• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.99-120
• /
• 2010

Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

• Journal of Chest Surgery
• /
• v.38 no.2 s.247
• /
• pp.152-156
• /
• 2005

Background: Occlusive complications after arterial revascularization are difficult to treat and have high recurrence rate. This study was performed to establish an effective treatment modality and to evaluate the factors affecting the occlusive complications by analysis of clinical data. Material and Method: During the period of 5 years. 33 patients (55 reoperations) were studied at the Department of Thoracic and Cardiovascular Surgery, Pusan National University Hospital following 173 arterial revascularization surgeries. The clinical characteristics, operating methods, the time intervals of reoperation, used graft, and the results of treatment were evaluated retrospectively. Result: All the patients were men except one and the mean age was 63.5 years old. The mean time internal from first operation to reoperation was 11.9 months. The cause of arterial occlusive diseases were 28 atherosclerosis and 5 Burger's diseases, Associated diseases were Hypertension $(57.6\%)$, Diabetes mellitus $(33.3\%)$, heart failure $(18.2\%)$, and so on. The mean rate of reoperation was 1.67 times and the most common type of first operation was femoro-popliteal bypass grafting $(57.6\%)$. The graft that used revascularization surgery were 25 cases of PTFE and 6 case were Dacron. There was no statistical difference between two groups. The kinds of reoperations were thrombectomy in 20 cases, angioplasty 18 cases, re-bypass surgery in 13 cases, and lumbar sympathectomy in 4 cases. The results of reoperation were 15 cases of functional recovery, 7 cases of limb salvage, 5 cases of above-knee amputation. 3 cases of below-knee amputation and 3 deaths. Conclusion: The main cause of occlusive complications are occlusion of inflow or outflow artery. Treatments were different according to the first operation methods and graft used. The most frequent time of reoperation was within one year after the first operation. We believe that graft surveillance especially during the first year is very important factor in observing the patient. We can look forward to improving limb salvage rate to perform additional treatment such as radiological interventions and lumbar sympathectomy.

• Journal of Chest Surgery
• /
• v.31 no.9
• /
• pp.884-892
• /
• 1998

Background: The gastroepiploic artery is not only an alternative graft but also may be considered an important primary graft for coronary revascularization. However, the long-term patency of the gastroepiploic arterial graft is yet to be determined and the incidence of perioperative spasm and long-term patency of a coronary graft may be affected by the properties of the graft response to certain vasoactive substances. The reactivity of the gastroepiploic artery to vasoactive substances has not been studied extensively and the results of the studies are contradictory. Material and Method: This study was designed to test the reactivity of human gastroepiploic artery to four constrictors and four relaxants. The middle sections of the human gastroepiploic arteries were collected from the patients undergoing gastrectomy and the arterial rings with intact endothelium were suspended in organ baths for isometric tension recording. Result: Epinephrine, norepinephrine, and potassium chloride induced the maximum constriction to higher forces (7.0$\pm$1.1g, 6.6$\pm$0.9g, and 6.5$\pm$1.1g) than 5-hydroxytryptamine did (3.8$\pm$1.7g, p<0.05). Nitroprusside and histamine induced almost full relaxation in the gastroepiploic arteries preconstricted with norepinephrine. There was no significant difference between two relaxants regarding maximum relaxation force. Acetylcholine induced the maximum relaxation to weaker force when compared with nitroprusside and histamine (p<0.05), and isoproterenol was the weakest of the relaxants (p<0.05 compared with acetylcholine). Conclusion: The gastroepiploic artery has a strong capacity of endothelium-dependent relaxation which could have an important influence on long-term patency. The gastroepiploic artery exhibits a potent contractility to catecholamines and the enhanced contractility may facilitate vasospasm in the presence of high circulating levels of catecholamines. Nitroprusside, a potent relaxant in gastroepiploic artery, might be beneficial for the treatment of gastroepiploic arterial graft spasm. The gastroepiploic arterial graft with intact endothelium may respond weakly to beta-adrenoceptor agonist and 5-hydroxytryptamine.

