• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.260-268
• /
• 2024

Cervical cancer is the fourth most common cancer in women worldwide, and more than 604,000 new cases were reported in 2020 alone, resulting in approximately 341,831 deaths. The Cox regression model is a major model widely adopted in cancer research, but considering the existence of nonlinear associations, it faces limitations due to linear assumptions. To address this problem, this paper proposes ResSurvNet, a new model that improves the accuracy of cervical cancer mortality prediction using ResNet's residual learning framework. This model showed accuracy that outperforms the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study. As this model showed accuracy that outperformed the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study, this excellent predictive performance demonstrates great value in early diagnosis and treatment strategy establishment in the management of cervical cancer patients and represents significant progress in the field of survival analysis.

• Tuberculosis and Respiratory Diseases
• /
• v.61 no.3
• /
• pp.207-213
• /
• 2006

기존의 폐암 발생의 고위험군(나이. 흡연력, $FEV_1$, 가족력, 직업적 발암물질의 노출력, 기존의 폐암 및 두경부 종양)에 대한 저선량 나선식 CT와 기관지 내시경 검사로 선별 검사 시 폐암의 유병률은 높아야 2%내외이고 대부분 그보다 낮은 것으로 알려져 있다. 특이도는 49-90%, 양성예측률은 10%이하로 선별검사 시 불필요한 검사를 초래하고 그에 따른 이환률과 사망률을 증가시키며 비용적인 문제를 야기하는 것으로 알려져 있다. 이에 기존의 고위험군에 대해 대상 환자를 더욱 더 좁힐 필요가 있으며, 이는 실제 임상적으로 이용 가능한 생물학적 표지자의 개발의 필요성이 있다고 하겠다. 그러나 현재까지 알려진 폐암조기검진에 대한 각종 진단 수기 중애서 상기의 3가지 방법(저선량 MDCT, 자가형광기관지경 및 객담내 MAGE)을 한꺼번에 시행하는 program은 비용적인 문제는 있지만 시도해 볼 만한 방법이라고 생각된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.384-390
• /
• 2020

Purpose: Organophosphate insecticide poisoning can have clinically fatal results. This study aimed to evaluate the relationship between the neutrophil/lymphocyte ratio (NLR) and the occurrence of death in patients with organophosphate insecticide poisoning. Methods: For this retrospective study, data on patients with organophosphate insecticide poisoning who visited the emergency room between January 2008 and November 2018 were collected. The NLR was measured at the time of arrival in the emergency room. The patients were divided into survival and death groups. Results: Overall, 150 patients were enrolled: 15 (10%) in the death group and 135 (90%) in the survival group. In the univariate analysis, the following variables were significantly different between the two groups: age, white blood cell count, amylase level, creatinine level, Acute Physiology And Chronic Health Evaluation (APACHE) II score, and NLR. In the logistic regression analysis of variables with significant differences in the univariate analysis, there were significant differences between the two groups with respect to age, APACHE II score, and NLR. The NLR was significantly higher in the death group than in the survival group (20.83 ± 22.24 vs. 7.38 ± 6.06, p=0.036). Conclusion: High NLR in patients with organophosphate insecticide poisoning may be useful in predicting mortality.

• Clinical and Experimental Pediatrics
• /
• v.52 no.10
• /
• pp.1153-1160
• /
• 2009

Purpose:To evaluate the risk factors for mortality and prognostic factors in pediatric hemato-oncology patients admitted to the pediatric intensive care unit (PICU). Methods:We retrospectively reviewed the medical records of pediatric hemato-oncology patients admitted at the PICU of the Asan Medical Center between September 2005 and July 2008. Patients admitted at the PICU for perioperative or terminal care were excluded. Results:Total 88 patients were analyzed. Overall ICU mortality rate was 34.1%. Mean age at PICU admission was $7.0{\pm}5.7$ years and mean duration of PICU stay was $18.1{\pm}22.2$ days. Hematologic diseases contributed to 77.3% of all the primary diagnoses, and the primary cause of admission was respiratory failure (39.8%). The factors related to increased mortality were C-reactive protein level (P<0.01), ventilation or dialysis requirement (P<0.01), and hematopoietic stem cell transplantation (P<0.05). In all, 3 scoring systems were investigated [Number of Organ System Failures (OSF number), the Pediatric Risk of Mortality III (PRISM III) score, and the Sequential Organ Failure Assessment (SOFA) score]; higher score correlated with worse outcome (P<0.01). The Oncological Pediatric Risk of Mortality (O-PRISM) scores of the 21 patients who had received hematopoietic stem cell transplantation were higher among the non-survivors, but not statistically significant (P=0.203). Conclusion:The PRISM III and SOFA scores obtained within 24 hours of PICU admission were found to be useful as early mortality predictors. The highest OSF number during the PICU stay was closely related to poor outcome.

