• Radiation Oncology Journal
• /
• v.16 no.4
• /
• pp.389-398
• /
• 1998

Purpose : To evaluate the role of conventional postoperative adjuvant radiotherapy in the management of supratentorial malignant glioma and to determine favorable prognostic factors affecting survival. Materials and Methods : From Sep. 1985 to Mar. 1997, the number of eligible patients who received postoperative radiotherapy completely was 69. They ranged in age from 7 to 66 years (median, 47). Forty-two (61$\%$) patients were glioblastoma multiforme and the other 27 (39$\%$) were anaplastic astrocytoma. Twenty patients (29$\%$) had Karnofsky score equal or more than 80 preoperatively. Forty-three patients (62$\%$) had symptom duration equal or less than 3 months. Twenty-four patients (35$\%$) had gross total resection and forty patients(58$\%$) had partial resection, the remaining five patients (7$\%$) had biopsy only. Radiotherapy dose ranged from 50.4 Gy to 61.2 Gy (median, 55.8; mode, 59.4) with fraction size of 1 8 Gy-2.0 Gy for 33-83 days(median, 48) except three patients delivered 33, 36, 39 Gr, respectively with fraction size of 3.0 Gy due to poor postoperative performance status. Follow-up rate was 93$\%$ and median follow-up period was 14 months. Results : Overall survival rate at 2 and 3 years and median survival were 38$\%$, 20$\%$, and 16 months for entire patients; 67$\%$, 44$\%$, and 34 months for anaplastic astrocytoma; 18$\%$, 4$\%$, and 14 months for glioblastoma multiforme, respectively (p=0.0001). According to the extent of surgery, 3-year overall survival for gross total resection, partial resection, and biopsy only was 38$\%$, 11$\%$, and 0$\%$, respectively (p=0.02) The 3-year overall survival rates for patients age 40>, 40-59, and 60< were 52$\%$, 8$\%$, and 0$\%$, respectively (p=0.0007). For the variate of performance score 80< vs 80>, the 3-year survival rates were 53$\%$ and 9$\%$, respectively (p=0.008). On multivariate analysis including covariates of three surgical and age subgroups as above, pathology, extent of surgery and age were significant prognostic factors affecting overall survival. On another multivariate analysis with covariates of two surgical (total resection vs others) and two a9e (50> vs 50<) subgroups, then, pathology, extent of surgery and performance status were significant factors instead of age and 3-year cumulative survival rate for the five patients with these three favorable factors was 100$\%$ without serious sequela. Conclusion : We confirmed the role of postoperative conventional radiotherapy in the management of supratentorial malignant glioma by improving survival as compared with historical data of surgery only. Patients with anaplastic astrocytoma, good performance score, gross total resection and/or young age survived longest. Maximum surgical resection with acceptable preservation of neurologic function should be attempted in glioblastoma patients, especially in younger patients. But the survival of most globlastoma patients without favorable factors is still poor, so other active adjuvant treatment modalities should be tried or added rather than conventional radiation treatment alone in this subgroup.

