Model-interpreted outcomes of artificial neural networks classifying immune biomarkers associated with severe infections in ICU.

Introduction: Millions of deaths worldwide are a result of sepsis (viral and bacterial) and septic shock syndromes which originate from microbial infections and cause a dysregulated host immune response. These diseases share both clinical and immunological patterns that involve a plethora of biomarkers that can be quantified and used to explain the severity level of the disease. Therefore, we hypothesize that the severity of sepsis and septic shock in patients is a function of the concentration of biomarkers of patients. Methods: In our work, we quantified data from 30 biomarkers with direct immune function. We used distinct Feature Selection algorithms to isolate biomarkers to be fed into machine learning algorithms, whose mapping of the decision process would allow us to propose an early diagnostic tool. Results: We isolated two biomarkers, i.e., Programmed Death Ligand-1 and Myeloperoxidase, that were flagged by the interpretation of an Artificial Neural Network. The upregulation of both biomarkers was indicated as contributing to increase the severity level in sepsis (viral and bacterial induced) and septic shock patients. Discussion: In conclusion, we built a function considering biomarker concentrations to explain severity among sepsis, sepsis COVID, and septic shock patients. The rules of this function include biomarkers with known medical, biological, and immunological activity, favoring the development of an early diagnosis system based in knowledge extracted from artificial intelligence.

Modelos de riesgo para la predicción de mortalidad hospitalaria en ancianos con neumonía por COVID-19 / Mortality risk model for patients with suspected COVID-19 based on information available from an emergency dispatch center

Objetivo. Los objetivos son comparar la utilidad pronóstica de tres escalas de gravedad (Pneumonia Severity Index: PSI; CURB-65 scale; Severity Community Acquired Pneumonia Score: SCAP) y diseñar un nuevo modelo predictivo de mortalidad hospitalaria en pacientes mayores de 75 años ingresados por neumonía por COVID-19. Método. Estudio retrospectivo de pacientes mayores de 75 años ingresados por neumonía por COVID-19 desde el servicio de urgencias entre el 12 de marzo y el 27 de abril de 2020. Se recogieron variables demográficas (edad, sexo, institucionalización), clínicas (síntomas, comorbilidades, índice de Charlson) y analíticas (bioquímica en suero, gasometría, hematimetría, hemostasia). Se derivó un modelo de riesgo y se compararon las escalas de gravedad PSI, CURB-65 y SCAP para predecir la mortalidad intrahospitalaria por cualquier causa. Resultados. Se incluyeron 186 pacientes, con una mediana de edad de 85 años (RIC 80-89), un 44,1% varones. La mortalidad fue del 47,3%. Las escalas PSI, CURB-65 y SCAP tuvieron un área bajo la curva (ABC) de 0,74 (IC 95% 0,64-0,82), 0,71 (IC 95% 0,62-0,79) y 0,72 (IC 95% 0,63-0,81), respectivamente. El modelo predictivo compuesto por la ausencia o presencia de síntomas (tos y disnea), comorbilidad (índice de Charlson) y datos analíticos (aspartato-aminotransferasa, potasio, urea y lactato-deshidrogenasa) tuvo un ABC de 0,81 (IC 95% 0,73-0,88). Conclusión. Este estudio muestra que la escala PSI tiene una capacidad predictiva de mortalidad moderada, notablemente mejor que las escalas CURB-65 y SCAP. Se propone un nuevo modelo predictivo de mortalidad que mejora significativamente el rendimiento de estas escalas, siendo necesario verificar su validez externa. (AU)

