• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Chest Surgery
• /
• v.38 no.2 s.247
• /
• pp.116-122
• /
• 2005

Background: Adverse effects of cardiopulmonary bypass can be avoided by 'Off-pump' coronary artery bypass (OPCAB) surgery. Recent studies have reported that OPCAB had the most beneficial impact on patients at highest risk by reducing bypass-related complications. The purpose of this study is to compare the outcome of OPCAB and conventional coronary artery bypass grafting (CCAB) in patients with poor left ventricular (LV) function. Material and Method: From March 1997 to February 2004, seventy five patients with left ventricular ejection fraction (LVEF) of $35\%$ or less underwent isolated coronary artery bypass grafting at our institute. Of these patients, 33 patients underwent OPCAB and 42 underwent CCAB. Preoperative risk factors, operative and postoperative outcomes, including LV functional change, were compared and analysed. Result: Patients undergoing CCAB were more likely to have unstable angina, three vessel disease and acute myocardial infarction among the preoperative factors. OPCAB group had significantly lower mean operation time, less numbers of total distal anastomoses per patient and less numbers of distal anastomoses per patient in the circumflex territory than the CCAB group. There was no difference between the groups in regard to in-hospital mortality $(OPCAB\; 9.1\%\;(n=3)\;Vs.\;CCAB\;9.5\%\;(n=4)),$ intubation time, the length of stay in intensive care unit and in hospital postoperatively. Postoperative complication occurred more in CCAB group but did not show statistical difference. On follow-up echocardiography, OPCAB group showed $9.1\%$ improvement in mean LVEF, 4.3 mm decrease in mean left ventricular end-diastolic dimension (LVEDD) and 4.2 mm decrease in mean left ventricular end-systolic dimension (LVESD). CCAB group showed $11.0\%$ improvement in mean LVEF, 5.1 mm decrease in mean LVEDD and 5.5 mm decrease in mean LVESD. But there was no statistically significant difference between the two groups. Conclusion: This study showed that LV function improves postoperatively in patients with severe ischemic LV dysfunction, but failed to show any difference in the degree of improvement between OPCAB and CCAB. In terms of operative mortality rate and LV functional recovery, the results of OPCAB were as good as those of CCAB in patients with poor LV function. But, OPCAB procedure was advantageous in shortening of operative time and in decrease of complications. We recommend OPCAB as the first surgical option for patients with severe LV dysfunction.

• Journal of Chest Surgery
• /
• v.39 no.3 s.260
• /
• pp.184-193
• /
• 2006

Background: Off-pump coronary artery bypass grafting (OPCAB) has been proven to result in less morbidity. The patients who have left ventricular dysfunction may have benefits by avoiding the adverse effects of the cardiopulmonary bypass. The present study compared early and midterm outcomes of off-pump versus on-pump coronary artery bypass grafting (On pump CABG) in patients with severe left ventricular dysfunction. Material and Method: Ninety hundred forth six patients underwent isolated coronary artery bypass grafting by one surgeon between January 2001 and Febrary 2005.. Data were collected in 100 patients who had left ventricular ejection fraction (L VEF) less than $35\%$ (68 OPCAB; 32 On pump CABG). Mean age of patients were 62.9$\pm$9.0 years in OPCAS group and 63.8$\pm$8.0 years in On pump CABG group. We compared the preoperative risk factors and evaluated early and midterm outcomes. Result: In OPCAB and On pump CABG group, mean number of used grafts per patient were 2.75$\pm$0.72, 2.78$\pm$0.55 and mean number of distal anastomoses were 3.00$\pm$0.79, 3.16$\pm$0.72 respectively. There was one perioperative death in OPCAB group ($1.5\%$). The operation time, ventilation time, ICU stay time, CK-MB on the first postoperative day, and occurrence rate of complications were significantly low in OPCAB group. Mean follow-up time was 26.6$\pm$12.8 months (4${\~}$54 months). Mean LVEF of OPCAB and On pump CABG group improved significantly from $27.1\pm4.5\%$ to $40.7\pm13.0\%$ and $26.9\pm5.4\%$ to $33.3\pm13.7\%$. The 4-year actuarial survival rate of OPCAB and On pump CABG group were $92.2\%,\;88.3\%$ and the 4-year freedom rates from cardiac death were $97.7\%,\;96.4\%$ respectively. There were no significant differences between two groups in 4 year freedom rate from cardiac event and angina. Conclusion: OPCAS improves myocardial function and favors early and mid-term outcomes in patients with severe left ventricular dysfunction compared to On pump CABG group. Therefore, OPCAB is a preferable operative strategy even in patients with severe left ventricular dysfunction.

