Diagnostic performance of artificial intelligence algorithms for detection of pulmonary involvement by COVID-19 based on portable radiography. / Rendimiento diagnóstico de algoritmos de inteligencia artificial para detección de compromiso pulmonar por COVID-19 basados en radiografía portátil.

INTRODUCTION AND OBJECTIVES: To evaluate the diagnostic performance of different artificial intelligence (AI) algorithms for the identification of pulmonary involvement by SARS-CoV-2 based on portable chest radiography (RX). MATERIAL AND METHODS: Prospective observational study that included patients admitted for suspected COVID-19 infection in a university hospital between July and November 2020. The reference standard of pulmonary involvement by SARS-CoV-2 comprised a positive PCR test and low-tract respiratory symptoms. RESULTS: 493 patients were included, 140 (28%) with positive PCR and 32 (7%) with SARS-CoV-2 pneumonia. The AI-B algorithm had the best diagnostic performance (areas under the ROC curve AI-B 0.73, vs. AI-A 0.51, vs. AI-C 0.57). Using a detection threshold greater than 55%, AI-B had greater diagnostic performance than the specialist [(area under the curve of 0.68 (95% CI 0.64-0.72), vs. 0.54 (95% CI 0.49-0.59)]. CONCLUSION: AI algorithms based on portable RX enabled a diagnostic performance comparable to human assessment for the detection of SARS-CoV-2 lung involvement.

Short and Long-Term Impact of COVID-19 Infection on Previous Respiratory Diseases.

On March 11, 2020, the World Health Organization declared Coronavirus Disease 2019 (COVID-19) a pandemic. Till now, it affected 452.4 million (Spain, 11.18 million) persons all over the world with a total of 6.04 million of deaths (Spain, 100,992). It is observed that 75% of hospitalized COVID-19 patients have at least one COVID-19 associated comorbidity. It was shown that people with underlying chronic illnesses are more likely to get it and grow seriously ill. Individuals with COVID-19 who have a past medical history of cardiovascular disorder, cancer, obesity, chronic lung disease, diabetes, or neurological disease had the worst prognosis and are more likely to develop acute respiratory distress syndrome or pneumonia. COVID-19 can affect the respiratory system in a variety of ways and across a spectrum of levels of disease severity, depending on a person's immune system, age and comorbidities. Symptoms can range from mild, such as cough, shortness of breath and fever, to critical disease, including respiratory failure, shock and multi-organ system failure. So, COVID-19 infection can cause overall worsening of these previous respiratory diseases, such as asthma, chronic obstructive pulmonary disease (COPD), interstitial lung disease, etc. This review aims to provide information on the impact of the COVID-19 disease on pre-existing lung comorbidities.

Clinical findings, risk factors, and final outcome in patients diagnosed with pulmonary thromboembolism and COVID-19 in hospital emergency departments. / Características clínicas, factores de riesgo y resultados finales de pacientes con COVID-19 diagnosticados de tromboembolia de pulmón en urgencias.

OBJECTIVES: To analyze clinical, laboratory, and radiologic findings and final health outcomes in patients with pulmonary embolism and coronavirus disease 2019 (COVID-19). To compare them to findings and outcomes in patients with pulmonary embolism without COVID-19. MATERIAL AND METHODS: Multicenter, observational, retrospective study in 4 Spanish hospital emergency departments (EDs) from January 15 to April 15, 2020. Cases were located by reviewing all ED requests for pulmonary computed tomography angiography (CTA) procedures. Clinical, laboratory, and radiologic findings; medical histories and comorbidity; risk factors; and outcomes were compared between the 2 groups of patients (with or without COVID-19). RESULTS: A total of 399 CTAs were ordered; 88 pulmonary embolisms were diagnosed, 28 of them (32%) in patients with COVID-19. This group had more men, and a history of thromboembolic disease was more common. We found no between-group differences in clinical presentation, laboratory, or radiologic findings; nor were there differences in final outcomes. In-hospital mortality was 7% (2 cases) in patients with COVID-19 and 17% (10 cases) in patients without the virus (odds ratio for death in patients with pulmonary embolism and COVID-19, 0.38; 95% CI, 0.08-1.89). CONCLUSION: We found no clinically important differences in the clinical, laboratory, or radiologic findings between patients with or without COVID-19 who were treated for pulmonary embolism in our hospital EDs. Final outcomes also did not differ.

OBJETIVO: Analizar las características clínicas, analíticas, radiológicas y los resultados finales de salud en una cohorte de pacientes con embolia pulmonar (EP) y COVID-19, y compararlas con un grupo de pacientes con EP sin COVID-19. METODO: Estudio multicéntrico, observacional y retrospectivo realizado en cuatro servicios de urgencias hospitalarios (SUH) españoles del 15 de enero al 15 de abril de 2020. La detección de EP se hizo mediante la revisión de todas las angiografías por tomografía computarizada (angioTC) pulmonares solicitadas desde los SUH. Se han analizado dos grupos de pacientes con EP, con o sin enfermedad por COVID-19, y se comparan las características clínicas, analíticas, radiológicas, antecedentes y comorbilidad, factores de riesgo y resultados finales. RESULTADOS: Se realizaron 399 angioTC y se diagnosticaron 88 EP, 28 (32%) en pacientes con COVID-19. Estos pacientes fueron con más frecuencia hombres y tenían más antecedentes de enfermedad tromboembólica previa. No hubo diferencias en la presentación clínica, características analíticas o radiológicas ni en los resultados finales entre ambos grupos. La mortalidad intrahospitalaria fue del 7% (2 casos) en pacientes COVID y del 17% (10 casos) en pacientes sin COVID (OR de muerte en pacientes COVID con EP: 0,38, IC 95%: 0,08-1,89). CONCLUSIONES: No se han observado diferencias clínicamente relevantes en las características clínicas, analíticas, radiológicas y los resultados finales de salud en una cohorte de pacientes con EP y COVID-19 respecto a los pacientes con EP sin esta enfermedad atendidos en los SUH.

Simultaneous mechanical ventilation of several patients with a single ventilator.

INTRODUCTION: Simultaneous mechanical ventilation of several patients with a single ventilator might reduce the deficit of these devices for the care of patients with acute respiratory failure due to Covid-19. OBJECTIVE: To communicate the results of a mechanical ventilation exercise with a ventilator in a lung simulator, and simultaneously in two and four. RESULTS: No statistically significant differences were observed between programmed, recorded and measured positive end-expiratory pressure, mean airway pressure and peak pressure, except when simultaneously ventilating four lung simulators. CONCLUSIONS: Simultaneous mechanical ventilation should be implemented by medical personnel with experience in the procedure, be restricted to two patients and carried out in the intensive care unit.

INTRODUCCIÓN: La ventilación mecánica simultánea a varios pacientes con un solo ventilador podría disminuir el déficit de esos dispositivos para atender a los enfermos con insuficiencia respiratoria aguda por Covid-19. OBJETIVO: Comunicar los resultados de un ejercicio de ventilación mecánica con un ventilador en un simulador de pulmón, y simultáneamente en dos y cuatro. RESULTADOS: No se observaron diferencias estadísticamente significativas entre la presión positiva al final de la espiración, presión media de la vía aérea y presión pico programadas, registradas y medidas, excepto al ventilar simultáneamente cuatro simuladores de pulmón. CONCLUSIONES: La ventilación mecánica simultánea debe ser instaurada por personal médico con experiencia en el procedimiento, restringirse a dos pacientes y ser realizada en la unidad de cuidados intensivos.