• Journal of Chest Surgery
• /
• v.31 no.9
• /
• pp.877-883
• /
• 1998

Background: Cardiopulmonary bypass(CPB), a standard adjunct for open heart surgery, can also play an important role in treating patients with noncardiac diseases. Material and Method: We report a collective analysis of noncardiac applications of cardiopulmonary bypass experienced at Seoul National University Hospital from 1969 to 1996. Out of a total of 20 patients, 8 were treated for membranous obstruction of inferior vena cava(MOVC), 5 for malignant melanoma, 3 for pulmonary embolism, 1 for double lung transplantation, 1 for intracranial giant aneurysm(GA), 1 for renal cell carcinoma(RC), and 1 for liposarcoma. CPB was used to induce profound hypothermia with circulatory arrest in 6 patients(MOVC 4, GA 1, RC 1). Result: CPB time was 113 mins on average for MOVC, 161 mins for GA, and 156 mins for RC, while the lowest rectal temperature was 26$^{\circ}C$ on average in MOVC, and 19$^{\circ}C$ in GA and RC. Postoperative recovery was good in all MOVC patients. The patient with GA, who underwent reoperation for the removal of hematoma, died 14 days postoperatively. The patient with RC recovered from the operation in a good condition but died from metastatic spread 6 months later. CPB was instituted for pulmonary embolectomy in 3 patients, in whom postoperative courses were uneventful, except in 1 patient who showed transient neurologic symptoms. CPB was used in a patient with double-lung transplantation for hemodynamic and ventilatory support. The patient was weaned successfully from CPB but died from low output and septicemia 19 days postoperatively. CPB without circulatory arrest was used to treat in 4 patients with MOVC. These patients showed good postoperative courses. CPB was used to administer high concentrations of chemotherapeutic agents to the extremities in 6 patients(malignant melanoma 5, recurrent liposarcoma 1). CPB time was 153 mins on average. No complications such as edema and neurologic disability were found. Conclusion: Although CPB has a limited indication in noncardiac diseases, if properly applied, it can be a very useful adjunct in a variety of surgical cases.

• Journal of Chest Surgery
• /
• v.32 no.3
• /
• pp.237-248
• /
• 1999

Background: The late results of repair of tetralogy of Fallot(TOF) are favorable in most patients. Some portion of the patients with tetralogy, however, require reoperation for residual lesions or result in late death. The outcome of patients after tetralogy repair performed during the past 13 years was studied, with an emphasis on postrepair survival and problems including reoperations. Material and Method: A retrospective review of clinical, echocardiographic and catheterization data was performed in 569 of 775 patients with TOF who underwent corrective repair between 1983 and 1995 at Sejong General Hospital, Buchon, Korea. Result: Of 28(4.9%) early deaths(defined as 30 days postrepair), 12 deaths(42.9%) were <1 year of age, with an operative mortality of 15.4%. The surviving 541 patients(age 2.8 months to 43.4 years, median 23 months) have been followed up from 1 month to 12.6 years(median 35 months) postoperatively. Most patients were in good functional class and had normal right ventricular(RV) function. Postrepair results were compared between the transatrial-transpulmonary approach and the conventional right ventriculotomy. The former technique provided a lesser incidence of significant pulmonary regurgitation(P<0.001) and alesser degree of RV dysfunction(P<0.05) compared with those in the latter. There were 10(1.8%) late deaths during the follow-up period and 6 of the deaths were directly related to reoperation or ventricular dysfunction. The 10-year actuarial survival rate was 96.7%. There were 44 reoperations(8.1%) in 39 patients(7.2%), with an operative mortality of 10.3%. The main indications or reoperation included residual ventricular septal defect(VSD) (n=6), pulmonary stenosis(PS) (n=11), VSD with PS(n=17), pulmonary regurgitation(n=7), and tricuspid regurgitation(n=2). The 5- and 10-year freedom from reoperation were 89.4% and 76.1%, respectively. Conclusion: Although the majority of patients with repaired TOF are clinically well, with a high rate of survival, approximately 7% of patients have residual lesions that require surgical therapy. Therefore, the timely and meticulous corrective repair is mandatory to avoid reoperation, and continued close surveillance is also needed for the early detection of residual problems.

