Development and evaluation of a machine learning-based in-hospital COVID-19 disease outcome predictor (CODOP): A multicontinental retrospective study.

New SARS-CoV-2 variants, breakthrough infections, waning immunity, and sub-optimal vaccination rates account for surges of hospitalizations and deaths. There is an urgent need for clinically valuable and generalizable triage tools assisting the allocation of hospital resources, particularly in resource-limited countries. We developed and validate CODOP, a machine learning-based tool for predicting the clinical outcome of hospitalized COVID-19 patients. CODOP was trained, tested and validated with six cohorts encompassing 29223 COVID-19 patients from more than 150 hospitals in Spain, the USA and Latin America during 2020-22. CODOP uses 12 clinical parameters commonly measured at hospital admission for reaching high discriminative ability up to 9 days before clinical resolution (AUROC: 0·90-0·96), it is well calibrated, and it enables an effective dynamic risk stratification during hospitalization. Furthermore, CODOP maintains its predictive ability independently of the virus variant and the vaccination status. To reckon with the fluctuating pressure levels in hospitals during the pandemic, we offer two online CODOP calculators, suited for undertriage or overtriage scenarios, validated with a cohort of patients from 42 hospitals in three Latin American countries (78-100% sensitivity and 89-97% specificity). The performance of CODOP in heterogeneous and geographically disperse patient cohorts and the easiness of use strongly suggest its clinical utility, particularly in resource-limited countries.

While COVID-19 vaccines have saved millions of lives, new variants, waxing immunity, unequal rollout and relaxation of mitigation strategies mean that the pandemic will keep on sending shockwaves across healthcare systems. In this context, it is crucial to equip clinicians with tools to triage COVID-19 patients and forecast who will experience the worst forms of the disease. Prediction models based on artificial intelligence could help in this effort, but the task is not straightforward. Indeed, the pandemic is defined by ever-changing factors which artificial intelligence needs to cope with. To be useful in the clinic, a prediction model should make accurate prediction regardless of hospital location, viral variants or vaccination and immunity statuses. It should also be able to adapt its output to the level of resources available in a hospital at any given time. Finally, these tools need to seamlessly integrate into clinical workflows to not burden clinicians. In response, Klén et al. built CODOP, a freely available prediction algorithm that calculates the death risk of patients hospitalized with COVID-19 (https://gomezvarelalab.em.mpg.de/codop/). This model was designed based on biochemical data from routine blood analyses of COVID-19 patients. Crucially, the dataset included 30,000 individuals from 150 hospitals in Spain, the United States, Honduras, Bolivia and Argentina, sampled between March 2020 and February 2022 and carrying most of the main COVID-19 variants (from the original Wuhan version to Omicron). CODOP can predict the death or survival of hospitalized patients with high accuracy up to nine days before the clinical outcome occurs. These forecasting abilities are preserved independently of vaccination status or viral variant. The next step is to tailor the model to the current pandemic situation, which features increasing numbers of infected people as well as accumulating immune protection in the overall population. Further development will refine CODOP so that the algorithm can detect who will need hospitalisation in the next 24 hours, and who will need admission in intensive care in the next two days. Equipping primary care settings and hospitals with these tools will help to restore previous standards of health care during the upcoming waves of infections, particularly in countries with limited resources.

Characteristics and outcomes of patients infected with nCoV19 requiring invasive mechanical ventilation in Argentina. / Características y resultados de los pacientes infectados con nCoV19 con requerimiento de ventilación mecánica invasiva en la Argentina.

OBJECTIVE: A novel coronavirus emerged this year as a cause of viral pneumonia. The main characteristics of the virus are rapid transmission, high contagion capacity and potential severity. The objective of this case series study is to describe the clinical characteristics of patients with confirmed coronavirus disease (COVID-19) admitted to different intensive care units in Argentina for mechanical ventilation. METHODS: A descriptive, prospective, multicenter case series study was conducted between April 1 and May 8, 2020. Data from patients older than 18 years who were admitted to the intensive care unit for mechanical ventilation for acute respiratory failure with a positive diagnosis of COVID-19 were included. RESULTS: The variables for 47 patients from 31 intensive care units were recorded: 78.7% were men (median age of 61 years), with a SAPS II score of 43 and a Charlson index score of 3. The initial ventilatory mode was volume control - continuous mandatory ventilation with a tidal volume less than 8mL/kg in 100% of cases, with a median positive end-expiratory pressure of 10.5cmH2O. At the end of the study, 29 patients died, 8 were discharged, and 10 remained hospitalized. The SAPS II score was higher among patients who died (p = 0.046). Charlson comorbidity index was associated with higher mortality (OR = 2.27, 95% CI 1.13 - 4.55, p = 0.02). CONCLUSION: Patients with COVID-19 and on mechanical ventilation in this series presented clinical variables similar to those described to date in other international reports. Our findings provide data that may predict outcomes.