Objectives: To compare the prognostic value of 3 severity scales: the Pneumonia Severity Index (PSI), the CURB-65 pneumonia severity score, and the Severity Community-Acquired Pneumonia (SCAP) score. To build a new predictive model for in-hospital mortality in patients over the age of 75 years admitted with pneumonia due to the coronavirus disease 2019 (COVID-19). Material and methods: Retrospective study of patients older than 75 years admitted from the emergency department for COVID-19 pneumonia between March 12 and April 27, 2020. We recorded demographic (age, sex, living in a care facility or not), clinical (symptoms, comorbidities, Charlson Comorbidity Index [CCI]), and analytical (serum biochemistry, blood gases, blood count, and coagulation factors) variables. A risk model was constructed, and the ability of the 3 scales to predict all-cause in-hospital mortality was compared. Results: We included 186 patients with a median age of 85 years (interquartile range, 80-89 years); 44.1% were men. Mortality was 47.3%. The areas under the receiver operating characteristic curves (AUCs) were as follows for each tool: PSI, 0.74 (95% CI, 0.64-0.82); CURB-65 score, 0.71 (95% CI, 0.62-0.79); and SCAP score, 0.72 (95% CI, 0.63-0.81). Risk factors included in the model were the presence or absence of symptoms (cough, dyspnea), the CCI, and analytical findings (aspartate aminotransferase, potassium, urea, and lactate dehydrogenase. The AUC for the model was 0.81 (95% CI, 0.73-0.88). Conclusion: This study shows that the predictive power of the PSI for mortality is moderate and perceptibly higher than the CURB-65 and SCAP scores. We propose a new predictive model for mortality that offers significantly better performance than any of the 3 scales compared. However, our model must undergo external validation. (AU)

Risk models for predicting in-hospital mortality from COVID-19 pneumonia in the elderly. / Modelos de riesgo para la predicción de mortalidad hospitalaria en ancianos con neumonía por COVID-19.

OBJECTIVES: To compare the prognostic value of 3 severity scales: the Pneumonia Severity Index (PSI), the CURB-65 pneumonia severity score, and the Severity Community-Acquired Pneumonia (SCAP) score. To build a new predictive model for in-hospital mortality in patients over the age of 75 years admitted with pneumonia due to the coronavirus disease 2019 (COVID-19). MATERIAL AND METHODS: Retrospective study of patients older than 75 years admitted from the emergency department for COVID-19 pneumonia between March 12 and April 27, 2020. We recorded demographic (age, sex, living in a care facility or not), clinical (symptoms, comorbidities, Charlson Comorbidity Index [CCI]), and analytical (serum biochemistry, blood gases, blood count, and coagulation factors) variables. A risk model was constructed, and the ability of the 3 scales to predict all-cause in-hospital mortality was compared. RESULTS: We included 186 patients with a median age of 85 years (interquartile range, 80-89 years); 44.1% were men. Mortality was 47.3%. The areas under the receiver operating characteristic curves (AUCs) were as follows for each tool: PSI, 0.74 (95% CI, 0.64-0.82); CURB-65 score, 0.71 (95% CI, 0.62-0.79); and SCAP score, 0.72 (95% CI, 0.63-0.81). Risk factors included in the model were the presence or absence of symptoms (cough, dyspnea), the CCI, and analytical findings (aspartate aminotransferase, potassium, urea, and lactate dehydrogenase. The AUC for the model was 0.81 (95% CI, 0.73-0.88). CONCLUSION: This study shows that the predictive power of the PSI for mortality is moderate and perceptibly higher than the CURB-65 and SCAP scores. We propose a new predictive model for mortality that offers significantly better performance than any of the 3 scales compared. However, our model must undergo external validation.

