RESUMO
Background: The emergence of new SARS-CoV-2 variants with significant immune-evasiveness, the relaxation of measures for reducing the number of infections, the waning of immune protection (particularly in high-risk population groups), and the low uptake of new vaccine boosters, forecast new waves of hospitalizations and admission to intensive care units. There is an urgent need for easily implementable and clinically effective Early Warning Scores (EWSs) that can predict the risk of complications within the next 24-48 hr. Although EWSs have been used in the evaluation of COVID-19 patients, there are several clinical limitations to their use. Moreover, no models have been tested on geographically distinct populations or population groups with varying levels of immune protection. Methods: We developed and validated COVID-19 Early Warning Score (COEWS), an EWS that is automatically calculated solely from laboratory parameters that are widely available and affordable. We benchmarked COEWS against the widely used NEWS2. We also evaluated the predictive performance of vaccinated and unvaccinated patients. Results: The variables of the COEWS predictive model were selected based on their predictive coefficients and on the wide availability of these laboratory variables. The final model included complete blood count, blood glucose, and oxygen saturation features. To make COEWS more actionable in real clinical situations, we transformed the predictive coefficients of the COEWS model into individual scores for each selected feature. The global score serves as an easy-to-calculate measure indicating the risk of a patient developing the combined outcome of mechanical ventilation or death within the next 48 hr.The discrimination in the external validation cohort was 0.743 (95% confidence interval [CI]: 0.703-0.784) for the COEWS score performed with coefficients and 0.700 (95% CI: 0.654-0.745) for the COEWS performed with scores. The area under the receiver operating characteristic curve (AUROC) was similar in vaccinated and unvaccinated patients. Additionally, we observed that the AUROC of the NEWS2 was 0.677 (95% CI: 0.601-0.752) in vaccinated patients and 0.648 (95% CI: 0.608-0.689) in unvaccinated patients. Conclusions: The COEWS score predicts death or MV within the next 48 hr based on routine and widely available laboratory measurements. The extensive external validation, its high performance, its ease of use, and its positive benchmark in comparison with the widely used NEWS2 position COEWS as a new reference tool for assisting clinical decisions and improving patient care in the upcoming pandemic waves. Funding: University of Vienna.
Assuntos
COVID-19 , Escore de Alerta Precoce , Humanos , SARS-CoV-2 , Estudos RetrospectivosRESUMO
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.
Assuntos
COVID-19 , SARS-CoV-2 , Hospitalização , Hospitais , Humanos , Aprendizado de Máquina , Estudos RetrospectivosRESUMO
(1) Background: This work aims to analyze clinical outcomes according to ethnic groups in patients hospitalized for COVID-19 in Spain. (2) Methods: This nationwide, retrospective, multicenter, observational study analyzed hospitalized patients with confirmed COVID-19 in 150 Spanish hospitals (SEMI-COVID-19 Registry) from 1 March 2020 to 31 December 2021. Clinical outcomes were assessed according to ethnicity (Latin Americans, Sub-Saharan Africans, Asians, North Africans, Europeans). The outcomes were in-hospital mortality (IHM), intensive care unit (ICU) admission, and the use of invasive mechanical ventilation (IMV). Associations between ethnic groups and clinical outcomes adjusted for patient characteristics and baseline Charlson Comorbidity Index values and wave were evaluated using logistic regression. (3) Results: Of 23,953 patients (median age 69.5 years, 42.9% women), 7.0% were Latin American, 1.2% were North African, 0.5% were Asian, 0.5% were Sub-Saharan African, and 89.7% were European. Ethnic minority patients were significantly younger than European patients (median (IQR) age 49.1 (40.5−58.9) to 57.1 (44.1−67.1) vs. 71.5 (59.5−81.4) years, p < 0.001). The unadjusted IHM was higher in European (21.6%) versus North African (11.4%), Asian (10.9%), Latin American (7.1%), and Sub-Saharan African (3.2%) patients. After further adjustment, the IHM was lower in Sub-Saharan African (OR 0.28 (0.10−0.79), p = 0.017) versus European patients, while ICU admission rates were higher in Latin American and North African versus European patients (OR (95%CI) 1.37 (1.17−1.60), p < 0.001) and (OR (95%CI) 1.74 (1.26−2.41), p < 0.001). Moreover, Latin American patients were 39% more likely than European patients to use IMV (OR (95%CI) 1.43 (1.21−1.71), p < 0.001). (4) Conclusion: The adjusted IHM was similar in all groups except for Sub-Saharan Africans, who had lower IHM. Latin American patients were admitted to the ICU and required IMV more often.
RESUMO
Introducción: La implicación de los médicos asistenciales en tareas de investigación clínica presenta grandes diferencias entre las diversas instituciones. Material y método: Estudio transversal basado en una encuesta enviada a los miembros del Grupo de Trabajo de Enfermedades Infecciosas (GTei) de la Sociedad Española de Medicina Interna (SEMI) durante el mes de mayo de 2022. Resultados: De 1.789 miembros del GTei, 169 miembros (9,45%) cumplimentaron la encuesta. La percepción de la conveniencia de participación de cada facultativo en una o varias líneas de investigación fue de 8 puntos (P25:7; P75: 9 puntos). La percepción sobre el estímulo para investigar del sistema sanitario o de la dirección del hospital fue de 2 puntos (1-4), respectivamente. El apoyo a la investigación fue valorado con de 5 (2-7) y 6 (3-7) puntos en relación con el jefe de servicio y los compañeros del departamento, respectivamente. Otros factores evaluados fueron la falta de tiempo por no poder reducir la actividad asistencial (9; 7-10 puntos), la priorización de las actividades de ocio durante el tiempo libre disponible (7; 5-8 puntos), la organización de la carga asistencial (6; 3-9 puntos), las dificultades en la coordinación con otros servicios clínicos o centrales (6; 5-7 puntos y 6; 5-8 puntos, respectivamente). Conclusiones: La investigación clínica es muy bien valorada por los internistas dedicados a la patología infecciosa. Las principales necesidades percibidas son un mayor apoyo institucional y de la dirección del hospital, una mejor organización del departamento, la coordinación interdepartamental y disponer de más tiempo para esta actividad.(AU)
Background: The involvement of attending physicians in clinical research activities differs greatly among institutions. Method: Cross-sectional study based on a survey submitted to the members of the Working Group on Infectious Diseases (GTei) of the Spanish Society of Internal Medicine (SEMI) during the month of May 2022. Results: Out of 1,789 members of the GTei, 169 members (9.45%) completed the survey. The perception of the convenience of participation of each physician in one or more lines of research was 8 points (P25:7; P75: 9 points). The perception of encouragement to do research by the health system or hospital management was 2points (1-4), respectively. Support for research was rated at 5 (2-7) and 6 (3-7) points inrelation to the head of service and colleagues in the department, respectively. Other factors evaluated were the lack of time due to not being able to reduce the care activity (9; 7-10 points), prioritization of leisure activities during available free time (7; 5-8 points), organization of the care load (6; 3-9 points), difficulties in coordinating with other clinical or central services (6; 5-7 points and 6; 5-8 points, respectively). Conclusions: Clinical research is highly valued by internists dedicated to infectious diseases. The main perceived needs are greater institutional and hospital managementsupport, better organization of the department, interdepartmental coordination and more time for this activity. (AU)