Background: A coronavirus disease 2019 (COVID-19) outbreak started in February 2020 and was controlled at the end of March 2020 in Daegu, the epicenter of the coronavirus outbreak in Korea. The aim of this study was to describe the clinical course and outcomes of patients with COVID-19 in Daegu. Methods: In collaboration with Daegu Metropolitan City and Korean Center for Diseases Control, we conducted a retrospective, multicenter cohort study. Demographic, clinical, treatment, and laboratory data, including viral RNA detection, were obtained from the electronic medical records and cohort database and compared between survivors and non-survivors. We used univariate and multi-variable logistic regression methods and Cox regression model and performed Kaplan-Meier analysis to determine the risk factors associated with the 28-day mortality and release from isolation among the patients. Results: In this study, 7,057 laboratory-confirmed patients with COVID-19 (total cohort) who had been diagnosed from February 18 to July 10, 2020 were included. Of the total cohort, 5,467 were asymptomatic to mild patients (77.4%) (asymptomatic 30.6% and mild 46.8%), 985 moderate (14.0%), 380 severe (5.4%), and 225 critical (3.2%). The mortality of the patients was 2.5% (179/7,057). The Cox regression hazard model for the patients with available clinical information (core cohort) (n = 2,254) showed the risk factors for 28-day mortality: age > 70 (hazard ratio [HR], 4.219, P = 0.002), need for O 2 supply at admission (HR, 2.995; P = 0.001), fever (> 37.5°C) (HR, 2.808; P = 0.001), diabetes (HR, 2.119; P = 0.008), cancer (HR, 3.043; P = 0.011), dementia (HR, 5.252; P = 0.008), neurological disease (HR, 2.084; P = 0.039), heart failure (HR, 3.234; P = 0.012), and hypertension (HR, 2.160; P = 0.017). The median duration for release from isolation was 33 days (interquartile range, 24.0-46.0) in survivors. The Cox proportional hazard model for the long duration of isolation included severity, age > 70, and dementia. Conclusion: Overall, asymptomatic to mild patients were approximately 77% of the total cohort (asymptomatic, 30.6%). The case fatality rate was 2.5%. Risk factors, including older age, need for O 2 supply, dementia, and neurological disorder at admission, could help clinicians to identify COVID-19 patients with poor prognosis at an early stage.

Purpose Discovery of models predicting the exact prognosis of epithelial ovarian cancer (EOC) is necessary as the first step of implementation of individualized treatment. This study aimed to develop nomograms predicting treatment response and prognosis in EOC. Materials and Methods We comprehensively reviewed medical records of 866 patients diagnosed with and treated for EOC at two tertiary institutional hospitals between 2007 and 2016. Patients’ clinico-pathologic characteristics, details of primary treatment, intra-operative surgical findings, and survival outcomes were collected. To construct predictive nomograms for platinum sensitivity, 3-year progression-free survival (PFS), and 5-year overall survival (OS), we performed stepwise variable selection by measuring the area under the receiver operating characteristic curve (AUC) with leave-one-out cross-validation. For model validation, 10-fold cross-validation was applied. Results The median length of observation was 42.4 months (interquartile range, 25.7 to 69.9 months), during which 441 patients (50.9%) experienced disease recurrence. The median value of PFS was 32.6 months and 3-year PFS rate was 47.8% while 5-year OS rate was 68.4%. The AUCs of the newly developed nomograms predicting platinum sensitivity, 3-year PFS, and 5-year OS were 0.758, 0.841, and 0.805, respectively. We also developed predictive nomograms confined to the patients who underwent primary debulking surgery. The AUCs for platinum sensitivity, 3-year PFS, and 5-year OS were 0.713, 0.839, and 0.803, respectively. Conclusion We successfully developed nomograms predicting treatment response and prognosis of patients with EOC. These nomograms are expected to be useful in clinical practice and designing clinical trials.

