• Korean Journal of Radiology
• /
• v.22 no.7
• /
• pp.1213-1224
• /
• 2021

Objective: To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. Materials and Methods: Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. Results: Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. Conclusion: CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.

• Parasites, Hosts and Diseases
• /
• v.39 no.3
• /
• pp.223-226
• /
• 2001

In South Korea, the north border area has been under vivax malaria epidemic since 1993. However, Jeollabuk-do, which is about 300 kms from the border, has not experienced the same epidemic. 1 investigated a total of 58 notified cases of malaria in Jeollabuk-do in the year 2000. All of the cases had an exposure history in the epidemic area. Among them were 49 ex-soldiers, 3 soldiers who served near the border area and 6 civilians who traveled there. The causal agent of all cases was Plasmodium vivax. Except the civilians, the soldiers and ex-soldiers were aged in their twenty's. In the present study, the incubation period was from 6 to 520 days with a median of 157 days, and the latent onset type (92%) was more prevalent than the early onset type. illness onset of most cases (86%) peaked during the summer season (June to September) despite of variable incubation periods. The time lag for diagnosis ranged from 2 to 42 days with a median of 11 days. Jeollabuk-do has not been an area of epidemic untill now, but incidences have been increasing annually since 1996. In Jeollabuk-do, early diagnosis and treatment can be a feasible disease control measure to prevent spreading from the epidemic area.

• Tuberculosis and Respiratory Diseases
• /
• v.83 no.4
• /
• pp.303-311
• /
• 2020

Background: If the duration of mechanical ventilation (MV) is related with the intensive care unit (ICU) readmission must be clarified. The purpose of this study was to elucidate if prolonged MV duration increases ICU readmission rate. Methods: The present observational cohort study analyzed national healthcare claims data from 2006 to 2015. Critically ill patients who received MV in the ICU were classified into five groups according to the MV duration: MV for <7 days, 7-13 days, 14-20 days, 21-27 days, and ≥28 days. The rate and risk of the ICU readmission were estimated according to the MV duration using the unadjusted and adjusted analyses. Results: We found that 12,929 patients had at least one episode of MV in the ICU. There was a significant linear relationship between the MV duration and the ICU readmission (R²=0.85, p=0.025). The total readmission rate was significantly higher as the MV duration is prolonged (MV for <7 days, 13.9%; for 7-13 days, 16.7%; for 14-20 days, 19.4%; for 21-27 days, 20.4%; for ≥28 days, 35.7%; p<0.001). The analyses adjusted by covariables and weighted with the multinomial propensity scores showed similar results. In the adjusted regression analysis with a Cox proportional hazards model, the MV duration was significantly related to the ICU readmission (hazard ratio, 1.058 [95% confidence interval, 1.047-1.069], p<0.001). Conclusion: The rate of readmission to the ICU was significantly higher in patients who received longer durations of the MV in the ICU. In the clinical setting, closer observation of patients discharged from the ICU after prolonged periods of MV is required.

• Journal of Preventive Medicine and Public Health
• /
• v.15 no.1
• /
• pp.47-56
• /
• 1982

Korean versions of British Medical Research Council (MRC), Cornell Medical Index(CMI), and American Thoracic Society 78 (ATS-DLD-78) respiratory questionaires were compared with each other, and were tested the stability, in terms of test-retest reliability, of each questions by self-administration of those to 156 medical students. The results obtained and conclusions drawn are as follow: 1. The degree of agreements between responses to the comparable questions of CMI vs MRC, and of CMI vs ATS-DLD-78 were not satisfactory. There were, however, $71{\sim}100$ per cent of agreement between responses to the questions on Cough, Wheezing, Phlegm, Breathlessness, and Chest illness of ATS-DLD-78 vs MRC questionaire. And the ATS-DLD-78 tended to yield greater number of positive responses than MRC (See Table 4). 2. All of the coefficient of stability of each questions in 3 questionaires were statistically significant, ranged $77{\sim}100$ per cent, except that of the question on episode of cough and phlegm in ATS-DLD-78 questionaire (See Table 5-1). The question is composed of two collateral conditions, 'lasting for 3 weeks or more' and 'each year'. 3. It can be insisted that the Section-B questions of CMI is not proper for use in epidemiologic survey on respiratory illness. And rather than MRC, the ATS-DLD-78 questionaire deserves to prefer to be used in epidemiologic studies on respiratory illness. 4. In question-wording, especially, of inquiring past experience, it is possible to lessen the reliability of the question that including collateral conditions such as 'the duration lasted of symptoms', and moreover, of which words are not common usage. For example, for Korean '10days' or 'half a month' is more familiar time unit rather than 'week'.