OBJETIVO: Los objetivos son comparar la utilidad pronóstica de tres escalas de gravedad (Pneumonia Severity Index: PSI; CURB-65 scale; Severity Community Acquired Pneumonia Score: SCAP) y diseñar un nuevo modelo predictivo de mortalidad hospitalaria en pacientes mayores de 75 años ingresados por neumonía por COVID-19. METODO: Estudio retrospectivo de pacientes mayores de 75 años ingresados por neumonía por COVID-19 desde el servicio de urgencias entre el 12 de marzo y el 27 de abril de 2020. Se recogieron variables demográficas (edad, sexo, institucionalización), clínicas (síntomas, comorbilidades, índice de Charlson) y analíticas (bioquímica en suero, gasometría, hematimetría, hemostasia). Se derivó un modelo de riesgo y se compararon las escalas de gravedad PSI, CURB-65 y SCAP para predecir la mortalidad intrahospitalaria por cualquier causa. RESULTADOS: Se incluyeron 186 pacientes, con una mediana de edad de 85 años (RIC 80-89), un 44,1% varones. La mortalidad fue del 47,3%. Las escalas PSI, CURB-65 y SCAP tuvieron un área bajo la curva (ABC) de 0,74 (IC 95% 0,64-0,82), 0,71 (IC 95% 0,62-0,79) y 0,72 (IC 95% 0,63-0,81), respectivamente. El modelo predictivo compuesto por la ausencia o presencia de síntomas (tos y disnea), comorbilidad (índice de Charlson) y datos analíticos (aspartato- aminotransferasa, potasio, urea y lactato-deshidrogenasa) tuvo un ABC de 0,81 (IC 95% 0,73-0,88). CONCLUSIONES: Este estudio muestra que la escala PSI tiene una capacidad predictiva de mortalidad moderada, notablemente mejor que las escalas CURB-65 y SCAP. Se propone un nuevo modelo predictivo de mortalidad que mejora significativamente el rendimiento de estas escalas, siendo necesario verificar su validez externa.

[Relevance of clinical and serum parameters on severe urinary sepsis after renal obstruction.] / Importancia de los parámetros clínicos y analíticos de la sepsis grave en la uropatía obstructiva.

INTRODUCTION: Urosepsis is an underdiagnosed entity with high morbidity and mortality and significant associated costs. The delay in diagnosis leads to an increased risk of multiorgan failure and death. Although its prognosis is better than that of other sepsis, the mortality rate is 20 - 40%. OBJECTIVE: Describe the obstructive uropathy cases (OU) that are complicated by severe sepsis (SS) and identify early biomarkers of SS. MATERIAL AND METHODS: Observational and prospective study of 65 patients with urgent high OU. All patients were evaluated at three different times (0, 24 and 48 hours). An SS predictor model has been constructed and a multivariate risk analysis has been carried out. RESULTS: 64.61% (n=42) developed SS (NSS: n=13). The only statistically significant variables in the 3 moments evaluated and that obtained a good area under the curve [AUROC (>0.70)] were the elevation of neutrophils, procalcitonin, and decrease of bicarbonate. At the time of patient admission, the variable that best predicted SS was the elevation of procalcitonin (AUROC:0.919). SS risk factors (p<0.005) were the history of cancer immunosuppression, and/or urinary tract surgeries, complete UO and high blood values of lactate, potassium and decrease of bicarbonate. The potassium-lactate combination on admission predicted SS with a probability function of 0.805. CONCLUSIONS: There is an analytical profile maintained over the time characteristic of SS that allows anearly identification of patients with OU subsidiary of been complicated with SS.

INTRODUCCIÓN: La Sepsis urinaria obstructiva (SUO) es una entidad infradiagnosticada con una elevada morbimortalidad e importantes costes asociados. El retraso en su diagnóstico condiciona un mayor riesgo de fracaso multiorgánico y fallecimiento. Aunque su pronóstico es mejor que el de otros focos de sepsis, su mortalidad es del 20 - 40%. OBJETIVO: Describir los cuadros de uropatía obstructiva (UO) que se complican con sepsis grave (SG) e identificarlos biomarcadores diagnósticos de SG en la UOde forma precoz.MATERIAL Y MÉTODOS: Estudio observacional y prospectivo de 72 pacientes con UO alta ingresados de manera urgente en el Servicio de Urología del Hospital Clínico Universitario de Valladolid. Todos los pacientes del estudio fueron evaluados en tres momentos diferentes (0, 24 y 48 horas). Se ha creado un modelo predictor de SG y se ha realizado un análisis multivariante de riesgo. RESULTADOS: El 64,61% de los pacientes (n=42) desarrolló SG (NSG: n=13). Las únicas variables estadísticamente significativas en los tres momentos evaluados y que obtenían una buena área bajo la curva [AUROC (>0,70)] fueron la elevación de neutrófilos y procalcitonina y la disminución de bicarbonato. En el momento del ingreso la variable que mejor predecía SG fue la elevación de procalcitonina (AUROC: 0,919). Los factores de riesgo de SG (p<0,05) fueron los antecedentes de cáncer, la inmunosupresión y/o cirugías de vías urinarias, la UO completa y los valores elevados en sangre de lactato y potasio y la disminución del bicarbonato en la gasometría venosa. La combinación potasio-lactato al ingreso predecía SG con una función de probabilidad de 0,805. CONCLUSIONES: Existe un perfil analítico, mantenido en el tiempo, característico de SG que permite la identificación precoz de los pacientes con UO subsidiarios de complicarse con SG.

