Development of severity and mortality prediction models for covid-19 patients at emergency department including the chest x-ray.

OBJECTIVES: To develop prognosis prediction models for COVID-19 patients attending an emergency department (ED) based on initial chest X-ray (CXR), demographics, clinical and laboratory parameters. METHODS: All symptomatic confirmed COVID-19 patients admitted to our hospital ED between February 24th and April 24th 2020 were recruited. CXR features, clinical and laboratory variables and CXR abnormality indices extracted by a convolutional neural network (CNN) diagnostic tool were considered potential predictors on this first visit. The most serious individual outcome defined the three severity level: 0) home discharge or hospitalization ≤ 3 days, 1) hospital stay >3 days and 2) intensive care requirement or death. Severity and in-hospital mortality multivariable prediction models were developed and internally validated. The Youden index was used for the optimal threshold selection of the classification model. RESULTS: A total of 440 patients were enrolled (median 64 years; 55.9% male); 13.6% patients were discharged, 64% hospitalized, 6.6% required intensive care and 15.7% died. The severity prediction model included oxygen saturation/inspired oxygen fraction (SatO2/FiO2), age, C-reactive protein (CRP), lymphocyte count, extent score of lung involvement on CXR (ExtScoreCXR), lactate dehydrogenase (LDH), D-dimer level and platelets count, with AUC-ROC = 0.94 and AUC-PRC = 0.88. The mortality prediction model included age, SatO2/FiO2, CRP, LDH, CXR extent score, lymphocyte count and D-dimer level, with AUC-ROC = 0.97 and AUC-PRC = 0.78. The addition of CXR CNN-based indices did not improve significantly the predictive metrics. CONCLUSION: The developed and internally validated severity and mortality prediction models could be useful as triage tools in ED for patients with COVID-19 or other virus infections with similar behaviour.

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 / Development of severity and mortality prediction models for covid-19 patients at emergency department including the chest x-ray

Objetivos: Desarrollar modelos de predicción de pronóstico para pacientes con COVID-19 que acuden a urgencias, basados en la radiografía de tórax inicial (RXT), parámetros demográficos, clínicos y de laboratorio. Métodos: Se reclutaron todos los pacientes sintomáticos con COVID-19 confirmada, que ingresaron en urgencias de nuestro hospital entre el 24 de febrero y el 24 de abril de 2020. Los parámetros de la RXT, las variables clínicas y de laboratorio y los índices de hallazgos en RXT extraídos por una herramienta diagnóstica de inteligencia artificial en esta primera visita se consideraron potenciales predictores. El desenlace individual más grave definió los tres niveles de gravedad: 0) alta domiciliaria u hospitalización de 3 días o inferior, 1) hospitalización más de 3 días y 2) necesidad de cuidados intensivos o muerte. Se desarrollaron y validaron internamente modelos de predicción multivariable de gravedad y mortalidad hospitalaria. El índice de Youden se utilizó para la selección del umbral óptimo del modelo de clasificación. Resultados: Se registraron 440 pacientes (mediana de 64 años; 55,9% hombres); el 13,6% de los pacientes fueron dados de alta, el 64% estuvo hospitalizado más de 3 días, el 6,6% requirió cuidados intensivos y un 15,7% falleció. El modelo de predicción de gravedad incluyó saturación de oxígeno/fracción de oxígeno inspirado (SatO2/FiO2), edad, proteína C reactiva (PCR), linfocitos, puntuación de la extensión de la afectación pulmonar en la RXT (ExtScoreRXT), lactato deshidrogenasa (LDH), dímero D y plaquetas, con AUC-ROC=0,94 y AUC-PRC=0,88. El modelo de predicción de mortalidad incluyó edad, SatO2/FiO2, PCR, LDH, ExtScoreRXT, linfocitos y dímero D, con AUC-ROC=0,97 y AUC-PRC=0,78. La adición de índices radiológicos obtenidos por inteligencia artificial no mejoró significativamente las métricas predictivas.(AU)