• Journal of Preventive Medicine and Public Health
• /
• v.48 no.1
• /
• pp.10-17
• /
• 2015

Objectives: An outbreak of acute febrile illness occurred in the Republic of Korea Air Force boot camp from May to July 2011. An epidemiological investigation of the causative agent, which was of a highly infective nature, was conducted. Methods: Throat swabs were carried out and a multiplex reverse transcriptase-polymerase chain reaction (RT-PCR) assay was performed to identify possible causative factors. Results: The mean age of patients who had febrile illness during the study period was 20.24 years. The multiplex RT-PCR assay identified respiratory syncytial virus (RSV) as the causative agent. The main symptoms were sore throat (76.0%), sputum (72.8%), cough (72.1%), tonsillar hypertrophy (67.9%), and rhinorrhea (55.9%). The mean temperature was $38.75^{\circ}C$ and the attack rate among the recruits was 15.7% (588 out of 3750 recruits), while the mean duration of fever was 2.3 days. The prognosis was generally favorable with supportive care but recurrent fever occurred in 10.1% of the patients within a month. Conclusions: This is the first epidemiological study of an RSV outbreak that developed in a healthy young adult group. In the event of an outbreak of an acute febrile illness of a highly infective nature in facilities used by a young adult group, RSV should be considered among the possible causative agents.

• Pediatric Infection and Vaccine
• /
• v.24 no.1
• /
• pp.31-36
• /
• 2017

Purpose: This study aimed to examine the accuracy of rapid influenza diagnostic tests (RIDT) in children with an influenza-like illness and to evaluate factors associated with greater accuracy. Methods: Pediatric patients, who visited Hallym University Sacred Heart Hospital with an influenza-like illness between June 2011 and May 2016, were enrolled in this study. We tested 798 samples using a real-time polymerase chain reaction (PCR) for respiratory viruses and compared the results with rapid influenza tests. Results: In comparison with the results of the multiplex PCR, the positive agreement rates of RIDT for influenza A and B virus were 75.7% and 60.0%, respectively. The performance of RIDT varied according to days after fever onset. The positive agreement rates of RIDT for influenza A and B tests, performed within 4 days of fever onset, were 77.6% and 73.2%, but the rates for tests performed more than 5 days after fever onset were 66.7% and 21.4%, respectively. Conclusions: The RIDT is a quick and simple aid to diagnosis, but is less sensitive than the labeled sensitivity. Moreover, test performance varied according to days after fever onset. Test specimens for RIDT should be collected as soon as possible after the onset of symptoms (less than 4 days).

• Clinical and Experimental Pediatrics
• /
• v.59 no.7
• /
• pp.308-311
• /
• 2016

We report a human parechovirus-3 (HPeV-3) infection in 2 neonates who had prolonged fever (>5 days) with palmar-plantar erythema. This distinctive rash was observed 4-5 days after fever onset, just before defervescence. Elevated aspartate aminotransferase, lactate dehydrogenase, and ferritin levels were characteristic laboratory findings in the 2 cases, suggesting tissue damage caused by hypercytokinemia. Case 1 was treated with intravenous immunoglobulin, considering the possibility of severe systemic inflammatory responses. The initial ferritin level was 385 ng/mL (range, 0-400 ng/mL); however, the level increased to 2,581 ng/dL on day 5 after fever onset. Case 2 presented with milder clinical symptoms, and the patient recovered spontaneously. HPeV-3 was detected in cerebrospinal fluid and/or blood samples, but no other causative agents were detected. The findings from our cases, in accordance with recent studies, suggest that clinical features such as palmar-plantar erythema and/or hyperferritinemia might be indicators of HPeV-3 infection in neonates with sepsis-like illness. In clinical practice, where virology testing is not easily accessible, clinical features such as palmar-plantar erythema and/or hyperferritinemia might be helpful to diagnose HPeV-3 infection.

