Development and validation of a prognostic model for early triage of patients diagnosed with COVID-19.

We developed a tool to guide decision-making for early triage of COVID-19 patients based on a predicted prognosis, using a Korean national cohort of 5,596 patients, and validated the developed tool with an external cohort of 445 patients treated in a single institution. Predictors chosen for our model were older age, male sex, subjective fever, dyspnea, altered consciousness, temperature ≥ 37.5 °C, heart rate ≥ 100 bpm, systolic blood pressure ≥ 160 mmHg, diabetes mellitus, heart disease, chronic kidney disease, cancer, dementia, anemia, leukocytosis, lymphocytopenia, and thrombocytopenia. In the external validation, when age, sex, symptoms, and underlying disease were used as predictors, the AUC used as an evaluation metric for our model's performance was 0.850 in predicting whether a patient will require at least oxygen therapy and 0.833 in predicting whether a patient will need critical care or die from COVID-19. The AUCs improved to 0.871 and 0.864, respectively, when additional information on vital signs and blood test results were also used. In contrast, the protocols currently recommended in Korea showed AUCs less than 0.75. An application for calculating the prognostic score in COVID-19 patients based on the results of this study is presented on our website ( https://nhimc.shinyapps.io/ih-psc/ ), where the results of the validation ongoing in our institution are periodically updated.

Association between Body Mass Index and Risk of Coronavirus Disease 2019 (COVID-19): A Nationwide Case-control Study in South Korea.

BACKGROUND: Increased body mass index (BMI) has been associated with a higher risk of severe coronavirus disease 2019 (COVID-19) infections. However, whether obesity is a risk factor for contracting COVID-19 has hardly been investigated so far. METHODS: We examined the association between BMI level and the risk of COVID-19 infection in a nationwide case-control study comprised of 3788 case patients confirmed to have COVID-19 between 24 January and 9 April 2020 and 15 152 controls matched by age and sex, who were aged 20 years or more and underwent National Health Insurance Service (NHIS) health examinations between 2015-2017, using data from the Korean NHIS with linkage to the Korea Centers for Disease Control and Prevention data. Our primary exposure of interest was BMI level, categorized into 4 groups: <18.5 (underweight), 18.5-22.9 (normal weight), 23-24.9 (overweight), and ≥25 kg/m2 (obese). RESULTS: Of the entire 18 940 study participants, 11 755 (62.1%) were women, and the mean age of the study participants was 53.7 years (standard deviation, 13.8). In multivariable logistic regression models adjusted for sociodemographic, comorbidity, laboratory, and medication data, there was a graded association between higher BMI levels and higher risk of COVID-19 infection. Compared to normal-weight individuals, the adjusted odds ratios in the overweight and obese individuals were 1.13 (95% confidence interval [CI], 1.03-1.25) and 1.26 (95% CI, 1.15-1.39), respectively. This association was robust across age and sex subgroups. CONCLUSIONS: Higher BMI levels were associated with a higher risk of contracting COVID-19.

Does Diabetes Increase the Risk of Contracting COVID-19? A Population-Based Study in Korea.

BACKGROUND: This study aimed to determine the infection risk of coronavirus disease 2019 (COVID-19) in patients with diabetes (according to treatment method). METHODS: Claimed subjects to the Korean National Health Insurance claims database diagnosed with COVID-19 were included. Ten thousand sixty-nine patients with COVID-19 between January 28 and April 5, 2020, were included. Stratified random sampling of 1:5 was used to select the control group of COVID-19 patients. In total 50,587 subjects were selected as the control group. After deleting the missing values, 60,656 subjects were included. RESULTS: Adjusted odds ratio (OR) indicated that diabetic insulin users had a higher risk of COVID-19 than subjects without diabetes (OR, 1.25; 95% confidence interval [CI], 1.03 to 1.53; P=0.0278). In the subgroup analysis, infection risk was higher among diabetes male insulin users (OR, 1.42; 95% CI, 1.07 to 1.89), those between 40 and 59 years (OR, 1.66; 95% CI, 1.13 to 2.44). The infection risk was higher in diabetic insulin users with 2 to 4 years of morbidity (OR, 1.744; 95% CI, 1.003 to 3.044). CONCLUSION: Some diabetic patients with certain conditions would be associated with a higher risk of acquiring COVID-19, highlighting their need for special attention. Efforts are warranted to ensure that diabetic patients have minimal exposure to the virus. It is important to establish proactive care and screening tests for diabetic patients suspected with COVID-19 for timely disease diagnosis and management.

Machine learning prediction for mortality of patients diagnosed with COVID-19: a nationwide Korean cohort study.

The rapid spread of COVID-19 has resulted in the shortage of medical resources, which necessitates accurate prognosis prediction to triage patients effectively. This study used the nationwide cohort of South Korea to develop a machine learning model to predict prognosis based on sociodemographic and medical information. Of 10,237 COVID-19 patients, 228 (2.2%) died, 7772 (75.9%) recovered, and 2237 (21.9%) were still in isolation or being treated at the last follow-up (April 16, 2020). The Cox proportional hazards regression analysis revealed that age > 70, male sex, moderate or severe disability, the presence of symptoms, nursing home residence, and comorbidities of diabetes mellitus (DM), chronic lung disease, or asthma were significantly associated with increased risk of mortality (p ≤ 0.047). For machine learning, the least absolute shrinkage and selection operator (LASSO), linear support vector machine (SVM), SVM with radial basis function kernel, random forest (RF), and k-nearest neighbors were tested. In prediction of mortality, LASSO and linear SVM demonstrated high sensitivities (90.7% [95% confidence interval: 83.3, 97.3] and 92.0% [85.9, 98.1], respectively) and specificities (91.4% [90.3, 92.5] and 91.8%, [90.7, 92.9], respectively) while maintaining high specificities > 90%, as well as high area under the receiver operating characteristics curves (0.963 [0.946, 0.979] and 0.962 [0.945, 0.979], respectively). The most significant predictors for LASSO included old age and preexisting DM or cancer; for RF they were old age, infection route (cluster infection or infection from personal contact), and underlying hypertension. The proposed prediction model may be helpful for the quick triage of patients without having to wait for the results of additional tests such as laboratory or radiologic studies, during a pandemic when limited medical resources must be wisely allocated without hesitation.