OBJETIVO: El coronavirus ha emergido este año como causa de neumonía viral. Una de las principales características es su rápida transmisión y su potencial severidad. El objetivo de este estudio de serie de casos es describir las características clínicas de los pacientes con confirmación de enfermedad por coronavirus (COVID-19) admitidos en diferentes unidades de cuidados intensivos de la Argentina con requerimiento de ventilación mecánica. MÉTODOS: Estudio de serie de casos, descriptivo-prospectivo, multicéntrico realizado entre el 01 de abril y el 08 de mayo de 2020. Se incluyeron los datos de los pacientes mayores a 18 años, que ingresaron a la unidad de cuidados intensivos con requerimiento de ventilación mecánica por falla respiratoria aguda con diagnóstico positivo de COVID-19. RESULTADOS: Se registraron las variables de 47 pacientes de 31 unidades cuidados intensivos, 78.7% hombres de una mediana de edad de 61 años, con un SAPS II de 43, un índice de Charlson de 3. El modo ventilatorio inicial fue volume control - continuous mandatory ventilation con volumen corriente menor a 8mL/kg en el 100% de los casos, con una mediana de presión positiva al final de la espiración de 10,5cmH2O. A la fecha de cierre del estudio, 29 pacientes fallecieron, 8 alcanzaron el alta, y 10 pacientes continúan internados al cierre del estudio. El SAPS II fue mayor entre los fallecidos (p = 0.046). El índice de Charlson se asoció con mayor mortalidad (OR = 2,27 IC95% 1,13 - 4,55; p = 0,02). CONCLUSIÓN: Los pacientes con COVID-19 y ventilación mecánica de esta serie presentan variables clínicas similares a las descriptas a la fecha en otros reportes internacionales. Nuestros hallazgos proporcionan datos que permitirían de alguna manera predecir los resultados.

Evaluación del bloqueo del cuadrado lumbar transmuscular ecoguiado en pediatría / Efficacy of ultrasound-guided transmuscular quadratus lumborum block in children

OBJECTIVES:Transmuscular quadratus lumborum block (TQLB) is a novel regional anaesthesia technique that has proven to be effective for postoperative pain reduction in different abdominal surgical procedures. The present study evaluated its efficacy on pain intensity and analgesic consumption in children undergoing low abdominal surgery. METHODS: The study included forty patients, aged 1 to 6 years, scheduled for low abdominal surgery (hernia repair or orchiopexy) under general anaesthesia. They were enrolled in two groups: TQLB block plus systemic analgesia (group 1; n = 20) wound infiltration done by the surgeon plus systemic analgesia (Group 2; n = 20). All blocks were performed by the same anesthesiologist under general anaesthesia before surgery. Both groups received the same systemic analgesia protocol. Analgesic consumption (ibuprofen) within the first 24 postoperative hours, pain intensity scores (FLACC scale) at 60 minutes, 2, 6 and 24 hours after surgery, time in which the first analgesia was required, satisfaction levels of the parents (0-10), adverse events related to systemic analgesia and time to hospital discharge were evaluated and registered. RESULTS: We found differences between both groups in ibuprofen consumption (80 mg 185 mg; p < 0.05) and pain scores (FLACC) within the first 24 postoperative hours at each interval (p < 0.05 for every point in time analyzed). Time in which the first analgesia was required was longer for the TQLB group (18 10 hours; p < 0.05). Satisfaction levels of the parents were also higher in the first group (p < 0.05). Adverse events related to medication and time to hospital discharge showed similar results. Further investigation comparing the TQLB with different approaches of QLB or conventional TAP block could be interesting and is required in a near future.