• Korean Journal of Biological Psychiatry
• /
• v.2 no.1
• /
• pp.115-122
• /
• 1995

This study was performed to know the relationship between neurologic soft signs (NSS) and clinical variables such as psychopathology. history of illness, and premorbid social adjustment in patients with schizophrenia. The authors evaluated NSS in 31 patients with schizophrenia using the structured tool for measuring neurologic abnormalities, Neurological Evaluation Scale- Korean Version(NES-K). Relationships between NSS and clinical variables such as duration of illness, intensity of precipitating stressors, duration of outpatient treatment, schooling, peer relationship, total duration of unemployment, total days of psychiatric admission, age, total days of being medicated, age at the first psychiatric admission, frequency of admissions, content of treatment, social adjustment, and severity of symptoms were analyzed. Differences between paranoid and non-paranoid schizophrenics were examined. In addition, Differences between patients with schizophrenia who have predominant positive symptoms and who have predominant negative symptoms were examined too. Total scores of NES-K were correlated with lower schooling (${\gamma}$=0.44, p<0.01). Scores of motor coordination subcategory were correlated with poor peer relationship(${\gamma}$=0.67, p<0.001). Other clinical variables were not correlated with any scores of NES-K. Paranoid and non-paranoid schizophrenics were not different in scores of NES-K. Also positive and negative schizophrenics were not different in scores of NES-K. Most clinical variables except schooling and peer relationship were not related with NSS. This results indicated that the meaning of these signs was not fully be understood. Introduction of the new classification concepts such as deficit or non-deficit syndrome will be helpful to elucidate the meaning of NSS in patients with schizophrenia.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.2
• /
• pp.1115-1119
• /
• 2013

Background: Febrile neutropenia (FN) is a serious complication following chemotherapy and is associated with significant mortality and financial expenditure. The aim of this study was to evaluate risk factors for longer length of stay (LOS) and mortality and cost of treatment among hospitalized adults with cancer who developed febrile neutropenia in Thailand. Materials and Methods: Information on illness of inpatients and casualties came from hospitals nationwide and from hospital withdrawals from the 3 health insurance schemes in fiscal 2010. The data covered 96% of the population and were analyzed by age groups, hospital level, and insurance year schemes in patients with febrile neutropenia. Results: A total of 5,809 patients were identified in the study. The mortality rate was 14%. The median LOS was 8.67 days and 69% of patients stayed for longer than 5 days. On bivariate analysis, age, cancer type, and infectious complications (bacteremia/sepsis, hypotension, fungal infections, and pneumonia) were significantly associated with longer LOS and death. On multivariate analysis, acute leukemia and infectious complications were linked with longer LOS and death significantly. The median cost of hospitalized FN was THB 33,686 (USD 1,122) with the highest cost observed in acute leukemia patients. Conclusions: FN in adult patients results in significant mortality in hospitalized Thai patients. Factors associated with increased mortality include older age (>70), acute leukemia, comorbidity, and infectious complications.

• Journal of Preventive Medicine and Public Health
• /
• v.26 no.3 s.43
• /
• pp.321-331
• /
• 1993

This survey was conducted to investigate Farmers' Syndrome and its related factors in Chonnam province. 5,920 (men 6,148, women 6,722) persons in urban area and 12,870 (men 6148, women 6,722) persons in rural area were selected in stratified cluster sampling manner, and interviewed individually with structured questionnaire in April, 1992. The results were summarized as follows : 1 In rural area of Chonnam province, the prevalence of Farmers' syndrome positive was 283 per 1,000 persons (203 in male, 355 in female). In urban area of Chonnam province, control area, the prevalence of Farmers' syndrome positive was 113 (72 in male, 145 in female). The prevalence of Farmers' syndrome positive in rural area was 2.5 times higher than that of urban area, and the prevalence in female was 1.7 times higher than that of male. The prevalence in total respondents was 256. 2. In rural area of Chonnam province, the age standardized prevalence of Farmers' syndrome positive was 209 per 1,000 persons (140 in male, 267 in female). In urban area of Chonnam province, control area, the age standardized prevalence of Farmers' syndrome positive was 122(79 in male, 158 in female). The age standardized prevalence in total respondents was 194. 3. The associated factors with Farmers' syndrome in univariate analysis were having illness during recent 15 days, age, sex, occupation, area, monthly income, education, medical security status, family size and duration of farming. 4. When applying multiple logistic regression for Farmers' syndrome, the significant variables were having illness during recent 15 days, area, sex, age, education, medical security status, family size and duration of farming.