• Radiation Oncology Journal
• /
• v.19 no.3
• /
• pp.216-223
• /
• 2001

Purpose : We evaluated retrospectively the outcomes of inoperable squamous cell lung cancer patients treated with radiotherapy to find out prognostic factors affecting survival. Materials and methods : Four hundred and eleven patients diagnosed as squamous cell lung cancer between November 1988 and December 1997 were the basis of this analyses. The planned dose to the gross tumor volume was ranged from 30 to 70.2 Gy. Chemotherapy was combined in 72 patients $(17.5\%)$ with the variable schedule and drug combination regimens. Follow-up period ranged from 1 to 113 months with the median of 8 months and survival status was identified in 381 patients $(92.7\%)$. Overall survival rate was calculated using the Kaplan-Meier method. Results : Age ranged from 23 years to 83 years with the median 63 years. The male to female ratio was about 16:1. For all 411 patients, the median overall survival was 8 months and the 1-year survival rate (YSR), 2-YSR, and 5-YSR were $35.6\%,\;12.6\%,\;and\;3.7\%$, respectively. The median and 5-YSR were 29 months and $33.3\%$ for Stage IA, 13 months and $6.3\%$ for Stage IIIA, and 9 months and $3.4\%$ for Stage IIIB, respectively(p=0.00). The median survival by treatment aim was 11 months in radical intent group and 5 months in palliative, respectively (p=0.00). Of 344 patients treated with radical intent, median survival of patients (N=247) who received planned radiotherapy completely was 12 months while that of patients (N=97) who did not was 5 months (p=0.0006). In the analyses of the various prognostic factors affecting to the survival outcomes in 247 patients who completed the planned radiotherapy, tumor location, supraclavicular LAP, SVC syndrome, pleural effusion, total lung atelectasis and hoarseness were statistically significant prognostic factors both in the univariate and multivariate analyses while the addition of chemotherapy was statistically significant only in multivariate analyses. The acute radiation esophagitis requiring analgesics was appeared in 49 patients $(11.9\%)$ and severe radiation esophagitis requiring hospitalization was shown in 2 patients $(0.5\%)$. The radiation pneumonitis requiring steroid medication was shown in 62 patients $(15.1\%)$ and severe pneumonitis requiring hospitalization was occurred in 2 patients $(0.5\%)$. During follow-up, 114 patients $(27.7\%)$ had progression of local disease with 10 months of median time to recur (range : $1\~87\;months$) and 49 patients $(11.9\%)$ had distant failure with 7 months of median value (range : $1\~52\;months$). Second malignancy before or after the diagnosis of lung cancer was appeared in 11 patients Conclusion : The conventional radiotherapy in the patients with locally advanced squamous cell lung cancer has given small survival advantage over supportive care and it is very important to select the patient group who can obtain the maximal benefit and to select the radiotherapy technique that would not compromise the life quality in these patients.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.16 no.1
• /
• pp.18-23
• /
• 2016

Objective: Newborn screening leads to improved treatment and disease outcomes, but false-positive newborn screening results may impact include parental stress and anxiety, perception of child as unhealthy, parent-child relationship dysfunction, and increased infant hospitalizations. The purpose of this study was to investigate of the false positive rates and the causative factors of false positive results in Tandem Mass Spectrometry (TMS) in single center. Methods: Records were reviewed for all 18,872 subjects who were born in Cheill General Hospital, during January 1st, 2012 to December 31st, 2014. 17,292 neonates (91.62%) were tested for tandem mass screening almost in 2-5th day of life. Newborn babies whose first results were abnormal had been tested repeatedly by same methods in 7-14 day. If the results were abnormal again, further evaluation was performed. TMS analysis included data for the 43 disorders screened for using TMS broken down into three categories: fatty acid oxidation disorders, organic acidurias, and aminoacidopathies. The impact of several factors on increased false positive rates was analyzed using a multivariate analysis: time from birth to sample collection, birth weight, birth height, BMI, gender, gestational age, delivery type. Results: Males of the subjects were 8942 (51.7%), female 8350 (48.3%), the mean gestational age was $38.6{\pm}1.7$ weeks, the average birth weight $3,155.6{\pm}502.4g$, the average birth height $49.1{\pm}2.9cm$, and the average BMI $13.0{\pm}3.8(kg/m^2)$. Vaginal delivery cases were 9713 (56.2%), caesarean section 7,579 (43.8%). The average date of the inspection was $2.8{\pm}1.1$ days. 224 cases were identified as TMS positive. All the subjects were false positive (222/17,292, 1.30%) except 2 cases (1 male; benign phenylketonuria and 1 female; Short chain acyl-CoA dehydrogenase deficiency). The false positive rates were 0.61% in fatty acid oxidation disorders, 0.25% in organic acidurias, and 0.45% in aminoacidopathies. In our study, the date of inspection got late, the false positive rates got higher. Because almost the cases of late test date were in treatment in neonatal intensive care unit so their test date was affected by their medical conditions. False positive rate was higher in extreme immaturity${\leq}27$ weeks than newborns of gestational age >27 weeks [OR=6.957 (CI=1.273-38.008), p<0.025] and extremely low birth weight<1,000 g than newborns of birthweight ${\geq}1,000g$ [OR=5.616 (CI=1.134-27.820), p<0.035]. Conclusion: False positive rate of TMS was 1.30% in Cheil General Hospital. Lower gestational age and birth weight impacted on increased false positive rates. Better understanding of factors that influence the reporting of screening tests, and the ability to modify these important factors, may improve the screening process and reduce the need for retesting. of screening tests, and the ability to modify these important factors, may improve the screening process and reduce the need for retesting.