INTRODUCCIÓN: El bloqueo del cuadrado lumbar transmuscular (TQL) es una técnica de anestesia regional ecoguiada que demostró ser efectiva en cirugía abdominal abierta y laparoscópica como parte de un esquema multimodal de analgesia postoperatoria. La presente investigación evaluó su eficacia en cirugía de hernia inguinal y testículo no descendido en población pediátrica (de 1-6 años de edad). MATERIALES Y MÉTODOS: El estudio fue diseñado como un ensayo clínico controlado, aleatorizado en 2 ramas: grupo protocolo bloqueo TQL (Grupo 1; n = 20) grupo protocolo infiltración local por cirujano (Grupo 2; n = 20), simple ciego que incluyó a 40 pacientes pediátricos sometidos a una cirugía de hernia inguinal u orquidopexia unilateral. Todos los bloqueos fueron realizados bajo anestesia general antes del inicio de procedimiento quirúrgico. Ambos grupos recibieron el mismo esquema de analgesia endovenosa y oral postoperatoria. Consumo de analgésicos durante las primeras 24 horas (mg de ibuprofeno), intensidad de dolor con escala FLACC a tiempo 1, 2, 6 y 24 horas postoperatorias, tiempo transcurrido a la primera administración de ibuprofeno, escala de satisfacción parental (0-10) e incidencia de náuseas y vómitos fueron evaluados y registrados. Se consideró como significativa una p < 0,05. RESULTADOS: El consumo promedio de ibuprofeno en las primeras 24 horas fue de 80 mg para el grupo bloqueo TQL y de 185 mg para el segundo grupo, diferencia estadísticamente significativa (p < 0,05). El tiempo transcurrido a la primera administración de ibuprofeno fue mayor en el grupo TQL (18 10 horas), p < 0,05. Las escalas de dolor por FLACC a los 60 y 120 minutos y a las 6 y 24 horas. postcirugía fueron menores comparadas con el grupo de infiltración local por el cirujano (p < 0,05 en cada punto de análisis). Las escalas de satisfacción parental mostraron puntajes más elevados para el grupo que recibió el bloqueo TQL (p < 0,05). No se hallaron diferencias significativas en la incidencia de episodios de náuseas y/o vómitos en las primeras 24 horas. postoperatorias (p > 0,2). No se reportaron complicaciones asociadas al bloqueo. CONCLUSIONES: Este estudio muestra que el bloqueo TQL aporta beneficios adicionales respecto al plan de analgesia estándar empleado en cirugía de hernia inguinal unilateral u orquidopexia, disminuyendo el requerimiento de analgésicos y la intensidad de dolor en las primeras 24 horas postoperatorias, así como también incrementando la satisfacción de los cuidadores respecto al estado postoperatorio del niño. Sería interesante llevar a cabo nuevas investigaciones comparando esta técnica con otros abordajes del bloqueo de cuadrado lumbar y con el cuestionado bloqueo TAP convencional.

Características y resultados de los pacientes infectados con nCoV19 con requerimiento de ventilación mecánica invasiva en la Argentina / Characteristics and outcomes of patients infected with nCoV19 requiring invasive mechanical ventilation in Argentina

RESUMEN Objetivo: El coronavirus ha emergido este año como causa de neumonía viral. Una de las principales características es su rápida transmisión y su potencial severidad. El objetivo de este estudio de serie de casos es describir las características clínicas de los pacientes con confirmación de enfermedad por coronavirus (COVID-19) admitidos en diferentes unidades de cuidados intensivos de la Argentina con requerimiento de ventilación mecánica. Métodos: Estudio de serie de casos, descriptivo-prospectivo, multicéntrico realizado entre el 01 de abril y el 08 de mayo de 2020. Se incluyeron los datos de los pacientes mayores a 18 años, que ingresaron a la unidad de cuidados intensivos con requerimiento de ventilación mecánica por falla respiratoria aguda con diagnóstico positivo de COVID-19 Resultados: Se registraron las variables de 47 pacientes de 31 unidades cuidados intensivos, 78.7% hombres de una mediana de edad de 61 años, con un SAPS II de 43, un índice de Charlson de 3. El modo ventilatorio inicial fue volume control - continuous mandatory ventilation con volumen corriente menor a 8mL/kg en el 100% de los casos, con una mediana de presión positiva al final de la espiración de 10,5cmH2O. A la fecha de cierre del estudio, 29 pacientes fallecieron, 8 alcanzaron el alta, y 10 pacientes continúan internados al cierre del estudio. El SAPS II fue mayor entre los fallecidos (p = 0.046). El índice de Charlson se asoció con mayor mortalidad (OR = 2,27 IC95% 1,13 - 4,55; p = 0,02). Conclusión: Los pacientes con COVID-19 y ventilación mecánica de esta serie presentan variables clínicas similares a las descriptas a la fecha en otros reportes internacionales. Nuestros hallazgos proporcionan datos que permitirían de alguna manera predecir los resultados.

Abstract Objective: A novel coronavirus emerged this year as a cause of viral pneumonia. The main characteristics of the virus are rapid transmission, high contagion capacity and potential severity. The objective of this case series study is to describe the clinical characteristics of patients with confirmed coronavirus disease (COVID-19) admitted to different intensive care units in Argentina for mechanical ventilation. Methods: A descriptive, prospective, multicenter case series study was conducted between April 1 and May 8, 2020. Data from patients older than 18 years who were admitted to the intensive care unit for mechanical ventilation for acute respiratory failure with a positive diagnosis of COVID-19 were included. Results: The variables for 47 patients from 31 intensive care units were recorded: 78.7% were men (median age of 61 years), with a SAPS II score of 43 and a Charlson index score of 3. The initial ventilatory mode was volume control - continuous mandatory ventilation with a tidal volume less than 8mL/kg in 100% of cases, with a median positive end-expiratory pressure of 10.5cmH2O. At the end of the study, 29 patients died, 8 were discharged, and 10 remained hospitalized. The SAPS II score was higher among patients who died (p = 0.046). Charlson comorbidity index was associated with higher mortality (OR = 2.27, 95% CI 1.13 - 4.55, p = 0.02). Conclusion: Patients with COVID-19 and on mechanical ventilation in this series presented clinical variables similar to those described to date in other international reports. Our findings provide data that may predict outcomes.