variables superimposed with samples are used. The method is applied to two microarray data sets, both containing survival time. The results show that the proposed method works well for interpreting gene expression microarray data.

• Journal of Preventive Medicine and Public Health
• /
• v.22 no.1 s.25
• /
• pp.81-89
• /
• 1989

The authors investigated mortality rate of hospitalized CWP(coal workers' pneumoconiosis) patients. Date, which was composed of age, date of hospitalization, date of death, and radiological findings(profusion of small opacity, type of large opacity, tuberculosis, emphysema, pneumothorax, and cardiac abnormality), was gathered from medical charts and chest x-ray films at the time of hospitalization of CWP patients. Among 738 CWP patients, that were entered survey differently and have followed different period, 160 CWP patients were died during different observational period. Mean value of observational period was 203 weeks, and mean age at hospitalization was 51 years. Because of short observational period, mean survival time could not found. There was statistically significant difference of mortality rate between group of small opacity and that of large opacity. In group of small opacity 5 year survival rate was 0.80 and in group of large opacity that was 0.73. And 80 percentile survival time was 57 months in group of small opacity and that was 40 months in group of large opacity.

• Journal of Korean Neurosurgical Society
• /
• v.30 no.4
• /
• pp.430-436
• /
• 2001

Objective : The proliferative potential of intracranial glioma affects the histological malignancy and prognosis of patients with these tumors. In this study, we present the relationship between MIB-1 labeling index(LI) and clinical variables which might play the major role in determining the prognosis of patient with astrocytic tumors. Patients and Methods : Excised tumor specimens from a total of 52 patients were stained to detect monoclonal MIB-1-Ki-67 antibody by avidin-biotin complex immunohistochemistry. The MIB-1 LI was evaluated with histological grades, demograpghic data, and survival time. The statistical significance of their correlation was analyzed by Pearson correlation test. Results : The 52 patients included 30 male patients and 22 female patients. The tumors according to the criteria of the World Health Organization(WHO) classification were verified as pleomorphic xanthoastrocytoma in one, pilocytic astrocytomas 4, astrocytomas 1, anaplastic astrocytomas 3, and glioblastomas 31. MIB-1 LI in astrocytic ttumors showed no correlation with age and gender. However, the patients under 10 years had the longest survival time, whereas short survival time was observed in the older patients. The mean MIB-1 LI of different tumor grades were as follows : pleomorphic xanthoastrocytoma, $4.40{\pm}0.00$ ; pilocytic astrocytoma, $4.53{\pm}3.09$ ; astrocytoma, $5.50{\pm}6.03$ ; anaplastic astrocytoma, $12.68{\pm}12.50$ ; Glioblastoma, $21.31{\pm}19.63$. Although the levels of MIB-1 LI were varied in individual tumors, the MIB-1 LI was increased in parallel with the histological grades. Glioblstomas showed significantly higher MIB-1 LI compared with that of anaplastic astrocytomas and low grade astrocytomas (p = 0.001). The mean survival time of entire group of patients was also well correlated with MIB-1 LI in astrocytic tumors(p = 0.015). Moreover, the mean survival time of the entire group of patients with Lis < 10 was $125.33{\pm}113.57weeks$, and the mean survival of those with $Lis{\geq}10$ was $60.71{\pm}62.58weeks$. This difference was also statistically significant(p = 0.004). Conclusion : The results of this study suggest that MIB-1 LI correlates with histological grades and might play a significant role in predicting the survival of patients with astrocytic tumors.

• Journal of Korean Neurosurgical Society
• /
• v.49 no.2
• /
• pp.92-96
• /
• 2011