Importancia de los parámetros clínicos y analíticos de la sepsis grave en la uropatía obstructiva / Relevance of clinical and serum parameters on severe urinary sepsis after renal obstruction

INTRODUCCIÓN: La Sepsis urinaria obstructiva (SUO) es una entidad infradiagnosticada con una elevada morbimortalidad e importantes costes asociados. El retraso en su diagnóstico condiciona un mayor riesgo de fracaso multiorgánico y fallecimiento. Aunque su pronóstico es mejor que el de otros focos de sepsis, su mortalidad es del 20 - 40%. OBJETIVO: Describir los cuadros de uropatía obstructiva (UO) que se complican con sepsis grave (SG) e identificarlos biomarcadores diagnósticos de SG en la UOde forma precoz. MATERIAL Y MÉTODOS: Estudio observacional y prospectivo de 72 pacientes con UO alta ingresados de manera urgente en el Servicio de Urología del Hospital Clínico Universitario de Valladolid. Todos los pacientes del estudio fueron evaluados en tres momentos diferentes (0, 24 y 48 horas). Se ha creado un modelo predictor de SG y se ha realizado un análisis multivariante de riesgo. RESULTADOS: El 64,61% de los pacientes (n=42) desarrolló SG (NSG: n=13). Las únicas variables estadísticamente significativas en los tres momentos evaluados y que obtenían una buena área bajo la curva [AUROC (>0,70)] fueron la elevación de neutrófilos y procalcitonina y la disminución de bicarbonato. En el momento del ingreso la variable que mejor predecía SG fue la elevación de procalcitonina (AUROC: 0,919). Los factores de riesgo de SG (p < 0,05) fueron los antecedentes de cáncer, la inmunosupresión y/o cirugías de vías urinarias, la UO completa y los valores elevados en sangre de lactato y potasio y la disminución del bicarbonato en la gasometría venosa. La combinación potasio-lactato al ingreso predecía SG con una función de probabilidad de 0,805. CONCLUSIONES: Existe un perfil analítico, mantenido en el tiempo, característico de SG que permite la identificación precoz de los pacientes con UO subsidiarios de complicarse con SG

INTRODUCTION: Urosepsis is an underdiagnosed entity with high morbidity and mortality and significant associated costs. The delay in diagnosis leads to an increased risk of multiorgan failure and death. Although its prognosis is better than that of other sepsis, the mortality rate is 20 - 40%. OBJECTIVE: Describe the obstructive uropathy cases (OU) that are complicated by severe sepsis (SS) and identify early biomarkers of SS. MATERIAL AND METHODS: Observational and prospective study of 65 patients with urgent high OU. All patients were evaluated at three different times (0, 24 and 48 hours). An SS predictor model has been constructed and a multivariate risk analysis has been carried out. RESULTS: 64.61% (n=42) developed SS (NSS: n=13). The only statistically significant variables in the 3 moments evaluated and that obtained a good area under the curve [AUROC (>0.70)] were the elevation of neutrophils, procalcitonin, and decrease of bicarbonate. At the time of patient admission, the variable that best predicted SS was the elevation of procalcitonin (AUROC: 0.919). SS risk factors (p < 0.05) were the history of cancer, immunosuppression, and/or urinary tract surgeries, complete UO and high blood values of lactate, potassium and decrease of bicarbonate. The potassium-lactate combination on admission predicted SS with a probability function of 0.805. CONCLUSIONS: There is an analytical profile maintained over the time characteristic of SS that allows an early identification of patients with OU subsidiary of been complicated with SS

Improvement of fatigue in multiple sclerosis by physical exercise is associated to modulation of systemic interferon response.