• Journal of Chest Surgery
• /
• v.32 no.9
• /
• pp.781-789
• /
• 1999

Background: Pulmonary artery banding(PAB) accompanies some risks in the aspect of band complications and mortality in the second-stage operation. To assess these risks of the second-stage operation after PAB, we reviewed the surgical results of the second-stage operation in the pediatric patients who had undergone PAB in infancy. Material and Method: From May 1988 to June 1997, a total of 29 patients with preliminary PAB underwent open heart surgery. Ages ranged from 2 to 45 months(mean 20.6$\pm$9.0 months). Preoperative congestive heart failure conditions were improved after PAB(elective operation group) in 27 patients, but early second-stage procedures were required in the remaining 2 patients due to sustaining congestive heart failure(early operation group). Preoperative surgical indications included 2 double outlet right ventricles(DORV group) and 27 ventricular septal defects as the main cardiac anomaly(VSD group). Result: The mean time interval from PAB to the second-stage operation was 15.5$\pm$8.7 months(range 5 days to 45 months). One patient in the DORV group underwent intraventricular tunnel repair and modified Glenn procedure in the other. In the VSD group, the VSD was closed with a Dacron patch in all patients. Concomitant procedures included a right ventricular infundibulectomy in 4 patients and a valvectomy of the dysplastic pulmonary valve in 1 patient. At the second-stage operations, pulmonary angioplasty was required due to the stenotic banding sites in 18 patients. One patient underwent complete ligation of the main pulmonary artery with the modified Glenn procedure. The mortality at the second-stage operation was 17.2%(5 patients). Causes of death were 4 low cardiac output, and 1 autoimmune hemolytic anemia. Diagnosis with DORV and the early operative group were the risk factors for operative death in this series. There was 1 late death. Conclusion: This study revealed the second-stage operation for pulmonary artery debanding and closure of VSD in children was complicated by the correction of the acquired lesions with a significantly high incidence of morbidity and early postoperative deaths. Primary repair is recommended for isolated VSD, if possible.

• Journal of Chest Surgery
• /
• v.38 no.2 s.247
• /
• pp.110-115
• /
• 2005

Background: The aims of this paper were to review the mid term clinical results and to analyze the preoperative risk factors of isolated aortic valve replacement (AVR). Material and Method: Between January 1992 and February 2003, 80 patients underwent isolated AVR. 58 were male and 22 were female patients, raging from 12 to 75 years of age (mean :$46.8{\pm}13.0$ years). 74 patients except one early death and 5 follow-up loss were contacted by OPD or by telephone. The mean duration of follow-up was $44.2{\pm}29.7$ months and the total cumulative period was 272.8 patient-year. Result: The complications in hospital occurred in 35 cases : 12 wound problems (11 superficial, 1 deep), 11 arrhythmias (9 temporary, 2 persistent), 3 low cardiac output, and so forth. The late deaths were 4 cases : the heart-related deaths were 2 cases ($0.7\%$ patient-year). Conclusion: The risk factors that influenced the early mortality and morbidity were older age (> 60 years)(p=0.04), poor preoperative NYHA functional class (> 3) (p=0.048), high preoperative serum creatinin level (> 1.2 mg/100 ml)(p=0.031), long operation time (aortic clamping time>90 min)(p=0.042). The same factors influenced the late mortality and morbidity. Freedom from valve-related complication was $86.4{\pm}5.3\%,$ actuarial survival rate were $96.8{\pm}2.3\%$ at 3 years and $90.8{\pm}4.6\%$ at 10 years.

