Elaboración de modelos predictivos de la gravedad y la mortalidad en pacientes con COVID-19 que acuden al servicio de urgencias, incluida la radiografía torácica

Calvillo-Batllés, Pilar; Cerdá-Alberich, Leonor; Fonfría-Esparcia, C.; Carreres-Ortega, A.; Muñoz-Núñez, C.F.; Trilles-Olaso, L.; Martí‐Bonmatí, Luis

doi:10.1016/j.rx.2021.09.011

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The ability to include CXR results is not widely available in other prediction calculators and has been included in a study 35 along with ten other parameters (symptoms, past medical history and measurables). More recently, some of the studies have included the CXR imaging in prognostic models 45 , 46 , with good accuracy; however, they have either utilised information such as electronic health records 45 including comorbidities 46 , 47 , which are not always known at the point of care, additional blood biomarkers such as D-Dimer 7 , 41 and lactate dehydrogenase 42 , which are not measured routinely during triage, or incorporated complex deep-learning methodologies 46 , affecting the explainability and simplicity of the model. Indeed, in a parallel study, we have developed a highly accurate deep-learning based model (DenResCov-19) to classify from CXR images patients positive for SARS-CoV-2, tuberculosis, and other forms of pneumonia 6 , which will be integrated into the LUCAS calculator in a future study.…”

Section: Discussionmentioning

confidence: 99%

A robust COVID-19 mortality prediction calculator based on Lymphocyte count, Urea, C-Reactive Protein, Age and Sex (LUCAS) with chest X-rays

Ray

Banerjee

Swift

et al. 2022

Sci Rep

View full text Add to dashboard Cite

There have been numerous risk tools developed to enable triaging of SARS-CoV-2 positive patients with diverse levels of complexity. Here we presented a simplified risk-tool based on minimal parameters and chest X-ray (CXR) image data that predicts the survival of adult SARS-CoV-2 positive patients at hospital admission. We analysed the NCCID database of patient blood variables and CXR images from 19 hospitals across the UK using multivariable logistic regression. The initial dataset was non-randomly split between development and internal validation dataset with 1434 and 310 SARS-CoV-2 positive patients, respectively. External validation of the final model was conducted on 741 Accident and Emergency (A&E) admissions with suspected SARS-CoV-2 infection from a separate NHS Trust. The LUCAS mortality score included five strongest predictors (Lymphocyte count, Urea, C-reactive protein, Age, Sex), which are available at any point of care with rapid turnaround of results. Our simple multivariable logistic model showed high discrimination for fatal outcome with the area under the receiving operating characteristics curve (AUC-ROC) in development cohort 0.765 (95% confidence interval (CI): 0.738–0.790), in internal validation cohort 0.744 (CI: 0.673–0.808), and in external validation cohort 0.752 (CI: 0.713–0.787). The discriminatory power of LUCAS increased slightly when including the CXR image data. LUCAS can be used to obtain valid predictions of mortality in patients within 60 days of SARS-CoV-2 RT-PCR results into low, moderate, high, or very high risk of fatality.

show abstract

Section: Discussionmentioning

confidence: 99%

A robust COVID-19 mortality prediction calculator based on Lymphocyte count, Urea, C-Reactive Protein, Age and Sex (LUCAS) with chest X-rays

Ray

Banerjee

Swift

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Calvillo-Batlles (25) desarrolló un modelo predictivo para la admisión a UCI, identi cando la saturación de oxígeno al ingreso como un criterio crucial, con un AUC-ROC de 0,97 y un AUC-PRC de 0,78 en el contexto de COVID-19 . Sin (26)(27)(28)(29)(30) embargo, en nuestro estudio, el ingreso a UCI no fue incluido en el modelo. Al igual que nuestros hallazgos, estos estudios corroboran la importancia de la saturación de oxígeno en el progreso de la enfermedad por COVID-19.…”

Section: Pg 95unclassified

Hiperglicemia al ingreso hospitalario como predictor de mala evolución en pacientes hospitalizados por COVID-19

Cuba Ticona,

Indacochea Cáceda

2024

RFMH

View full text Add to dashboard Cite

Introducción: La hiperglicemia al ingreso hospitalario podría ser una buena herramienta para predecir evolución desfavorable en pacientes con COVID-19. Objetivo: Determinar si la hiperglicemia al ingreso hospitalario constituye un factor pronóstico de evolución desfavorable. Métodos: Se realizó un estudio observacional, analítico, de cohorte retrospectivo en el Hospital Regional de Moquegua. Se revisaron de manera aleatoria historias clínicas de 640 pacientes hospitalizados con COVID-19 confirmado durante las primeras dos olas de la pandemia. Las variables incluyeron evolución desfavorable, secuelas respiratorias, ingreso a la Unidad de Cuidados Intensivos (UCI), y fallecimiento. La hiperglicemia al ingreso se definió como glicemia >140 mg/dL. Se realizaron análisis bivariados y multivariados utilizando modelos de regresión de Poisson con varianzas robustas para hallar el riesgo relativo crudo y ajustado (RRa) con sus respectivos IC95%. Resultados: El 36,9% tuvo 60 o más años, el 58,9% fue del sexo masculino y el 10,2% tuvo diabetes mellitus. El 34,7% de los pacientes presentaron hiperglicemia al ingreso. La hiperglicemia se asoció significativamente con una evolución desfavorable (RRa = 5,65; IC95%: 3,72-8,62; p < 0,001), secuelas respiratorias (RRa = 1,96; IC95%: 1,74-2,21; p < 0,001), ingreso a UCI (RRa = 3,68; IC95%: 2,03-6,69; p < 0,001), y fallecimiento (RRa = 1,57; IC95%: 1,22-2,02; p = 0,001). Conclusión: La hiperglicemia al ingreso es un factor pronóstico significativo para evolución desfavorable en pacientes con COVID-19. Es esencial monitorear cuidadosamente a estos pacientes.

show abstract

Eficacia de la capacidad y la eficiencia pronósticas de la herramienta de inteligencia artificial Thoracic Care Suite de GE aplicada a la radiografía torácica de pacientes con neumonía COVID-19

et al. 2023

View full text Add to dashboard Cite

Elaboración de modelos predictivos de la gravedad y la mortalidad en pacientes con COVID-19 que acuden al servicio de urgencias, incluida la radiografía torácica

Cited by 5 publications

References 34 publications

A robust COVID-19 mortality prediction calculator based on Lymphocyte count, Urea, C-Reactive Protein, Age and Sex (LUCAS) with chest X-rays

A robust COVID-19 mortality prediction calculator based on Lymphocyte count, Urea, C-Reactive Protein, Age and Sex (LUCAS) with chest X-rays

Hiperglicemia al ingreso hospitalario como predictor de mala evolución en pacientes hospitalizados por COVID-19

Eficacia de la capacidad y la eficiencia pronósticas de la herramienta de inteligencia artificial Thoracic Care Suite de GE aplicada a la radiografía torácica de pacientes con neumonía COVID-19

Contact Info

Product

Resources

About