Mechanisms underlying multiple sclerosis (MS) fatigue and the causes of the beneficial effect of exercise on this symptom are not clarified. Our aim was to evaluate gene expression profiles in MS patients who improved their fatigue status after an exercise program and to compare them with healthy controls (HC). Gene expression in whole blood was profiled at baseline in 7 HC and also in 7 fatigued-MS patients. Patients underwent an exercise program for 6 months, and their fatigue status and gene expression profiles were again analyzed. MS patients showed a significant activation of genes participating in the systemic interferon response in comparison with HC that disappeared at the end of the program. Our results provide a biological basis for the observed benefit of exercise in MS.

Severe 2009 A/H1N1v influenza in pregnant women in Spain.

OBJECTIVES: To describe the severity of the 2009 influenza A/H1N1v illness among pregnant women admitted to Spanish intensive care units. DESIGN AND PATIENTS: Prospective, observational, multicenter study conducted in 148 Spanish intensive care units. We reviewed demographic and clinical data from the Spanish Society of Intensive Care Medicine database reported from April 23, 2009, to February 15, 2010. We included women of reproductive age (15-44 yrs) with confirmed A/H1N1v infection admitted to intensive care units. MAIN RESULTS: Two hundred thirty-four women of reproductive age were admitted to intensive care units, 50 (21.4%) of them pregnant. Seven deaths were recorded in pregnant and 22 in nonpregnant women. Among intensive care unit admissions, there were no statistically significant differences between pregnant women and nonpregnant in Acute Physiology and Chronic Health Evaluation II, Sequential Organ Failure Assessment scores, chest x-rays, inotrope requirement, or need for mechanical ventilation or steroid therapy. Mortality risk was significantly associated with Acute Physiology and Chronic Health Evaluation II, Sequential Organ Failure Assessment, and obesity. Viral pneumonia was more frequent in pregnant women than in nonpregnant women, with an odds ratio (adjusted for asthma, time from onset influenza symptoms to hospital admission and obesity) of 4.9 (95% confidence interval: 1.4-17.2). The development of primary viral pneumonia in women of reproductive age appeared to be related to the time of commencement of antiviral treatment, the lowest rates being reported with initiation of antiviral therapy within 48 hrs of symptom onset (63.6% vs. 82.6%, p = .03). However, antiviral therapy was started within this time span in only 14% of pregnant women. CONCLUSIONS: More than 20% of women of reproductive age admitted to intensive care unit for pH1N1 infection were pregnant. Pregnancy was significantly associated with primary viral pneumonia. Pregnant women should receive prompt treatment with oseltamivir within 48 hrs of the onset of influenza symptoms.

Vigilancia de la gripe mediante diagnóstico molecular / Influenza surveillance by molecular diagnosis

