Utility of a Clinical Scoring System for Point of Care Triaging in COVID-19 Pneumonia
Gangemi, A. J.; Gupta, R.; Fernandez-Romero, G.; Zhao, H.; Patel, M.; Chowdhury, J.; Zantah, M.; Zheng, M.; Abramian, O.; Codella, S.; Vien, L.; Dominguez-Castillo, E.; Buckey, T.; Earley, C.; Frankovich, J.; Jurkowski, M.; Jurkowski, Z.; O'Brien, J.; Guo, N.; Stanley, P.; Halsey, B.; Kahlon, J.; Kaur, N.; Prosniak, R.; Kumaran, M.; Dass, C.; Fleece, D.; Jacobs, M. R.; Criner, G. J.; Temple University COVID-19 Research Group,
Show abstract
BackgroundSurges in COVID-19 disease cases can rapidly overwhelm healthcare resources; triaging to appropriate levels of care can assist in resource planning. At the beginning of the pandemic, we developed a simple triage tool, the Temple COVID-19 Pneumonia Triage Tool (TemCOV) based on a combination of clinical and radiographic features that are readily available on presentation to categorize and predict illness severity. MethodsWe prospectively examined 579 sequential cases admitted to Temple University Hospital who were assigned severity categories on admission. Our primary outcome was to compare the performance of TemCOV in predicting patients who have the highest likely of admission to the ICU at 24 and at 72 hours to other standard triage tools: the National Early Warning System (NEWS), the Modified Early Warning System (MEWS) and the CURB65 score. Additional endpoints included need for invasive mechanical ventilation (IMV) within 72 hours, total hospital admission charges, and mortality. Results26% of patients fell within our highest risk Category 4 and were more likely to require ICU admission at 24 hours (OR 11.51) and 72 hours (OR 8.6). Additionally they had the highest likelihood of needing IMV (OR 29.47) and in-hospital mortality (OR 2.37)., TemCOV performed similar to MEWS in predicting ICU admission at 24 hours (receive operator characteristic (ROC) curve area under the curve (AUC) 0.77 vs. 0.74, p=0.21) but better than NEWS2 and CURB65 (ROC AUC 0.77 vs. 0.69 and 0.77 vs. 0.64, respectively, p<0.01). While all severity scores had a weak correlation to hospital charges, the TemCOV performed the best among all severity scores measured (r=0.18); median hospital charges for Category 4 patients was $170,468 ($96,972-$487,556). ConclusionTemCOV is a simple triage score that can be used upon hospitalization in patients with COVID-19 that predicts the need for hospital resources such as ICU bed capacity, invasive mechanical ventilation and personnel staffing.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Development and validation of a predictive model for critical illness in adult patients requiring hospitalization for COVID-19 96%
- Derivation and validation of a triage tool for acutely ill adults with suspected COVID-19: The PRIEST observational cohort study 95%
- Predicting patients with false negative SARS-CoV-2 testing at hospital admission: A retrospective multi-center study 95%
Similar papers in this journal
- Cardiovascular disease and severe hypoxemia associated with higher rates of non-invasive respiratory support failure in COVID-19 94%
- A Multicenter Evaluation of Blood Purification with Seraph 100 Microbind Affinity Blood Filter for the Treatment of Severe COVID-19: A Preliminary Report 94%
- ABCDEF Bundle Implementation: The influence of access to bundle-enhancing supplies and equipment 92%
Similar papers in this journal
- Exploring Associations with Severe Hypoxemic Respiratory Failure in COVID-19 Patients upon Admission: A Model for Severe Hypoxemic Respiratory Failure in 329 Unvaccinated, Hospitalized COVID-19 Patients 96%
- Use of the FebriDx point-of-care assay as part of a triage algorithm for medical admissions with possible COVID-19 95%
- Use of the first National Early Warning Score recorded within 24 hours of admission to estimate the risk of in-hospital mortality in unplanned COVID-19 patients: a retrospective cohort study 94%
Similar papers in this journal
- Characteristics and outcomes of clinically diagnosed RT-PCR swab negative COVID-19: a retrospective cohort study 94%
- Imputation of PaO2 from SpO2 values from the MIMIC-III Critical Care Database Using Machine-Learning Based Algorithms 94%
- The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission 93%
Similar papers in this journal
"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.