Objectives: To develop prognosis prediction models for COVID-19 patients attending an emergency department (ED) based on initial chest X-ray (CXR), demographics, clinical and laboratory parameters. Methods: All symptomatic confirmed COVID-19 patients admitted to our hospital ED between February 24th and April 24th 2020 were recruited. CXR features, clinical and laboratory variables and CXR abnormality indices extracted by a convolutional neural network (CNN) diagnostic tool were considered potential predictors on this first visit. The most serious individual outcome defined the three severity level: 0) home discharge or hospitalization ≤ 3 days, 1) hospital stay>3 days and 2) intensive care requirement or death. Severity and in-hospital mortality multivariable prediction models were developed and internally validated. The Youden index was used for the optimal threshold selection of the classification model. Results: A total of 440 patients were enrolled (median 64 years; 55.9% male); 13.6% patients were discharged, 64% hospitalized, 6.6% required intensive care and 15.7% died. The severity prediction model included oxygen saturation/inspired oxygen fraction (SatO2/FiO2), age, C-reactive protein (CRP), lymphocyte count, extent score of lung involvement on CXR (ExtScoreCXR), lactate dehydrogenase (LDH), D-dimer level and platelets count, with AUC-ROC=0.94 and AUC-PRC=0.88. The mortality prediction model included age, SatO2/FiO2, CRP, LDH, CXR extent score, lymphocyte count and D-dimer level, with AUC-ROC=0.97 and AUC-PRC=0.78. The addition of CXR CNN-based indices did not improve significantly the predictive metrics. Conclusion: The developed and internally validated severity and mortality prediction models could be useful as triage tools in ED for patients with COVID-19 or other virus infections with similar behaviour.(AU)

[Development of severity and mortality prediction models for covid-19 patients at emergency department including the chest x-ray]. / 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.

Objectives: To develop prognosis prediction models for COVID-19 patients attending an emergency department (ED) based on initial chest X-ray (CXR), demographics, clinical and laboratory parameters. Methods: All symptomatic confirmed COVID-19 patients admitted to our hospital ED between February 24th and April 24th 2020 were recruited. CXR features, clinical and laboratory variables and CXR abnormality indices extracted by a convolutional neural network (CNN) diagnostic tool were considered potential predictors on this first visit. The most serious individual outcome defined the three severity level: 0) home discharge or hospitalization ≤ 3 days, 1) hospital stay >3 days and 2) intensive care requirement or death. Severity and in-hospital mortality multivariable prediction models were developed and internally validated. The Youden index was used for the optimal threshold selection of the classification model. Results: A total of 440 patients were enrolled (median 64 years; 55.9% male); 13.6% patients were discharged, 64% hospitalized, 6.6% required intensive care and 15.7% died. The severity prediction model included oxygen saturation/inspired oxygen fraction (SatO2/FiO2), age, C-reactive protein (CRP), lymphocyte count, extent score of lung involvement on CXR (ExtScoreCXR), lactate dehydrogenase (LDH), D-dimer level and platelets count, with AUC-ROC = 0.94 and AUC-PRC = 0.88. The mortality prediction model included age, SatO2/FiO2, CRP, LDH, CXR extent score, lymphocyte count and D-dimer level, with AUC-ROC = 0.97 and AUC-PRC = 0.78. The addition of CXR CNN-based indices did not improve significantly the predictive metrics. Conclusion: The developed and internally validated severity and mortality prediction models could be useful as triage tools in ED for patients with COVID-19 or other virus infections with similar behaviour.

Noninvasive Liver Assessment in Adult Patients With Fontan Circulation Using Acoustic Radiation Force Impulse Elastography and Hepatic Magnetic Resonance Imaging.

BACKGROUND: Patients who have undergone the Fontan procedure are at risk of developing hepatic dysfunction. However, broad recommendations regarding liver monitoring are limited. The purpose of this study was to characterize the frequency of liver disease in adult Fontan patients using multimodality imaging (hepatic magnetic resonance imaging [MRI], acoustic radiation force impulse [ARFI] elastography, or hepatic ultrasound). METHODS: In a prospective cross-sectional analysis of adult patients palliated with a Fontan procedure, hepatic MRI, ARFI, and hepatic ultrasound were used to assess for liver disease. The protocol compared (1) varying prevalence of liver disease based on each imaging technique, (2) agreement between different techniques, and (3) association between noninvasive imaging diagnosis of liver disease and clinical variables, including specific liver disease biomarkers. RESULTS: Thirty-seven patients were enrolled. The ARFI results showed high wave propagation velocity in 35 patients (94.6%). All patients had some abnormality in the hepatic MRI. Specifically, 8 patients (21.6%) showed signs of chronic liver disease, 10 patients (27%) had significant liver fibrosis, and 27 patients (73%) had congestion. No correlation was found between liver stiffness measured as propagation velocity and hepatic MRI findings. Only 7 patients had an abnormal hepatic ultrasound study. CONCLUSIONS: There is an inherent liver injury in adult Fontan patients. Signs of liver disease were observed in most patients by both hepatic MRI and ARFI elastography but not by ultrasound imaging. Increased liver stiffness did not identify specific disease patterns from MRI, supporting the need for multimodality imaging to characterize liver disease in Fontan patients.