• Radiation Oncology Journal
• /
• v.19 no.3
• /
• pp.237-244
• /
• 2001

Purpose : To assess the tolerance, complete response rate, bladder preservation rate and survival rate in patients with muscle-invading bladder cancer treated with selective bladder preservation protocol. Method and Materials : From October 1990 to June 1998, twenty six patients with muscle-invading bladder cancer (clinical stage T2-4, N0-3, M0) were enrolled for the treatment protocol of bladder preservation. They were treated with maximal TURBT (transurethral resection of bladder tumor) and 2 cycles of MCV chemotherapy (methotrexate, crisplatin, and vinblastine) followed by $39.6\~45\;Gy$ pelvic irradiation with concomitant cisplatin. After complete urologic evaluation (biopsy or cytology), the patients who achieved complete response were planed for bladder preservation treatment and treated with consolidation cisplatin and radiotherapy (19.8 Gy). The patients who had incomplete response were planed to immediate radical cystectomy. If they refused radical cystectomy, they were treated either with TURBT followed by MCV or cisplatin chemotherapy and radiotherapy. The median follow-up duration is 49.5 months. Results : The Patients with stage T2-3a and T3b-4a underwent complete removal of tumor or gross tumor removal by TURBT, respectively. Twenty one out of 26 patients $(81\%)$ successfully completed the protocol of the planned chemo-radiotherapy. Seven patients had documented complete response. Six of them were treated with additional consolidation cisplatin and radiotherapy. One patient was treated with 2 cycles of MCV chemotherapy due to refusal of chemo-radiotherapy. Five of 7 complete responders had functioning tumor-free bladder. Fourteen patients of incomplete responders were further treated with one of the followings : radical cystectomy (1 patient), or TURBT and 2 cycles of MCV chemotherapy (3 patients), or cisplatin and radiotherapy (10 patients). Thirteen patients of them were not treated with planned radical cystectomy due to patients' refusal (9 patients) or underlying medical problems (4 patients). Among twenty one patients, 12 patients $(58\%)$ were alive with their preserved bladder, 8 patients died with the disease, 1 patient died of intercurrent disease. The 5 years actuarial survival rates according to CR and PR after MCV chemotherapy and cisplatin chemoradiotherapy were $80\%\;and\;14\%$, respectively (u=0.001). Conclusion : In selected patients with muscle-invading bladder cancer, the bladder preservation could be achieved by MCV chemotherapy and cisplatin chemo-radiotherapy. All patients tolerated well this bladder preservation protoco. The availability of complete TURBT and the responsibility of neoadjuvant chemotherapy and chemoradiotherapy were important predictors for bladder preservation and survival. The patients who had not achieved complete response after neoadjuvant chemotherapy and chemoradiotherapy should be immediate radical cystectomy. A randomized prospective trial might be essential to determine more accurate indications between cystectomy or bladder preservation.

• Radiation Oncology Journal
• /
• v.16 no.1
• /
• pp.35-41
• /
• 1998

Purpose : To investigate the role of adjuvant chemoradiotherapy in adenocarcinoma of the rectum, we retrospectively compared the treatment results between postoperative adjuvant radiotherapy alone and combined chemoradiotherapy. Material and Methods : From October 1989 to May 1994, 141 patients with rectal carcinoma were treated by postoperative adjuvant therapy in Yonsei Cancer Center. Sixty eight patients were treated by radiation therapy alone. Seventy three patients were treated by combined chemoradiotherapy. Radiation therapy was delivered with 10 MV linear accelerator, 180cGy fraction/5 days per week. Total radiation doses were 5400cGy in the postoperative radiotherapy alone group. Three to twelve cycles of Fluorouracil(mean dose $393.9mg/m^2$) with Leucovorin($20mg/m^2$) and 5040cGy of radiation were delivered in the combined chemoradiotherapy group. Third and 4th cycle of chemotherapy were administrated during the radiation treatment in the combined group. The median follow up was 38 months with a range of 3 to 81 months. Results : The 5 year overall survival rate of radiation alone group and combined group were $60.1\%$ and $66.3\%$, respectively. The 5 year disease free survival rate of radiation aione group and combined group were $54.2\%$ and $65.5\%$, respectively There was no significant difference of overall survival and disease free survival between RT alone group and combined group(p<0.05). But the 5 year Local failure free survival rate of combined group was significantly better than radiotherapy alone group($05.8\%\;vs.\;50.3\%.\;p=0.04$). Conclusion : There was no significant difference in overall survival, disease free survival, and distant metastasis free survival between postoperative adjuvant radiotheray alone group and combinded chemoradiotherapy group. Only the Local failure free survival rate was superior in the combined treatment group. These results confirm the radiosensitizing effect of the chemotherapeutic agent in the combined chemoradiotherapy treatment.