• Radiation Oncology Journal
• /
• v.27 no.4
• /
• pp.189-193
• /
• 2009

Purpose: To report on the changes in the patterns of care and survival over time for esthesioneuroblastoma. Materials and Methods: We retrospectively analyzed 42 previously untreated and histologically confirmed esthesioneuroblastoma patients seen between March 1989 and June 2007. According to Kadish's classification, 3 patients (7%) were stage A, 6 (14%) at stage B, and 33 (79%) at stage C. Of the 33 Kadish C patients, 19 and 14 patients were treated from 1989 through 2000 and from 2001 through 2007, respectively. Treatment included surgical resection, radiotherapy, chemotherapy, or a combination of these methods. Chemotherapy was administered to 8 of 19 patients (42%) seen from 1989 through 2000, whereas all of the 14 patients seen from 2001 through 2007 received chemotherapy (p<0.001). No patient was treated by three-dimensional conformal radiotherapy (3D-CRT) from 1989 through 2000, however 8 of 14 patients (67%) seen from 2001 through 2007 underwent 3D-CRT (p<0.001). The median follow-up time for surviving patients was 6.5 years (range, 2.2~15.8 years). Results: The 5-year overall survival (OS) and progression-free survival (PFS) rates for the entire cohort were 53% and 39%, respectively. The 5-year OS was 100% for Kadish stages A or B and 39% for stage C (p=0.007). For patients with stage C disease who were treated from 1989 to 2000 and from 2001 to 2007, the 5-year OS rate was 26% and 59% (p=0.029), respectively and the corresponding 5-year PFS rate was 16% and 46% (p=0.001), respectively. Intraorbital extension and treatment era (1989~2000 vs. 2001~2007) were found as independent factors for OS and PFS in a multivariate analyses. Conclusion: The results of this study suggest that treatment era, which features a distinction in treatment modality and technique with the introduction of 3D-CRT, may be the cause of improved OS and PFS in Kadish stage C patients. To achieve better outcomes for patients with Kadish stage C, combined chemoradiotherapy, especially 3D-CRT, is recommended in addition to surgery.

• Radiation Oncology Journal
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2008

Purpose: This study evaluates the association of estrogen receptor(ER), progesterone receptor(PR), Her-2, COX-2, and survivin with the clinicopathological features and outcomes in young Korean women with breast cancer using recently developed tissue microarray(TMA) technology. Materials and Methods: A cohort of 212 young patients with breast cancer diagnosed at the age of 45 years or younger from March 1994 to August 2005, were enrolled in this study. The age range of patients was $23{\sim}45$ years(median age, 39 years). The minimum and median follow-up periods were 24 months and 60 months, respectively. Serial sections of primary tumors were processed by the use of a TMA for immunohistochemical staining for five biomarkers. The correlation of these five biomarkers and the clinicopathological features and outcomes were analyzed by statistical methods. Results: The majority of the patients were stage T1(90 patients) or T2(101 patients), and 105 patients(49.5%) had an axillary node metastasis. The 5-year overall and relapse free survival rates for all of the patients were 90.4% and 82.3%, respectively, and 36 patients had a locoregional or distant metastasis as a first event. Positive expression of ER, PR, Her-2, COX-2, and survivin was determined in 38.2%, 45.3%, 25.9%, 41.5%, and 43.4%, of the tumor samples, respectively. Tumor stage, nodal status, age, as well as expression of ER, PR, and HER-2 status were significantly associated with the disease free survival rate. Tumor stage, nodal status, as well as expression of ER, PR, and HER-2 were significantly related with the overall survival rate. Expression of COX-2 and survivin were not single independent prognostic factors for the disease free and overall survival rate although co-expression of HER-2 and COX-2 had a tendency as a poor prognostic factor. By multivariate analysis, only T stage and lymph node status were significant prognostic factors, and ER status was a marginally significant prognostic factor(p=0.075). Conclusion: Expression of ER, PR and HER-2 were significant prognostic factors for the relapse free and overall survival rate. Expression of COX-2 and survivin were not prognostic factors for young women with breast cancer.

