Dataset Information

Individualizing Risk Prediction for Positive Coronavirus Disease 2019 Testing: Results From 11,672 Patients.

ABSTRACT: BACKGROUND:Coronavirus disease 2019 (COVID-19) is sweeping the globe. Despite multiple case-series, actionable knowledge to tailor decision-making proactively is missing. RESEARCH QUESTION:Can a statistical model accurately predict infection with COVID-19? STUDY DESIGN AND METHODS:We developed a prospective registry of all patients tested for COVID-19 in Cleveland Clinic to create individualized risk prediction models. We focus here on the likelihood of a positive nasal or oropharyngeal COVID-19 test. A least absolute shrinkage and selection operator logistic regression algorithm was constructed that removed variables that were not contributing to the model's cross-validated concordance index. After external validation in a temporally and geographically distinct cohort, the statistical prediction model was illustrated as a nomogram and deployed in an online risk calculator. RESULTS:In the development cohort, 11,672 patients fulfilled study criteria, including 818 patients (7.0%) who tested positive for COVID-19; in the validation cohort, 2295 patients fulfilled criteria, including 290 patients who tested positive for COVID-19. Male, African American, older patients, and those with known COVID-19 exposure were at higher risk of being positive for COVID-19. Risk was reduced in those who had pneumococcal polysaccharide or influenza vaccine or who were on melatonin, paroxetine, or carvedilol. Our model had favorable discrimination (c-statistic = 0.863 in the development cohort and 0.840 in the validation cohort) and calibration. We present sensitivity, specificity, negative predictive value, and positive predictive value at different prediction cutoff points. The calculator is freely available at https://riskcalc.org/COVID19. INTERPRETATION:Prediction of a COVID-19 positive test is possible and could help direct health-care resources. We demonstrate relevance of age, race, sex, and socioeconomic characteristics in COVID-19 susceptibility and suggest a potential modifying role of certain common vaccinations and drugs that have been identified in drug-repurposing studies.

SUBMITTER: Jehi L

PROVIDER: S-EPMC7286244 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Individualizing Risk Prediction for Positive Coronavirus Disease 2019 Testing: Results From 11,672 Patients.

Jehi Lara L Ji Xinge X Milinovich Alex A Erzurum Serpil S Rubin Brian P BP Gordon Steve S Young James B JB Kattan Michael W MW

Chest 20200610 4

<h4>Background</h4>Coronavirus disease 2019 (COVID-19) is sweeping the globe. Despite multiple case-series, actionable knowledge to tailor decision-making proactively is missing.<h4>Research question</h4>Can a statistical model accurately predict infection with COVID-19?<h4>Study design and methods</h4>We developed a prospective registry of all patients tested for COVID-19 in Cleveland Clinic to create individualized risk prediction models. We focus here on the likelihood of a positive nasal or ...[more]

PMID: 32533957

Similar Datasets

Project description:ImportanceAdministration of hydroxychloroquine with or without azithromycin for the treatment of coronavirus disease 2019 (COVID-19)-associated pneumonia carries increased risk of corrected QT (QTc) prolongation and cardiac arrhythmias.ObjectiveTo characterize the risk and degree of QT prolongation in patients with COVID-19 in association with their use of hydroxychloroquine with or without concomitant azithromycin.Design, setting, and participantsThis was a cohort study performed at an academic tertiary care center in Boston, Massachusetts, of patients hospitalized with at least 1 positive COVID-19 nasopharyngeal polymerase chain reaction test result and clinical findings consistent with pneumonia who received at least 1 day of hydroxychloroquine from March 1, 2020, through April 7, 2020.Main outcomes and measuresChange in QT interval after receiving hydroxychloroquine with or without azithromycin; occurrence of other potential adverse drug events.ResultsAmong 90 patients given hydroxychloroquine, 53 received concomitant azithromycin; 44 (48.9%) were female, and the mean (SD) body mass index was 31.5 (6.6). Hypertension (in 48 patients [53.3%]) and diabetes mellitus (in 26 patients [28.9%]) were the most common comorbid conditions. The overall median (interquartile range) baseline QTc was 455 (430-474) milliseconds (hydroxychloroquine, 473 [454-487] milliseconds vs hydroxychloroquine and azithromycin, 442 [427-461] milliseconds; P?<?.001). Those receiving concomitant azithromycin had a greater median (interquartile range) change in QT interval (23 [10-40] milliseconds) compared with those receiving hydroxychloroquine alone (5.5 [-15.5 to 34.25] milliseconds; P?=?.03). Seven patients (19%) who received hydroxychloroquine monotherapy developed prolonged QTc of 500 milliseconds or more, and 3 patients (8%) had a change in QTc of 60 milliseconds or more. Of those who received concomitant azithromycin, 11 of 53 (21%) had prolonged QTc of 500 milliseconds or more and 7 of 53 (13 %) had a change in QTc of 60 milliseconds or more. The likelihood of prolonged QTc was greater in those who received concomitant loop diuretics (adjusted odds ratio, 3.38 [95% CI, 1.03-11.08]) or had a baseline QTc of 450 milliseconds or more (adjusted odds ratio, 7.11 [95% CI, 1.75-28.87]). Ten patients had hydroxychloroquine discontinued early because of potential adverse drug events, including intractable nausea, hypoglycemia, and 1 case of torsades de pointes.Conclusions and relevanceIn this cohort study, patients who received hydroxychloroquine for the treatment of pneumonia associated with COVID-19 were at high risk of QTc prolongation, and concurrent treatment with azithromycin was associated with greater changes in QTc. Clinicians should carefully weigh risks and benefits if considering hydroxychloroquine and azithromycin, with close monitoring of QTc and concomitant medication usage.