• Radiation Oncology Journal
• /
• v.16 no.1
• /
• pp.43-49
• /
• 1998

Purpose : Carcinomas arising in the gall bladder(GB) or extrahepatic biliary ducts are uncommon and generally have a poor prognosis. The overall 5-year survival rates are less than $10\%$. Early experiences with the external radiation therapy demonstrated a good palliation with occasional long-term survival. The present report describes our experience over the past decade with irradiation of primary carcinomas of the gallbladder and extrahepatic biliary duct. Materials and Methods : From Feb. 1984 to Nov. 1995, thirty-three patients with carcinoma of the GB and extrahepatic biliary duct were treated with external beam radiotherapy with curative intent at our institution. All patients were treated with 4-MV linear accelerator and radiation dose ranged from 31.44Gy to 54.87Gy(median 44.25Gy), and three Patients received additional intraluminal brachytherapy(range, 25Gy to 30Gy). Twenty-seven Patients received postoperative radiation. Among 27 patients, Sixteen patients underwent radical operation with curative aim and the rest of the patients either had bypass surgery or biopsy alone. In seventeen patients, adjuvant chemotherapy was used and eleven patients were treated with 5-FU, mitomycin and leucovorin. Results : Median follow up period was 8.5 months(range 2-97 months). The overall 2-year and 5-year survival rates in all patients were $29.9\%$ and $13.3\%$ respectively. In patients with GB and extrahepatic biliary duct carcinomas, the 2-year survival rates were $34.5\%$ and $27.8\%$ respectively. Patients who underwent radical operation showed better 2-year survival rates than those who underwent palliative operation($43.8\%\;vs.\;20.7\%$), albeit statistically insignificant(p>0.05). The 2-year survival rates in Stage I and II were higher than in Stage III and IV with statistical significance(p<0.05). Patients with good performance status in the beginning showed significantly better survival rates than those with worse status(p<0.05). The 2-year survival rates in combined chemotherapy group and radiation group were $40.5\%$ and $22.0\%$ respectively. There was no statistical differences in two groups (p>0.05). Conclusion : The survival of patients with relatively lower stage and/or initial good performance was significantly superior to that of others. We found an statistically insignificant trend toward better survival in patients with radical operation and/or chemotherapy, More radical treatment strategies, such as total resection with intensive radiation and/or chemotherapy may offer a better chance for cure in selective patients with carcinoma of gall bladder and extrahepatic biliary ducts.

• Radiation Oncology Journal
• /
• v.20 no.3
• /
• pp.237-245
• /
• 2002

Purpose : This study was conducted to evaluate the treatment results, prognostic factors, and complication rates after high dose rate (HDR) brachytherapy in patients with uterine cervix cancer who were treated with curative aim. Materials and Methods : Of 269 cervix cancer patients treated at the department of radiation oncology, Samsung Medical Center from September 1994 to July 1998, the 106 who were treated with radical radio-therapy were analyzed. The median age was 61 years (range 22 to 89). All patients except 4 with carcinoma in situ (CIS) were given external beam radiotherapy (range $30.6\~50.4\;Gy$ to whole pelvis) and HDR brachytherapy. The common regimens of HDR brachytherapy were a total dose of $24\~28\;Gy$ with $6\~7$ fractions to point A at two fractions per week. The median overall treatment time was 55 days (range 44 to 104) in patients given both external beam radiotherapy and HDR brachytherapy. Results : Early responses of radiotherapy were evaluated by gynecologic examination and follow-up MRI 1 month after radiotherapy. Treatment responses were complete remission in 72 patients, partial response in 33 and no response in 1. The overall survival (OS) rate of all patients was $82\%,\;and\;73\%$, and the disease free survival (DFS) rate was $72\%,\;and\;69\%$, at 3, and 5 years, respectively. The pelvic control rate (PCR) was $79\%$ at both 3 and 5 years. According to the FIGO stage,3 and 5 year OS were $100\%\;and\;50\%$ in CIS/IA, $100\%\;and\;100%$ in IB, $83\%\;and\;69\%$ in IIA, $87\%\;and\;80\%$ in IIB, and $62\%\;and\;62\%$ in III, respectively. The 3 year OS in 4 patients with stage IVA was $100\%$. Three-year DFS were $80\%$ in CIS/IA, $88\%$ in IB, $100\%$ in IIA, $64\%$ in IIB, $58\%$ in III, and $75\%$ in IVA. Three-year PCR were $100\%$ in CIS/IA, $94\%$ in IB, $100\%$ in IIA, $84\%$ in IIB, $69\%$ in III, and $50\%$ in IVA. By univariate analysis, FIGO stage and treatment response were significant factors for OS. The significant factors for DFS were age, FIGO stage, treatment response and overall treatment time (OTT). For pelvic control rate, treatment response and OTT were significant factors. By multivariate analysis, FIGO stage had a borderline significance for OS (p=0.0825) and treatment response had a borderline significance for DFS (0=0.0872). A total of 14 patients $(13\%)$ experienced rectal bleeding, which occurred from 3 to 44 months (median, 13 months) after the completion of radiotherapy. Conclusion : HDR brachytherapy protocol of Samsung Medical Center combined with properly optimal external beam pelvic irradiation is a safe and effective treatment for patients with uterine cervix cancer. The authors found that OTT of less than 55 days had a positive impact on pelvic control and survival rate.

• Radiation Oncology Journal
• /
• v.16 no.4
• /
• pp.433-440
• /
• 1998

Purpose : Although small ceil lung cancer (SCLC) has high response rate to chemotherapy and radiotherapy (RT), the prognosis is dismal. The authors evaluated survival and failure patterns according to the prognostic factors in SCLC patients who had thoracic radiation therapy with chemotherapy. Materials and Methods : One hundred and twenty nine patients with SCLC had received thoracic radiation therapy from August 1985 to December 1990. Seventy-seven accessible patients were evaluated retrospectively among 87 patients who completed RT. Median follow-up period was 14 months (2-87months). Results : The two years survival rate was 13$\%$ with a median survival time of 14 months. The two year survival rates of limited disease and extensive disease were 20$\%$ and 8$\%$, respectively, with median survival time of 14 months and 9 months, respectively. Twenty two patients (88$\%$) of limited disease showed complete response (CR) and 3 patients (12$\%$) did partial response (PR). The two year survival rates on CR and PR groups were 24$\%$ and 0$\%$, with median survival times of 14 months and 5 months. respectively (p=0.005). No patients with serum sodium were lower than 135 mmol/L survived 2years and their median survival time was 7 months (p=0.002). Patients whose alkaline phophatase lower than 130 IU/L showed 26$\%$ of 2 year survival rate and showed median survival time of 14 months and those with alkaline phosphatase higher than 130 IU/L showed no 2 year survival and median survival time of 5 the months, respectively (p=0.019). No statistical differences were found according to the age, sex, and performance status. Among the patients with extensive disease, two rear survivals according to the metastatic sites were 14$\%$, 0$\%$, and 7$\%$ in brain, liver, and other metastatic sites, respectively, with median survival time of 9 months, 9 months, and 8 months, respectively (p>0.05). Two year survivals on CR group and PR group were 15$\%$ and 4$\%$, respectively, with a median survival time of 11 months and 7 months, respectively (p=0.01). Conclusion : For SCLC, complete response after chemoradiotherapy was the most significant prognostic tactor. To achieve this goal. there should be further investigation about hyperfractionation, dose escalation, and compatible chemo-radiation schedule such as concurrent chemo-radiation and early radiation therapy with chemotherapy.

