ABSTRACT
BACKGROUND: Efficient and early triage of hospitalized Covid-19 patients to detect those with higher risk of severe disease is essential for appropriate case management. METHODS: We trained, validated, and externally tested a machine-learning model to early identify patients who will die or require mechanical ventilation during hospitalization from clinical and laboratory features obtained at admission. A development cohort with 918 Covid-19 patients was used for training and internal validation, and 352 patients from another hospital were used for external testing. Performance of the model was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity and specificity. RESULTS: A total of 363 of 918 (39.5%) and 128 of 352 (36.4%) Covid-19 patients from the development and external testing cohort, respectively, required mechanical ventilation or died during hospitalization. In the development cohort, the model obtained an AUC of 0.85 (95% confidence interval [CI], 0.82 to 0.87) for predicting severity of disease progression. Variables ranked according to their contribution to the model were the peripheral blood oxygen saturation (SpO2)/fraction of inspired oxygen (FiO2) ratio, age, estimated glomerular filtration rate, procalcitonin, C-reactive protein, updated Charlson comorbidity index and lymphocytes. In the external testing cohort, the model performed an AUC of 0.83 (95% CI, 0.81 to 0.85). This model is deployed in an open source calculator, in which Covid-19 patients at admission are individually stratified as being at high or non-high risk for severe disease progression. CONCLUSIONS: This machine-learning model, applied at hospital admission, predicts risk of severe disease progression in Covid-19 patients.
Subject(s)
COVID-19/classification , Machine Learning , Adult , Aged , Area Under Curve , COVID-19/diagnosis , COVID-19/epidemiology , COVID-19/therapy , Cohort Studies , Female , Forecasting , Hospitalization/statistics & numerical data , Humans , Male , Middle Aged , Models, Statistical , ROC Curve , Respiration, Artificial , Retrospective Studies , Risk Assessment , SARS-CoV-2/isolation & purification , Severity of Illness Index , Spain/epidemiology , Triage/methodsABSTRACT
INTRODUCTION: Hydatid disease is a major health problem in endemic countries. In Spain, this disease was notifiable from 1981 to 1996, although its incidence kept increasing until the end of this period. From 1997 on, hydatid disease is only surveyed by endemic autonomous regions. Thus, true incidences for human hydatid disease in Spain are currently unknown. In this study the cases recorded from 1996 to 2003 at the Hospital Universitario (Salamanca) which receives patients from all Salamanca province, were analyzed. Method. We obtained epidemiological and clinical data from patients at the University Hospital (reference hospital in Salamanca province) with registered CIE-10 codification 122.0 to 122.9 (hydatid disease), from January 1996 to December 2003, excluding those patients not arriving from Salamanca. We estimated the incidence of hydatid disesase in Salamanca province regarding the total population of the province. RESULTS: Our data show that the mean incidence (1996-2003) was 10,8/100.000 inhabitants, twice as many as previously reported by the notifiable diseases scheme. 30% of infected patients were younger than 45. In addition, during the last three years of study, several cases of paediatric hydatid disease were observed. The analysis of the origin of the cases showed a broad distribution throughout the whole province of Salamanca. CONCLUSIONS: The real incidence of this disease seems to be higher than previously estimated. Importantly, the several cases of paediatric hydatid disease detected within the last two years of our study, suggest a possible re-emergence of hydatid disease.
Subject(s)
Echinococcosis/epidemiology , Echinococcosis/diagnosis , Humans , Incidence , Retrospective Studies , Spain/epidemiologyABSTRACT
Introducción. La hidatidosis humana es un problema importante de salud en países endémicos. En España, esta enfermedad fue de declaración obligatoria (EDO) desde 1981 hasta 1996; el número de casos en Castilla y León aumentó desde 1985 a 1996. En 1997 la hidatidosis pasó a ser vigilada por las Comunidades Autónomas con hidatidosis endémica. Actualmente el número de casos y la incidencia anual son desconocidos. En este trabajo, investigamos la situación actual de la hidatidosis humana en la provincia de Salamanca. Método. Se seleccionaron pacientes del Hospital Universitario (hospital de referencia de la provincia de Salamanca) cuya codificación en la novena Clasificación Internacional de Enfermedades (CIE-9) fue 122.0 a 122.9 (hidatidosis) desde enero de 1996 hasta diciembre de 2003, excluyéndose los pacientes residentes en otras provincias. Se obtuvieron datos epidemiológicos y clínicos de los registros informáticos y de las historias clínicas de los pacientes. Se estimó la incidencia provincial según datos del censo poblacional. Resultados. Nuestros resultados demuestran una incidencia media (1996-2003) de 10,8 casos por 100.000 habitantes/año, 2 veces mayor que la registrada previamente mediante el sistema EDO. El 30% de los casos fueron en menores de 45 años. En los años 2000-2003 reaparecieron casos en pacientes en edad pediátrica. También se demostró una amplia distribución de casos en toda la provincia. Conclusiones. La incidencia real de esta parasitosis es superior a la previamente estimada. La reaparición de casos pediátricos y el mantenimiento del 30% de los casos en menores de 45 años apuntan a una posible reemergencia de esta enfermedad (AU)
Introduction. Hydatid disease is a major health problem in endemic countries. In Spain, this disease was notifiable from 1981 to 1996, although its incidence kept increasing until the end of this period. From 1997 on, hydatid disease is only surveyed by endemic autonomous regions. Thus, true incidences for human hydatid disease in Spain are currently unknown. In this study the cases recorded from 1996 to 2003 at the Hospital Universitario (Salamanca) which receives patients from all Salamanca province, were analyzed. Method. We obtained epidemiological and clinical data from patients at the University Hospital (reference hospital in Salamanca province) with registered CIE-10 codification 122.0 to 122.9 (hydatid disease), from January 1996 to December 2003, excluding those patients not arriving from Salamanca. We estimated the incidence of hydatid disesase in Salamanca province regarding the total population of the province. Results. Our data show that the mean incidence (1996-2003) was 10,8/100.000 inhabitants, twice as many as previously reported by the notifiable diseases scheme. 30% of infected patients were younger than 45. In addition, during the last three years of study, several cases of paediatric hydatid disease were observed. The analysis of the origin of the cases showed a broad distribution throughout the whole province of Salamanca. Conclusions. The real incidence of this disease seems to be higher than previously estimated. Importantly, the several cases of paediatric hydatid disease detected within the last two years of our study, suggest a possible re-emergence of hydatid disease (AU)