Project description:BackgroundAvailable data suggest that the obstetric population is particularly vulnerable to severe respiratory syndrome coronavirus 2 infection, with a variable clinical course leading to severe respiratory failure. However, established early warning scores designed to identify patients at risk of clinical deterioration were never validated in the obstetric population.ObjectiveThis retrospective cohort study sought to evaluate the initial clinical characteristics of pregnant patients diagnosed with severe acute respiratory syndrome coronavirus 2 infection and to develop a pregnancy-specific early warning score to identify patients at risk for clinical deterioration and requiring advanced respiratory support.Study designThis was a single center, retrospective cohort study of pregnant patients diagnosed with severe acute respiratory syndrome coronavirus 2 infection between April 2020 and December 2020. A total of 50 patients with severe acute respiratory syndrome coronavirus 2 infection between April 2020 and November 2020 were used to create the prediction model. Initial clinical characteristics identified at the time of diagnosis were compared between patients who required advanced respiratory support and those who were asymptomatic or had mild symptoms for those diagnosed during the period of April 2020 to November 2020. Risk factors associated with a requirement for advanced respiratory support were used to create the Obstetric Warning Score system. The Obstetric Warning Score system was then validated using 30 patients diagnosed with severe acute respiratory syndrome coronavirus 2 infection in December 2020. A receiver operating characteristic curve was generated to evaluate the test characteristics of the Obstetric Warning Score system compared with other scoring systems including the Early Warning Score, the National Early Warning Score 2, and the Maternal Early Warning Criteria.ResultsWomen who required advanced respiratory support were more likely to present with dyspnea (100% vs 33.3%; P<.001), have a higher heart rate (113.4 beats per minute vs 93 beats per minute; P<.001), respiratory rate (23.5 breaths per minute vs 17.7 breaths per minute; P<.001), temperature (99.1°F vs 98.3°F; P=.004), and C-reactive protein level (7.4 mg/dL vs 2.4 mg/dL; P<.001). Furthermore, 88.2% of patients requiring advanced respiratory support showed chest x-ray findings consistent with pneumonia, compared with 20.0% of the patients not requiring advanced respiratory support (P<.001). All patients requiring advanced respiratory support presented with at least 1 coronavirus disease 2019 symptom, whereas only 51.5% of patients not requiring advanced respiratory support were symptomatic (P<.001). The Obstetrical Warning Score model allocated 1 point each for a hazard ratio of >100 beats per minute, temperature of >99.0°F, C-reactive protein level of >2.0 mg/dL, respiratory rate between 20 and 24 breaths per minute, complaints of dyspnea, and a positive chest x-ray. A respiratory rate of >24 breaths per minute was assigned 2 points. The area under the curve for the Obstetric Warning Score system was 0.97 compared with 0.72 for the Early Warning Score system, 0.92 for the National Early Warning Score 2 system, and 0.85 for the Maternal Early Warning Criteria system. An Obstetric Warning Score of ≥3 was predictive of a requirement for advanced respiratory support with a sensitivity of 100%, specificity 64%, and a positive predictive value of 36%.ConclusionThe Obstetric Warning Score system presents a validated method for providers to identify pregnant patients who are at risk for respiratory failure and a requirement for advanced respiratory support.

Project description:ObjectivesCritically ill patients with coronavirus disease 2019 have variable mortality. Risk scores could improve care and be used for prognostic enrichment in trials. We aimed to compare machine learning algorithms and develop a simple tool for predicting 28-day mortality in ICU patients with coronavirus disease 2019.DesignThis was an observational study of adult patients with coronavirus disease 2019. The primary outcome was 28-day inhospital mortality. Machine learning models and a simple tool were derived using variables from the first 48 hours of ICU admission and validated externally in independent sites and temporally with more recent admissions. Models were compared with a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 using the area under the receiver operating characteristic curve and calibration.SettingSixty-eight U.S. ICUs.PatientsAdults with coronavirus disease 2019 admitted to 68 ICUs in the United States between March 4, 2020, and June 29, 2020.InterventionsNone.Measurements and main resultsThe study included 5,075 patients, 1,846 (36.4%) of whom died by day 28. eXtreme Gradient Boosting had the highest area under the receiver operating characteristic curve in external validation (0.81) and was well-calibrated, while k-nearest neighbors were the lowest performing machine learning algorithm (area under the receiver operating characteristic curve 0.69). Findings were similar with temporal validation. The simple tool, which was created using the most important features from the eXtreme Gradient Boosting model, had a significantly higher area under the receiver operating characteristic curve in external validation (0.78) than the Sequential Organ Failure Assessment score (0.69), National Early Warning Score (0.60), and CURB-65 (0.65; p < 0.05 for all comparisons). Age, number of ICU beds, creatinine, lactate, arterial pH, and Pao2/Fio2 ratio were the most important predictors in the eXtreme Gradient Boosting model.ConclusionseXtreme Gradient Boosting had the highest discrimination overall, and our simple tool had higher discrimination than a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 on external validation. These models could be used to improve triage decisions and clinical trial enrichment.

Dataset Information

Individualizing Risk Prediction for Positive Coronavirus Disease 2019 Testing: Results From 11,672 Patients.

Publications

Individualizing Risk Prediction for Positive Coronavirus Disease 2019 Testing: Results From 11,672 Patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets