The CoLab-score rapidly and efficiently excludes COVID-19 at the emergency department without need for SARS-CoV-2 testing: a multicenter case-control study
Boer, A.-K.; Deneer, R.; Maas, M.; Ammerlaan, H.; van Balkom, R. H. H.; Leers, M. P.; Martens, R. J. H.; Buijs, M. M.; Kerremans, J. J.; Messchaert, M.; van Suijlen, J. D. E.; van Riel, N. A. W.; Scharnhorst, V.
Show abstract
BackgroundRapid identification of emergency department (ED) patients with a possible COVID-19 infection is needed. PCR-testing all ED patients is neither feasible nor effective in most centers, therefore a rapid, objective, low-cost screening tool to triage ED patients is necessary. MethodsResults from all routine lab tests from ED patients at the Catharina Hospital were collected from July 2019 to July 2020 and used in a statistical model to obtain the CoLab-score. The score was validated temporally and externally in three independent centers. ResultsThe CoLab-score consists of 10 routine lab results and can be used to safely rule-out a COVID-19 infection in more than one third of ED presentations with a negative predictive value of 0.997 (95% CI: 0.994 - 0.999). ConclusionsThe CoLab-score is a valuable tool to rule out COVID-19, guide PCR testing and is available to any center with access to routine laboratory tests.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Clinical prediction rule for SARS-CoV-2 infection from 116 U.S. emergency departments 95%
- Evaluation of a novel, rapid antigen detection test for the diagnosis of SARS-CoV-2 95%
- Derivation and validation of a triage tool for acutely ill adults with suspected COVID-19: The PRIEST observational cohort study 94%
Similar papers in this journal
- Accuracy of the National Early Warning Score version 2 (NEWS2) in predicting need for time-critical treatment: Retrospective observational cohort study 94%
- Emergency medicine patient wait time multivariable prediction models: a multicentre derivation and validation study 92%
- High use of the emergency department shows typical features of complex systems: analysis of multicentre linked data 92%
Similar papers in this journal
- Using explainable machine learning to identify patients at risk of reattendance at discharge from emergency departments 93%
- COMPARISON OF sPLA2-IIA PERFORMANCE WITH HIGH-SENSITIVE CRP, NEUTROPHIL PERCENTAGE, PCT AND LACTATE TO IDENTIFY BACTERIAL INFECTION: A PROSPECTIVE STUDY 93%
- Standard blood laboratory results in SARS-CoV-19 positive patients: do they show a typical pattern? 92%
Similar papers in this journal
- A Data-Driven Framework for Identifying Intensive Care Unit Admissions Colonized with Multidrug-Resistant Organisms 93%
- Evaluation of a clinical decision support system for detection of patients at risk after kidney transplantation 90%
- Bigger and Better? Representativeness of the Influenza A surveillance using one consolidated clinical microbiology laboratory data set as compared to the Belgian Sentinel Network of Laboratories 90%
Similar papers in this journal
- SARS-CoV-2 screening in patients in need of urgent inpatient treatment in the Emergency Department (ED) by digitally integrated point-of-care PCR: A clinical cohort study 95%
- Diagnostic performance of multiplex lateral flow tests in ambulatory patients with acute respiratory illness 90%
- Effect of Antimicrobial Stewardship with Rapid MALDI-TOF Identification and Vitek 2 Antimicrobial Susceptibility Testing on Hospitalization Outcome 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.