Introducción: Nuestro objetivo ha sido evaluar la aplicaciónde técnicas moleculares en la vigilancia de gripe, así comodescribir características clínicas y epidemiológicas de los casosdiagnosticados en las temporadas 2007-2008 y 2008-2009.Métodos: se analizaron 183 frotis faríngeos procedentesde otros tantos pacientes remitidos al laboratorio de virologíapor la Red de Médicos Centinelas de Castilla y León, para el estudiode virus gripales mediante la técnica de shell-vial y RTPCRmúltiple capaz de detectar de forma simultánea, virus gripalesA, B, C, virus respiratorio sincitial A, B y adenovirus.Resultados: Mediante cultivo celular se aislaron 17 virusgripales A y 19 virus gripales B (19,7% del total). Por RT-PCRmúltiple, se detectaron 49 virus gripales A, 29 virus gripales B,un virus gripal C, 3 virus sincitiales tipo A u otro B y 6 adenovirus,(44,3% del total). Todos los virus gripales aislados por cultivocelular se detectaron mediante RT-PCR. Por RT-PCR se detectaron5 coinfecciones, que supuso un 6,25% decoinfecciones sobre las muestras positivas. La edad media delos pacientes fue de 29 años (SD=21,07). La proporción de mujeresy hombres correspondió al 43,7% y 56,3% respectivamente.El número de casos diagnosticados en relación a laedad sigue un patrón de correlación lineal negativa.Conclusiones: La RT-PCR se presenta como una herramientaútil para la vigilancia epidemiológica de la gripe permitiendoademás subtipar los virus gripales y detectar otros virusimplicados en procesos respiratorios de forma simultánea(AU)

Introduction: Our objective was to evaluate the applicationof molecular techniques in the surveillance ofinfluenza, and to describe clinical and epidemiologicalcharacteristics of cases diagnosed in 2007-2008 and2008-2009 seasons.Methods: We analyzed 183 pharyngeal swabs fromthe same number of patients referred to the virology laboratoryof the Sentinel Physician Network of Castilla yLeon, the study of influenza viruses by shell-vial techniqueand RT-PCR capable of detecting multiple Simultaneously,influenza virus A, B, C, respiratory syncytial virusA, B and adenovirus.Results: Using cell culture were isolated 17 influenzaA viruses and 19 influenza B viruses (19.7% of total). Bymultiple RT-PCR, was detected 49 influenza A virus, 29influenza B virus, an influenza virus C, 3 syncytial virustype A and other B and 6 adenoviruses (44.3% of total).All influenza viruses isolated in cell culture was detectedby RT-PCR. RT-PCR by 5 co-infections were detected,which represented a 6.25% of co-infections on the wholeof positive samples. The average age of patients was 29years (SD = 21.07). The proportion of women and menaccounted for 43.7% and 56.3% respectively. The numberof cases diagnosed in relation to age follows a patternof negative linear correlation.Conclusions: RT-PCR is revealed as an useful toolfor epidemiological surveillance of influenza, allowingalso to detect viral subtypes along with other viruses involvedin respiratory infections(AU9

[Influenza surveillance by molecular diagnosis]. / Vigilancia de la gripe mediante diagnóstico molecular.

INTRODUCTION: Our objective was to evaluate the application of molecular techniques in the surveillance of influenza, and to describe clinical and epidemiological characteristics of cases diagnosed in 2007-2008 and 2008-2009 seasons. METHODS: We analyzed 183 pharyngeal swabs from the same number of patients referred to the virology laboratory of the Sentinel Physician Network of Castilla y Leon, the study of influenza viruses by shell-vial technique and RT-PCR capable of detecting multiple Simultaneously, influenza virus A, B, C, respiratory syncytial virus A, B and adenovirus. RESULTS: Using cell culture were isolated 17 influenza A viruses and 19 influenza B viruses (19.7% of total). By multiple RT-PCR, was detected 49 influenza A virus, 29 influenza B virus, an influenza virus C, 3 syncytial virus type A and other B and 6 adenoviruses (44.3% of total). All influenza viruses isolated in cell culture was detected by RT-PCR. RT-PCR by 5 co-infections were detected, which represented a 6.25% of co-infections on the whole of positive samples. The average age of patients was 29 years (SD = 21.07). The proportion of women and men accounted for 43.7% and 56.3% respectively. The number of cases diagnosed in relation to age follows a pattern of negative linear correlation. CONCLUSIONS: RT-PCR is revealed as an useful tool for epidemiological surveillance of influenza, allowing also to detect viral subtypes along with other viruses involved in respiratory infections.