Algoritmo para el diagnóstico y el seguimiento de la tromboembolia pulmonar aguda / Algorithm for the diagnosis and follow-up of acute pulmonary embolisms

El diagnóstico urgente de una tromboembolia pulmonar (TEP) aguda se beneficia del uso de pautas de decisión clínica basadas en la evidencia que mejoran el pronóstico de los pacientes y reducen el empleo innecesario de pruebas de imagen. En este artículo se explican los algoritmos para el diagnóstico de la TEP publicados más recientemente por las sociedades científicas implicadas, en la población general y en situaciones especiales, intentando esclarecer las dudas frecuentes y analizar las controversias persistentes. También se discute la necesidad de controlar con imagen la resolución de la TEP tras el tratamiento anticoagulante, actualmente no recomendado en las guías clínicas (AU)

The urgent diagnosis of acute pulmonary thromboembolism benefits from the use of evidence-based clinical guidelines that improve patients’ prognoses and reduce the unnecessary use of imaging tests. This article explains the diagnostic algorithms for pulmonary thromboembolism most recently published by the relevant scientific societies both for the general population and for special situations, trying to clear up common doubts and analyzing persistent controversies. It also discusses the need to follow up the thromboembolism after anticoagulation treatment, which is not currently recommended in the guidelines (AU)

Algorithm for the diagnosis and follow-up of acute pulmonary embolisms. / Algoritmo para el diagnóstico y el seguimiento de la tromboembolia pulmonar aguda.

The urgent diagnosis of acute pulmonary thromboembolism benefits from the use of evidence-based clinical guidelines that improve patients' prognoses and reduce the unnecessary use of imaging tests. This article explains the diagnostic algorithms for pulmonary thromboembolism most recently published by the relevant scientific societies both for the general population and for special situations, trying to clear up common doubts and analyzing persistent controversies. It also discusses the need to follow up the thromboembolism after anticoagulation treatment, which is not currently recommended in the guidelines.

Neoplasias hematológicas: interpretación de los hallazgos pulmonares en la tomografía computarizada torácica / Hematologic neoplasms: interpreting lung findings in chest computed tomography

La patología pulmonar en la historia de un paciente con neoplasia hematológica es muy frecuente y variable en función de la enfermedad de base y la terapia recibida. La morbimortalidad asociada es alta, por lo que requiere un tratamiento correcto y precoz. La tomografía computarizada (TC) torácica, junto con el análisis de muestras biológicas, son las herramientas de diagnóstico de primera línea empleadas en estos pacientes, y en determinados casos se requieren métodos invasivos. La interpretación de las imágenes exige el análisis de un contexto clínico en muchas ocasiones complejo. Partiendo del conocimiento que adquiere el radiólogo en su formación sobre el diagnóstico diferencial de los hallazgos pulmonares, el objetivo de este trabajo es explicar los aspectos clínicos y radiológicos claves que permiten orientar correctamente el diagnóstico y asimilar el papel actual de la TC en la estrategia terapéutica de este grupo de enfermos (AU)

Lung disease is very common in patients with hematologic neoplasms and varies in function of the underlying disease and its treatment. Lung involvement is associated with high morbidity and mortality, so it requires early appropriate treatment. Chest computed tomography (CT) and the analysis of biologic specimens are the first line diagnostic tools in these patients, and sometimes invasive methods are necessary. Interpreting the images requires an analysis of the clinical context, which is often complex. Starting from the knowledge about the differential diagnosis of lung findings that radiologists acquire during training, this article aims to explain the key clinical and radiological aspects that make it possible to orient the diagnosis correctly and to understand the current role of CT in the treatment strategy for this group of patients (AU)

Hematologic neoplasms: interpreting lung findings in chest computed tomography.

Lung disease is very common in patients with hematologic neoplasms and varies in function of the underlying disease and its treatment. Lung involvement is associated with high morbidity and mortality, so it requires early appropriate treatment. Chest computed tomography (CT) and the analysis of biologic specimens are the first line diagnostic tools in these patients, and sometimes invasive methods are necessary. Interpreting the images requires an analysis of the clinical context, which is often complex. Starting from the knowledge about the differential diagnosis of lung findings that radiologists acquire during training, this article aims to explain the key clinical and radiological aspects that make it possible to orient the diagnosis correctly and to understand the current role of CT in the treatment strategy for this group of patients.