• Childhood Kidney Diseases
• /
• v.7 no.2
• /
• pp.166-173
• /
• 2003

Purpose : The cause and pathogenesis of $Henoch-Sch\"{o}nlein$ purpura has been studied for many years but the results are disappointing. Recently the hypothesis that abnormalities involving the glycosylation of the hinge region of immunoglobulin Al(IgAl) may have an important role in the pathogenesis of $Henoch-Sch\"{o}nlein$ purpura is being approved. $Henoch-Sch\"{o}nlein$ purpura is the most common vasculitis Ihat affects children and the prognosis is good. But if kidney invovement occurs, the course may be chronic and troublesome. So we evaluated children with $Henoch-Sch\"{o}nlein$ purpura especially from the point of epidemiology and clinical manifestations. Methods : Investigation of 124 children who were diagnosed with $Henoch-Sch\"{o}nlein$ purpura at Inje University Ilsan Paik Hospital from December 1999 to July 2003 was performed retrospectively through chart review. Efforts were made to get informations about the profile, epidemiology, clinical manifestations, progress of the disease and recurrence rate of patients. Results : The patients were 69 boys and 55 girls, with a mean age of $6.1{\pm}2.7$ years at the time of data collection. The male to female ratio was 1.25 : 1. The occurrence rate was much higher in autumn(from September to November, 31.5%) and winter(from December to February, 28.2%) than in spring and summer, with a peak in November. Joint involvement was shown in 66.9% of patients mostly on the foot/ankle(75.9%), knee(39.8%). Seventy(56.5%) out of 124 patients had abdominal pain and 10 patients(8.1%) showed bloody stools. Renal involvement was observed in 24 patients(19.4%) after 21.1 days on the average. IgA was elevated in 10 of 21 patients(47.6%). $C_3$ and $C_4$ levels were normal in 40 of 49 patients (81.7%) and 47 of 48 patients(97.9%), respectively Antistreptolysin-O(ASO) titer was elevated over 250 Todd units in 29 of 62 Patients(46.8%). Mycoplasma antibody titer was elevated in 21 of 49 patients(42.9%) equal or greater than 1:80. Radiologic studies were peformed in 23 patients. Seven patients(30.4%) showed bowel wall thickening and one of them received intestinal resection and anastomosis operation due to terminal ileum necrosis. Eighty four patients took steroid 1.4 mg/kg/day in average. Recurrence rate was 2.5 in 37 patients(29.8%). Conclusion : $Henoch-Sch\"{o}nlein$ purpura in childhood appears most in about 6 years of age. The occurrence rate is much higher in autumn and winter relatively. Diagnosis can be made through the perspective history taking and the inspection of clinical manifestations, but the laboratory findings are not of great help. A small portion of the patients might show abdominal pain or arthritis before purpura develops, therfore various diagnosis can be made. Radiologic evaluation should be performed to avoid surgical complications in cases accompanying abdominal pain, and long term follow up should be needed especially in patients suffering from kidney involvement. In about 30% of the patients $Henoch-Sch\"{o}nlein$ purpura would recur. Steroid can be used safely without side effects.

• Journal of Genetic Medicine
• /
• v.7 no.2
• /
• pp.125-132
• /
• 2010

Purpose: Preimplantation genetic diagnosis (PGD), also known as embryo screening, is a pre-pregnancy technique used to identify genetic defects in embryos created through in vitro fertilization. PGD is considered a means of prenatal diagnosis of genetic abnormalities. PGD is used when one or both genetic parents has a known genetic abnormality; testing is performed on an embryo to determine if it also carries the genetic abnormality. The main advantage of PGD is the avoidance of selective pregnancy termination as it imparts a high likelihood that the baby will be free of the disease under consideration. The application of PGD to genetic practices, reproductive medicine, and genetic counseling is becoming the key component of fertility practice because of the need to develop a custom PGD design for each couple. Materials and Methods: In this study, a survey on the contents of genetic counseling in PGD was carried out via direct contact or e-mail with the patients and specialists who had experienced PGD during the three months from February to April 2010. Results: A total of 91 persons including 60 patients, 49 of whom had a chromosomal disorder and 11 of whom had a single gene disorder, and 31 PGD specialists responded to the survey. Analysis of the survey results revealed that all respondents were well aware of the importance of genetic counseling in all steps of PGD including planning, operation, and follow-up. The patient group responded that the possibility of unexpected results (51.7%), genetic risk assessment and recurrence risk (46.7%), the reproduction options (46.7%), the procedure and limitation of PGD (43.3%) and the information of PGD technology (35.0%) should be included as a genetic counseling information. In detail, 51.7% of patients wanted to be counseled for the possibility of unexpected results and the recurrence risk, while 46.7% wanted to know their reproduction options (46.7%). Approximately 96.7% of specialists replied that a non-M.D. genetic counselor is necessary for effective and systematic genetic counseling in PGD because it is difficult for physicians to offer satisfying information to patients due to lack of counseling time and specific knowledge of the disorders. Conclusions: The information from the survey provides important insight into the overall present situation of genetic counseling for PGD in Korea. The survey results demonstrated that there is a general awareness that genetic counseling is essential for PGD, suggesting that appropriate genetic counseling may play a important role in the success of PGD. The establishment of genetic counseling guidelines for PGD may contribute to better planning and management strategies for PGD.