Objective : We retrospectively evaluated the prognostic factors that can influence long-term survival in patients who suffered acute large cerebral infarction. Methods : Between June 2003 and October 2008, a total of 178 patients were diagnosed with a large cerebral infarction, and, among them, 122 patients were alive one month after the onset of stroke. We investigated the multiple factors that might have influenced the life expectancies of these 122 patients. Results : The mean age of the patients was $70{\pm}13.4$ years and the mean survival was $41.7{\pm}2.8$ months. The mean survival of the poor functional outcome group ($mRS{\geq}4$) was $33.9{\pm}3.3$ months, whereas that of the good functional outcome group ($mRS{\leq}3$) was $58.6{\pm}2.6$ months (p value=0.000). The mean survival of the older patients (270 years) was $29.7{\pm}3.4$ months, whereas that of the younger patients (<70 years) was much better as $58.9{\pm}3.2$ months (p value=0.000). Involvement of ACA or PCA territory in MCA infarction is also a poor prognostic factor (p value=0.021). But, other factors that are also known as significant predictors of poor survival (male gender, hypertension, heart failure, atrial fibrillation, diabetes mellitus, a previous history of stroke, smoking, and dyslipidemia) did not significantly influence the mean survival time in the current study. Conclusion : Age (older versus younger than 70 years old) and functional outcome at one month could be critical prognostic factors for survival after acute large cerebral infarction. Involvement of ACA or PCA territory is also an important poor prognostic factor in patients with MCA territorial infarction.

• Journal of Chest Surgery
• /
• v.33 no.4
• /
• pp.301-305
• /
• 2000

Background: The surgical indications of stage IV non-small cell lung cancer(NSCLC) are extremely limited with its controversial results. We analyzed the surgical results and survival in selected patients with resectable stage IV NSCLC. Material and Method: We reviewed the medical records of 21 patients who underwent operation for stage IV NSCLC from Jan. 1992 to Sep. 1999. Result: The mean age of patients was 55.6 years(range: 35 to 78). Sixteen were men and 5 were women. Tissue types were squamous cell carcinoma in 10(45.5%), adenocarcinoma in 9(40.9%), large cell carcinoma in 1 and carcinosarcoma in 1. Distant metastatic lesions were ipsilateral other lobe of lung in 18, brain in 2 and adrenal gland in 1. Pneumonectomy was performed in 16 patients, bilobectomy in 3, and lobectomy in 2 who underwent previous operatin for brain metastasis. Mean follow-up duration was 21.2$\pm$17.7 months. During follow-up period, 13 patients died. Three-and 5-year survival of patients were 38.0% and 19.0%, the median survival time was 19.1$\pm$7.8 months. In the group with ipsilateral pulonary metastasis(PM, n=18), 3- and 5-year survival of patients with N0 and N1(n=9) disease were 64.8% and 32.4%, median survival time was 55.3$\pm$27.2 months. Three-year survival of patients with N2(n=9) disease was 11.1%, median survival time was 10.6$\pm$0.3 months. The survival of N0 and N1 disease group was significantly better than that of N2 disease group(p=0.042). Also the disease free survival of N0 and N1 was significantly better than that of N2 disease in overall group(53.3 months vs 12.1 months, p=0.036) and ipsilateral PM group(63.4 months vs 8.8 months, p=0.001). Conclusion: We suggest that surgical treatment is worthful modality in well selected patients with stage IV NHSCLC especially with ipsilateral PM and N0 or N1 disease,. Nevertheless our study indicate questions that will need to be experienced further in larger studies.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.14
• /
• pp.5571-5575
• /
• 2014

Background: The ability to predict the survival time of breast cancer patients is important because of the potential high morbidity and mortality associated with the disease. To develop a predictive inference for determining the survival of breast cancer patients, we applied a novel Bayesian method. In this paper, we propose the development of a databased statistical probability model and application of the Bayesian method to predict future survival times for White Hispanic female breast cancer patients, diagnosed in the US during 1973-2009. Materials and Methods: A stratified random sample of White Hispanic female patient survival data was selected from the Surveillance Epidemiology and End Results (SEER) database to derive statistical probability models. Four were considered to identify the best-fit model. We used three standard model-building criteria, which included Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC) to measure the goodness of fit. Furthermore, the Bayesian method was used to derive future survival inferences for survival times. Results: The highest number of White Hispanic female breast cancer patients in this sample was from New Mexico and the lowest from Hawaii. The mean (SD) age at diagnosis (years) was 58.2 (14.2). The mean (SD) of survival time (months) for White Hispanic females was 72.7 (32.2). We found that the exponentiated Weibull model best fit the survival times compared to other widely known statistical probability models. The predictive inference for future survival times is presented using the Bayesian method. Conclusions: The findings are significant for treatment planning and health-care cost allocation. They should also contribute to further research on breast cancer survival issues.