[Performance in prognostic capacity and efficiency of the Thoracic Care Suite GE AI tool applied to chest radiography of patients with COVID-19 pneumonia]. / 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 por COVID-19.

OBJECTIVE: Rapid progression of COVID-19 pneumonia may put patients at risk of requiring ventilatory support, such as non-invasive mechanical ventilation or endotracheal intubation. Implementing tools that detect COVID-19 pneumonia can improve the patient's healthcare. We aim to evaluate the efficacy and efficiency of the artificial intelligence (AI) tool GE Healthcare's Thoracic Care Suite (featuring Lunit INSIGHT CXR, TCS) to predict the ventilatory support need based on pneumonic progression of COVID-19 on consecutive chest X-rays. METHODS: Outpatients with confirmed SARS-CoV-2 infection, with chest X-ray (CXR) findings probable or indeterminate for COVID-19 pneumonia, who required a second CXR due to unfavorable clinical course, were collected. The number of affected lung fields for the two CXRs was assessed using the AI tool. RESULTS: One hundred fourteen patients (57.4 ± 14.2 years, 65 -57%- men) were retrospectively collected. Fifteen (13.2%) required ventilatory support. Progression of pneumonic extension ≥ 0.5 lung fields per day compared to pneumonia onset, detected using the TCS tool, increased the risk of requiring ventilatory support by 4-fold. Analyzing the AI output required 26 seconds of radiological time. CONCLUSIONS: Applying the AI tool, Thoracic Care Suite, to CXR of patients with COVID-19 pneumonia allows us to anticipate ventilatory support requirements requiring less than half a minute.

Early radiological worsening of SARS-CoV-2 pneumonia predicts the need for ventilatory support.

OBJECTIVES: Identifying early markers of poor prognosis of coronavirus disease 2019 (COVID-19) is mandatory. Our purpose is to analyze by chest radiography if rapid worsening of COVID-19 pneumonia in the initial days has predictive value for ventilatory support (VS) need. METHODS: Ambispective observational ethically approved study in COVID-19 pneumonia inpatients, validated in a second outpatient sample. Brixia score (BS) was applied to the first and second chest radiography required for suspected COVID-19 pneumonia to determine the predictive capacity of BS worsening for VS need. Intraclass correlation coefficient (ICC) was previously analyzed among three radiologists. Sensitivity, specificity, likelihood ratios, AUC, and odds ratio were calculated using ROC curves and binary logistic regression analysis. A value of p < .05 was considered statistically significant. RESULTS: A total of 120 inpatients (55 ± 14 years, 68 men) and 112 outpatients (56 ± 13 years, 61 men) were recruited. The average ICC of the BS was between 0.812 (95% confidence interval 0.745-0.878) and 0.906 (95% confidence interval 0.844-0.940). According to the multivariate analysis, a BS worsening per day > 1.3 points within 10 days of the onset of symptoms doubles the risk for requiring VS in inpatients and 5 times in outpatients (p < .001). The findings from the second chest radiography were always better predictors of VS requirement than those from the first one. CONCLUSION: The early radiological worsening of SARS-CoV-2 pneumonia after symptoms onset is a determining factor of the final prognosis. In elderly patients with some comorbidity and pneumonia, a 48-72-h follow-up radiograph is recommended. KEY POINTS: • An early worsening on chest X-ray in patients with SARS-CoV-2 pneumonia is highly predictive of the need for ventilatory support. • This radiological worsening rate can be easily assessed by comparing the first and the second chest X-ray. • In elderly patients with some comorbidity and SARS-CoV-2 pneumonia, close early radiological follow-up is recommended.

Use of diagnostic tests in elderly patients consulting the emergency department. Analysis of the emergency department and elder needs cohort (EDEN-8).

OBJECTIVE: Analyse the association between the use of diagnostic tests and the characteristics of older patients 65 years of age or more who consult the emergency department (ED). METHODS: We performed an analysis of the EDEN cohort that includes patients who consulted 52 Spanish EDs. The association of age, sex, and ageing characteristics with the use of diagnostic tests (blood tests, electrocardiogram (ECG), microbiological cultures, X-ray, computed tomography, ultrasound, invasive techniques) was studied. The association was analysed by calculating the adjusted odds ratios (aOR) and their 95 % confidence intervals (CI) using a logistic regression model. RESULTS: A total of 25,557 patients were analysed. There was an increase in the use of diagnostic tests based on age, with an aOR for blood test of 1.805 (95 %CI 1.671 - 1.950), ECG 1.793 (95 %CI 1.664 - 1.932) and X-ray 1.707 (95 %CI 1.583 - 1.840) in the group of 85 years or more. The use of diagnostic tests is lower in the female population. Most ageing characteristics (cognitive impairment, previous falls, polypharmacy, dependence, and comorbidity) were independently associated with increased use of diagnostic tests. CONCLUSIONS: Age, and the characteristics of ageing itself are generally associated with a greater use of diagnostic tests in the ED.

Study EDEN-12: Analysis of access to intensive care units of patients older than 65 years requiring emergency hospitalization.