• Journal of Chest Surgery
• /
• v.40 no.1 s.270
• /
• pp.32-36
• /
• 2007

Background: Although acute renal failure (ARF) after coronary artery bypass graft (CABG) is relatively rare, but devastating complication with high mortality. Our study aims to evaluate the effectiveness of early application of CRRT in patients with ARF which developed after on-pump CABG. Material and Method: Two hundred and eighty seven patients underwent isolated on-pump CABG between May 2002 and Feb. 2006 at our institution, of whom 15 (5.2%) needed CRRT (11 patients for postoperatively developed ARF and the remaining 4 patients with preexisting dialysis-dependent chronic renal failure (CRF) for postoperative hemodynamic and metabolic control). Criteria for early application of CRRT were as follows; decreased urine output less than 0.5cc/h/kg for 2 consecutive hours and elevated serum creatinine level greater than 2.0 mg/dL. Result: The incidence of ARF requiring CRRT after on-pump CABG was 3.9% (11/283) and the overall hospital mortality of patient with CRRT was 33.3% (5/15). Of 5 deaths, 4 were patients with postoperatively developed ARF, and 1 was a patient with pre-existing dialysis-dependent CRF patient. The mean time between the operation and the initiation of CRRT was $25.8{\pm}5.8$ hours and the mean duration of CRRT was $62.1{\pm}41.2$ hours. Of the 7 survivors who were not on dialysis-dependent preoperatively, 6 patients fully recovered renal function during hospital stay and 1 patient required permanent renal supportive treatment after discharge from hospital. Conclusion: Early application of CRRT could maintain stable postoperative hemodynamic status and make outcomes better than those of previous reports in patients with ARF which developed after on-pump CABG.

• Journal of Chest Surgery
• /
• v.40 no.2 s.271
• /
• pp.103-108
• /
• 2007

Background: Surgical resection is an important modality in the treatment of pulmonary metastases from various solid tumors. We analyzed 37 patients who underwent surgical treatments of pulmonary metastases in our hospital from 1996 to 2005. Material and Method: Age, sex, disease free interval, operative procedure, the number of pulmonary metastases, and lymphatic metastasis were investigated with admission and operative records, and pathologic reports. Actuarial survival and comparisons between each survival rate were calculated according to Kaplan-Meier method and log-rank test, respectively, Result: Complete resections were carried out in 34 of 37 patients. The primary tumor was carcinoma in 25 cases, sarcoma in 10, and others in 2. The number of pulmonary metastases was 1 in 25 cases and 2 or more in 12 cases. 3-year and 5-year survival rates after complete resection were 50.5% and 35.9%, respectively. 3-year and 5-year survival rates for carcinoma were 64.5% and 45.0%, respectively, and 3-year survival rate for sarcoma was 17.5%. Otherwise, none of the operative procedures, the number of pulmonary metastases, lymphatic metastasis, adjunctive therapy and the disease free interval in the case of carcinoma significantly affected the survival rates. Conclusion: Complete resection of pulmonary metastasis in well selected patients allows high long term survival rate with low mortality and morbidity. Long-term follow up and randomized prospective studies were necessary to determine the prognostic factors of pulmonary metastases after surgical resection.

• Journal of Chest Surgery
• /
• v.40 no.6 s.275
• /
• pp.407-413
• /
• 2007

Background: The brain natriuretic peptide (BNP) level has been reported in some studies to be associated with the occurrence of atrial fbrillation (AF). The aim of this study is to evaluate the potential usefulness of the BNP level as a predictor of the occurrence of postoperative (postop) AF and to assess the relationship of the BNP level with the onset of AF and the restoration of sinus rhythm. Material and Method: From January 1, 2005 to February 28, 2006, 82 patients without a history of atrial arrhythmia that had undergone cardiac surgery were enrolled in the study. Blood samples for plasma BNP were drawn daily for all these patients from the preoperative (preop) day to the 7th postop day. The patient records were reviewed and postop EKGs were checked daily for AF until the time of discharge. Result: Patients were divided into two groups based on development of postop AF. Postoperative AF developed in 26 patients (31.7%). There was no significant statistical difference in age, sex distribution, preop left ventricle ejection fraction, hypertension, left ventricular hypertrophy, or the use of beta blockers between the non-postop AF and postop AF group. More patients in the AF group had undergone valve surgery (39.3% versus 76.9%, p=0.002). The preop left atrium size was significantly larger in the AF patients ($43.8{\pm}10.3 mm$ versus $49.8{\pm}11.5 mm$, p=0.029). The preop plasma BNP levels were higher in the postop AF patients ($144.1{\pm}20.8 pg/mL$ versus $267.5{\pm}68 pg/mL$, p=0.034). In the postop AF group, the plasma BNP level was the highest on the 3rd postop day. Postop AF developed in most patients by the 3rd postop day; restored sinus rhythm developed by the 7th postop day. Conclusion: Elevated plasma BNP levels may lead to the occurrence of postop AF in patients undergoing cardiac surgery. Patients who have a high risk of postop AF should be considered for aggressive prophylactic antiarrhythmic therapy.