• Journal of Chest Surgery
• /
• v.43 no.3
• /
• pp.285-291
• /
• 2010

Background: Thoracic trauma is one of the leading causes of morbidity and mortality in developing countries. A rib fracture that is secondary to blunt thoracic trauma is an important indicator of the severity of the trauma. The purpose of study was to determine the morbidity and mortality rates and the management of rib fractures. Material and Method: We performed a retrospective study that involved all the blunt trauma patients with rib fractures, excluding those that were transferred to other hospital within 3 days, that were seen at our hospital between May 2002 and December 2008. Of the 474 admitted patients, 454 met the inclusion criteria. There were 356 male and 98 females, and their overall mean age was 53 years (range: 5~90 years). The outcome parameters included the mechanism of injury, the number of fractured ribs, the length of stay in the ICU, the Injury Severity Score (ISS), the length of the hospital stay, the pulmonary complications and the mortality. Result: The mechanism of trauma included traffic accidents in 189 (41.7%) cases, slipping down in 103 (22.7%) cases, falls in 85 (18.7%) cases, cultivator accidents in 30 (6.6%) cases, industrial accidents in 32 (7.0%) cases and assault in 15 (3.3%) cases. Intrathoracic injury was noted such as hemothorax in 269 (59.3%) cases, pneumothorax in 144 (31.7%) cases, pulmonary contusion in 95 (20.9%) cases, subcutaneous emphysema in 29 (6.4%) cases and great vessel injury in 5 (0.1%) cases. Conservative treatment was administered to most of the patients. Tube thoracostomy was administered in 234 (51.5%) cases, whereas thoracotomy was performed in 18 (4.0%) cases. The mean duration of thoracostomy was $5.2{\pm}6.2$ days. Most of the cases with rib fracture were treated in wards and their mean duration of hospital stay was $22.5{\pm}20$ days. The mean Injury Severity Score (ISS) was $14.8{\pm}10.9$ (range: 3~75). The mortality rate was calculated to be 4.8% (n=22). The main factors correlated with an adverse outcome were the number of ribs fractured, the duration of thoracostomy and pulmonary disease. Industrial insurance affected the length of hospitalization. Pulmonary contusion and the Injury Severity Score (ISS) affected the mortality. Conclusion: Rib fractures are a indicator of severe injury. Because of the complication and associated injuries, we believe these patients should be admitted for evaluation and treatment. Recent studies on the impact of rib fractures after blunt trauma have shown that patients as young as 40 years of age demonstrate increased morbidity and mortality with similar injuries as compared to that of older patients. The ISS and pulmonary contusion influenced the mortality rate. Patients with isolated rib fractures should be hospitalized if the number of fractured ribs is one or more.

• Tuberculosis and Respiratory Diseases
• /
• v.65 no.2
• /
• pp.99-104
• /
• 2008

Background: Acute respiratory distress syndrome (ARDS) is ultimately an inflammatory state. The erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP) level are inflammatory markers. The aim of this study was to evaluate the value of the ESR, CRP and APACHE II score as prognostic factors for patient with ARDS. Methods: We retrospectively analyzed the medical records of 87 ARDS patients. The predictors (APACHE II score, ESR and CRP) and outcomes (mortality and length of the total hospital stay, the ICU stay and mechanical ventilator care) were obtained from the patients' records. The patients were grouped according to survival as the Survivor and Non survivor groups. We compared the APACHE II score, the ESR and the CRP level between the survivor group and the nonsurvivor group. We evaluated the correlation between the predictors and the outcomes. The initial ESR, CRP level and APACHE II score were checked at the time of ICU admission and the second ESR and CRP level were checked $3.3{\pm}1.2$ days after ICU admission. Results: Thirty-eight (43.7%) patients remained alive and 49 (56.3%) patients died. The APACHE II score was significantly lower for the survivor group than that for the non survivor group ($14.7{\pm}7.6$ vs $19.6{\pm}9.1$, respectively, p=0.006). The initial ESR and CRP level were not different between the survivor and non-survivor groups (ESR $64.0{\pm}37.8mm/hr$ vs $63.3{\pm}36.7mm/hr$, respectively, p=0.93, CRP $15.5{\pm}9.6mg/dl$ vs $16.3{\pm}8.5mg/dl$, respectively, p=0.68). The decrement of the CRP level for the survivor group was greater than that for the non survivor group ($-8.23{\pm}10.0mg/dl$ vs $-1.46{\pm}10.1mg/dl$, respectively, p=0.003). Correlation analysis revealed the initial ESR was positively correlated with the length of the total hospital stay and the ICU stay (correlation coefficient of the total hospital days: R=0.43, p=0.001, correlation coefficient of the ICU stay: R=0.39, p=0.014). Conclusion: The initial APACHE II score can predict the mortality of ARDS patients, and the degree of the early CRP change can be a predictor of mortality for ARDS patients. The initial ESR has positive correlation with the ARDS patients' duration of the total hospital stay and the ICU stay.