• Journal of Gastric Cancer
• /
• v.7 no.3
• /
• pp.152-159
• /
• 2007

Purpose: Recently, the use of laparoscopic assisted gastrectomy for early gastric cancer has been on the increase and the procedure has been quickly adopted by clincians. However, there are few reports regarding the safety and risk of this type of surgery. The aim of this study is to evaluate the morbidity and to verify the safety of laparoscopic assisted gastrectomy for early gastric cancer. Materials and Methods: A total of 376 patients that had undergone laparoscopic assisted gastrectomy for early gastric cancer between April 2004 and December 2006 were reviewed retrospectively. The clinicopathological characteristics, operative complications, and factors related to complications were evaluated. Results: The overall operative morbidity and mortality rates were 10.6% and 0%, intraoperative morbidity was 1.1% (4 of 376 patients) and post operative morbidity was 9.6% (36 of 376 patients). Most complications required no surgery except for an intestinal obstruction in two cases. Multivariate analysis of risk factors related to operative morbidity determined that age was an independent factor associated with morbidity (P=0.021). Conclusion: The complication rate of laparoscopic assisted gastrectomy is low and most complications can be managed by conservative methods rather than with surgery. There were no specific predicting factors for complications except old age. Laparoscopy is a technically feasible and acceptable surgical modality for early gastric cancer.

• Radiation Oncology Journal
• /
• v.22 no.4
• /
• pp.254-264
• /
• 2004

Purpose: This study was carried out to confirm clinical values and limitations of postoperative radiotherapy for hypopharyngeal carcinoma, to evaluate various prognostic factors which may affect to the treatment results and to use these results as fundamental data for making a new treatment strategy. Methods and Materials:. A retrospective analysis was peformed on 64 previously untreated patients with squamous cell carcinoma of the hypopharynx, seen between 1988 and 1999 at Pusan National University Hospital. Most of patients were treated by laryngopharyngectomy and neck dissection followed by conventional fractionated postoperative radiotherapy on surgical bed and cervical nodal areas. Results: The five-year overall survival rate and cause-specific survival rate were 42.2 percent and 51.6 percent, respectively. Univariate analysis of various clinical and pathologic factors confirmed the overall stage, TN-stage, secondary primary cancers, surgical positive margin, nodal extracapsular extension, total radiation doses as significant prognostic factors of hypopharyngeal carcinomas. But in multivariate analysis, TN-stage, surgical positive margin and extracapsular extesion were only statistically significant. Conclusion: In resectable cases of hypopharyngeal carcinoma, combined surgery and postoperative radio-therapy obtained good treatement results, even though sacrificing the function of larynx and pharynx. But in advanced and unresectable cases, with respect to survivals and qualify of life issues, we were able to confirm some limitations of combined therapy. So we recommend that comparative studies of recent various chemo-radiotherapy methods and advanced radiotherapy techniques with these data should be needed.

• Radiation Oncology Journal
• /
• v.28 no.2
• /
• pp.57-63
• /
• 2010

Purpose: We performed an immunohistochemical study with pre-treatment biopsy specimens to evaluate the prognostic significance of four biomolecular markers which can be used as a predictive assay for radiotherapy (RT) treatment of nasopharyngeal carcinoma (NPC). Materials and Methods: From January 1998 through December 2006, 68 patients were histologically diagnosed as non-metastatic NPC and treated by RT. Only 38 patients had the paraffin block for the immunohistochemical study. Thirty-one patients had undifferentiated carcinoma and 7 patients had squamous cell carcinoma. Thirtytwo patients (84%) had advanced stage NPC (2002 AJCC Stage III~IV). Immunohistochemical staining was performed for Met, COX-2, nm23-H1, and epidermal growth factor receptor (EGFR) expression using routine methods. Results: The median follow-up time was 30 months (range, 11 to 83 months) for all patients, and 39 months (range, 19 to 83 months) for surviving patients. The 5-year overall survival (OS) rate of the patients with high Met extent (${\geq}50%$) was significantly lower than that of the patients with low Met extent (48% vs. 84%, p=0.02). In addition, Met extent was also a significant prognostic factor in multivariate analysis (p=0.01). No correlation was observed between Met extent and T stage, N stage, stage group, gender, age, and the response to chemotherapy or RT. Met extent showed moderate correlation with COX-2 expression (Pearson coefficient 0.496, p<0.01), but COX-2 expression did not affect OS. Neither nm23-H1 or EGFR expression was a prognostic factor for OS in this study. Conclusion: High Met extent (${\geq}50%$) might be an independent prognostic factor that predicts poor OS in NPC treated with RT.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.