OBJECTIVE: To investigate the relationship between the age of an urgently hospitalized patient and his or her probability of admission to an intensive care unit (ICU). DESIGN: Observational, retrospective, multicenter study. SETTING: 42 Emergency Departments from Spain. TIME-PERIOD: April 1-7, 2019. PATIENTS: Patients aged ≥65 years hospitalized from Spanish emergency departments. INTERVENTIONS: None. MAIN VARIABLES OF INTEREST: ICU admission, age sex, comorbidity, functional dependence and cognitive impairment. RESULTS: 6120 patients were analyzed (median age: 76 years; males: 52%. 309 (5%) were admitted to ICU (186 from ED, 123 from hospitalization). Patients admitted to the ICU were younger, male, and with less comorbidity, dependence and cognitive impairment, but there were no differences between those admitted from the ED and from hospitalization. The OR for ICU-admission adjusted by sex, comorbidity, dependence and dementia reached statistical significance >83 years (OR: 0.67; 95%CI: 0.45-0.49). In patients admitted to the ICU from ED, the OR did not begin to decrease until 79 years, and was significant >85 years (OR: 0.56, 95%CI: 0.34-0.92); while in those admitted to ICU from hospitalization, the decrease began 65 years of age, and were significant from 85 years (OR: 0.55, 95%CI: 0.30-0.99). Sex, comorbidity, dependency and cognitive deterioration of the patient did not modify the association between age and ICU-admission (overall, from the ED or hospitalization). CONCLUSIONS: After taking into account other factors that influence admission to the ICU (comorbidity, dependence, dementia), the chances of admission to the ICU of older patients hospitalized on an emergency basis begin to decrease significantly after 83 years of age. There may be differences in the probability of admission to the ICU from the ED or from hospitalization according to age.

Sociodemographic characteristics, functional status, and health resource use of older patients treated in Spanish emergency departments: a description of the EDEN cohort. / Características sociodemográficas, funcionales y consumo de recursos de la población mayor atendida en los servicios de urgencias españoles: una aproximación desde la cohorte EDEN.

OBJECTIVES: To describe the sociodemographic characteristics of and the health care resources used to treat patients aged 65 years or older who come to hospital emergency departments (EDs) in Spain, according to age groups. MATERIAL AND METHODS: We studied the phase-1 data for the EDEN cohort (Emergency Department and Elder Needs). Forty Spanish EDs collected data on all patients aged 65 years or older who were treated on the first 7 days in April 2019. We registered information on 6 sociodemographic and 5 function variables for all patients. For health resource use we used 6 diagnostic, 13 therapeutic, and 5 physical structural variables, for a total of 24 variables. Differences were analyzed according to age in blocks of 5 years. RESULTS: A total of 18 374 patients with a median age of 78 years were included; 55% were women. Twenty-seven percent arrived by ambulance, 71% had not previously been seen by a physician, and 13% lived alone without assistance. Ten percent had a high level of functional dependence, and 14% had serious comorbidity. Resources used most often were blood analysis (in 60%) and radiology (59%), analgesics (25%), intravenous fluids (21%), antibiotics (14%), oxygen (13%), and bronchodilators (11%). Twenty-six percent were kept under observation in the ED, 26% were admitted to wards, and 2% were admitted to intensive care units (ICUs). The median stay in the ED was 3.5 hours, and the median hospital stay was 7 days. Sociodemographic characteristics changed according to age. Functional dependence worsened with age, and resource requirements increased in general. However, benzodiazepine use was unaffected, while the use of nonsteroidal anti-inflammatory drugs and ICU admission decreased. CONCLUSION: The functional dependence of older patients coming to EDs increases with age and is associated with a high level of health care resource use, which also increases with age. Planners should take into consideration the characteristics of the older patients and the proportion of the caseload they represent when arranging physical spaces and designing processes for a specific ED.

OBJETIVO: Investigar las características sociodemográficas y consumo de recursos de los pacientes de 65 o más años que consultan en servicios de urgencias hospitalarios (SUH) en España, y su modificación por grupos etarios. METODO: Se utilizaron datos de la cohorte EDEN obtenidos en fase 1 (Emergency Department and Elder Needs). Cuarenta SUH españoles incluyeron todos los pacientes de $ 65 años atendidos del 1-4-2019 al 7-4-2019 (7 días). Se analizaron 6 características sociodemográficas, 5 funcionales y 24 referidas a consumo de recursos (6 diagnósticos, 13 terapéuticos, 5 estructurales) y sus cambios a medida que avanza la edad (agrupada en bloques de 5 años). RESULTADOS: Se analizaron 18.374 pacientes (mediana edad: 78 años; 55% mujeres). El 27% acude a urgencias en ambulancia, el 71% sin consulta médica previa y el 13% vive solo sin cuidadores. Funcionalmente, el 10% tiene dependencia grave y el 14% comorbilidad grave. La solicitud de analítica sanguínea (60% de casos) y radiología (59%) destaca entre el consumo de recursos diagnósticos, y el uso de analgésicos (25%), sueroterapia (21%), antibioticoterapia (14%), oxigenoterapia (13%) y broncodilatadores (11%), entre los terapéuticos. El 26% requiere observación en urgencias, el 26% hospitalización y el 2% cuidados intensivos. La mediana de estancia en urgencias es de 3:30 horas y la de hospitalización es de 7 días. Las características sociodemográficas se modifican con la edad, las funcionales empeoran y el consumo de recursos aumenta (excepto benzodiacepinas, que no se modifica, y antinflamatorios no esteroideos y cuidados intensivos, que disminuye). CONCLUSIONES: Las características funcionales de la población mayor que consulta en los SUH empeora a medida que su edad avanza, y se asocia a un consumo de recursos alto que también se incrementa con la edad. Las características de esta población y su proporción en un determinado SUH deben tenerse en cuenta en su planificación estructural y funcional.