• Korea journal of population studies
• /
• v.34 no.2
• /
• pp.113-133
• /
• 2011

The generation of babyboomers has a significant impact on the socio-economic development of the society in general. The Korean Babyboomers will soon leave from their workforce as they reach the retirement age. This, coupled with the low fertility rate, may cause a serious social problem in the society at large as well as the social welfare issues among the Korean elderly population. The Central Statistical Systems have estimated the future projection which plays critical role to establish fundamental basis for the social and economic policies of the nation. This study examined the effect of the babyboomers on the life expectancy by comparing forecasted life expectancies provided by the statistical office and the previous studies in the related areas. The study also suggested a future population projection based on fertility rates provided, along with the changes of the number of babyboomers as they become ageing. The study results with the comparison between the population projection by the statistical office are provided.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.868-871
• /
• 2014

오늘날 한국에서는 급성 심근경색증으로 인한 사망률이 높은 상태로, 발병 시에 치료까지 신속한 의사결정이 요구되는 위중한 질병이기 때문에, 한국인에게 맞는 급성 심근경색증 연구가 매우 중요 하다. 본 연구는 한국인 급성 심근경색증 등록 데이터를 이용해 기계 학습 방법의 한 종류인 나이브 베이지안 방법을 이용해 급성 심근경색증 환자의 예후를 예측하고자, 의료 데이터의 특성에 따른 데이터 변환 방법을 제안한다. 타겟 클래스에서 보다 중요한 의미를 가진 death 값에 대해 각 값을, nominal value, numeric value, 결측치로 구분한 방식에 따라, 확률을 계산해 변환한다. 실험 결과를 통해 결측치를 피처마다 존재하는 값들의 평균을 낸 값으로 대입하였을 때 가장 좋은 성능임을 알 수 있었는데, 기존의 방법에 비해 precision=5.4%, recall=7.0%의 성능이 향상되었다. 따라서 제안한 방법은 나이브 베이지안 방법의 예측 성능 향상에 기여하였다고 판단된다. 이후 적용했던 데이터 변환 방법을 여러 가지 기계 학습 방법에서 판단해보고, 다른 타겟 클래스에도 시험해보고자 한다.

• Journal of Korean Academy of Nursing
• /
• v.41 no.1
• /
• pp.92-100
• /
• 2011

Purpose: Mortality Provability Model (MPM) II is a model for predicting mortality probability of patients admitted to ICU. This study was done to test the validity of MPM II for critically ill neurological patients and to determine applicability of MPM II in predicting mortality of neurological ICU patients. Methods: Data were collected from medical records of 187 neurological patients over 18 yr of age who were admitted to the ICU of C University Hospital during the period from January 2008 to May 2009. Collected data were analyzed through $X^2$ test, t-test, Mann-Whiteny test, goodness of fit test, and ROC curve. Results: As to mortality according to patients' general and clinically related characteristics, mortality was statistically significantly different for ICU stay, hospital stay, APACHE III score, APACHE predicted death rate, GCS, endotracheal intubation, and central venous catheter. Results of Hosmer-Lemeshow goodness-of-fit test were MPM $II_0$ ($X^2$=0.02, p=.989), MPM $II_24$ ($X^2$=0.99 p=.805), MPM $II_48$ ($X^2$=0.91, p=.822), and MPM $II_72$ ($X^2$=1.57, p=.457), and results of the discrimination test using the ROC curve were MPM $II_0$, .726 (p<.001), MPM $II_24$, .764 (p<.001), MPM $II_48$, .762 (p<.001), and MPM $II_72$, .809 (p<.001). Conclusion: MPM II was found to be a valid mortality prediction model for neurological ICU patients.

• Korean Journal of Clinical Laboratory Science
• /
• v.53 no.4
• /
• pp.309-316
• /
• 2021

Sepsis is a physiological response to a source of infection that triggers mechanisms that compromise organ function, leading to death if not treated early. Biomarkers with high sensitivity, specificity, speed, and accuracy that could differentiate sepsis from non-infectious systemic inflammatory response syndrome (SIRS) could bring about a revolution in sepsis treatment. Given the limitations and time required for microbial verification of pathogens, the accurate diagnosis of infection before employing antibiotic therapy is important and clinically necessary. Procalcitonin (PCT), lactate, C-reactive protein (CRP), cytokines, and proadrenomedullin (ProADM) are the common biomarkers used for diagnosis. The procalcitonin (PCT)-guided antibiotic treatment in patients with acute respiratory infections effectively reduces antibiotic exposure and side effects while improving survival rates. The evidence regarding sepsis screening in hospitalized patients is limited. Clinicians, researchers, and healthcare decision-makers should consider these findings and limitations when implementing screening tools, future research, or policy on sepsis recognition in hospitalized patients. The use of biomarkers in pediatric sepsis is promising, although such use should always be correlated with clinical evaluation. Biomarkers may also improve the prediction of mortality, especially in the early phase of sepsis, when the levels of certain pro-inflammatory cytokines and proteins are elevated.