Background Limited information is available about the present characteristics and dynamic clinical changes that occur in patients with COVID-19 during the early phase of the illness. Objective This study aimed to develop and validate machine learning models based on clinical features to assess the risk of severe disease and triage for COVID-19 patients upon hospital admission. Methods This retrospective multicenter cohort study included patients with COVID-19 who were released from quarantine until April 30, 2020, in Korea. A total of 5628 patients were included in the training and testing cohorts to train and validate the models that predict clinical severity and the duration of hospitalization, and the clinical severity score was defined at four levels: mild, moderate, severe, and critical. Results Out of a total of 5601 patients, 4455 (79.5%), 330 (5.9%), 512 (9.1%), and 301 (5.4%) were included in the mild, moderate, severe, and critical levels, respectively. As risk factors for predicting critical patients, we selected older age, shortness of breath, a high white blood cell count, low hemoglobin levels, a low lymphocyte count, and a low platelet count. We developed 3 prediction models to classify clinical severity levels. For example, the prediction model with 6 variables yielded a predictive power of >0.93 for the area under the receiver operating characteristic curve. We developed a web-based nomogram, using these models. Conclusions Our prediction models, along with the web-based nomogram, are expected to be useful for the assessment of the onset of severe and critical illness among patients with COVID-19 and triage patients upon hospital admission.

To support the implementation of individualized disease management, we aimed to develop machine learning models predicting platinum sensitivity in patients with high-grade serous ovarian carcinoma (HGSOC). We reviewed the medical records of 1002 eligible patients. Patients’ clinicopathologic characteristics, surgical findings, details of chemotherapy, treatment response, and survival outcomes were collected. Using the stepwise selection method, based on the area under the receiver operating characteristic curve (AUC) values, six variables associated with platinum sensitivity were selected: age, initial serum CA-125 levels, neoadjuvant chemotherapy, pelvic lymph node status, involvement of pelvic tissue other than the uterus and tubes, and involvement of the small bowel and mesentery. Based on these variables, predictive models were constructed using four machine learning algorithms, logistic regression (LR), random forest, support vector machine, and deep neural network; the model performance was evaluated with the five-fold cross-validation method. The LR-based model performed best at identifying platinum-resistant cases with an AUC of 0.741. Adding the FIGO stage and residual tumor size after debulking surgery did not improve model performance. Based on the six-variable LR model, we also developed a web-based nomogram. The presented models may be useful in clinical practice and research.

Objective The need to perform genetic sequencing to diagnose the polymerase epsilon exonuclease ( POLE ) subtype of endometrial cancer (EC) hinders the adoption of molecular classification. We investigated clinicopathologic and protein markers that distinguish the POLE from the copy number (CN)-low subtype in EC. Methods Ninety-one samples (15 POLE , 76 CN-low) were selected from The Cancer Genome Atlas EC dataset. Clinicopathologic and normalized reverse phase protein array expression data were analyzed for associations with the subtypes. A logistic model including selected markers was constructed by stepwise selection using area under the curve (AUC) from 5-fold cross-validation (CV). The selected markers were validated using immunohistochemistry (IHC) in a separate cohort. Results Body mass index (BMI) and tumor grade were significantly associated with the POLE subtype. With BMI and tumor grade as covariates, 5 proteins were associated with the EC subtypes. The stepwise selection method identified BMI, cyclin B1, caspase 8, and X-box binding protein 1 (XBP1) as markers distinguishing the POLE from the CN-low subtype. The mean of CV AUC, sensitivity, specificity, and balanced accuracy of the selected model were 0.97, 0.91, 0.87, and 0.89, respectively. IHC validation showed that cyclin B1 expression was significantly higher in the POLE than in the CN-low subtype and receiver operating characteristic curve of cyclin B1 expression in IHC revealed AUC of 0.683. Conclusion BMI and expression of cyclin B1, caspase 8, and XBP1 are candidate markers distinguishing the POLE from the CN-low subtype. Cyclin B1 IHC may replace POLE sequencing in molecular classification of EC.