Machine learning in predicting severe acute respiratory infection outbreaks / Aprendizado de máquina na previsão de surtos de síndrome respiratória aguda grave / Aprendizaje automático en la predicción de brotes de síndrome respiratorio agudo grave

Abstract: Severe acute respiratory infection (SARI) outbreaks occur annually, with seasonal peaks varying among geographic regions. Case notification is important to prepare healthcare networks for patient attendance and hospitalization. Thus, health managers need adequate resource planning tools for SARI seasons. This study aims to predict SARI outbreaks based on models generated with machine learning using SARI hospitalization notification data. In this study, data from the reporting of SARI hospitalization cases in Brazil from 2013 to 2020 were used, excluding SARI cases caused by COVID-19. These data were prepared to feed a neural network configured to generate predictive models for time series. The neural network was implemented with a pipeline tool. Models were generated for the five Brazilian regions and validated for different years of SARI outbreaks. By using neural networks, it was possible to generate predictive models for SARI peaks, volume of cases per season, and for the beginning of the pre-epidemic period, with good weekly incidence correlation (R2 = 0.97; 95%CI: 0.95-0.98, for the 2019 season in the Southeastern Brazil). The predictive models achieved a good prediction of the volume of reported cases of SARI; accordingly, 9,936 cases were observed in 2019 in Southern Brazil, and the prediction made by the models showed a median of 9,405 (95%CI: 9,105-9,738). The identification of the period of occurrence of a SARI outbreak is possible using predictive models generated with neural networks and algorithms that employ time series.

Resumo: Surtos de síndrome respiratória aguda grave (SRAG) ocorrem anualmente, com picos sazonais variando entre regiões geográficas. A notificação dos casos é importante para preparar as redes de atenção à saúde para o atendimento e internação dos pacientes. Portanto, os gestores de saúde precisam ter ferramentas adequadas de planejamento de recursos para as temporadas de SRAG. Este estudo tem como objetivo prever surtos de SRAG com base em modelos gerados com aprendizado de máquina usando dados de internação por SRAG. Foram incluídos dados sobre casos de hospitalização por SRAG no Brasil de 2013 a 2020, excluindo os casos causados pela COVID-19. Estes dados foram preparados para alimentar uma rede neural configurada para gerar modelos preditivos para séries temporais. A rede neural foi implementada com uma ferramenta de pipeline. Os modelos foram gerados para as cinco regiões brasileiras e validados para diferentes anos de surtos de SRAG. Com o uso de redes neurais, foi possível gerar modelos preditivos para picos de SRAG, volume de casos por temporada e para o início do período pré-epidêmico, com boa correlação de incidência semanal (R2 = 0,97; IC95%: 0,95-0,98, para a temporada de 2019 na Região Sudeste). Os modelos preditivos obtiveram uma boa previsão do volume de casos notificados de SRAG; dessa forma, foram observados 9.936 casos em 2019 na Região Sul, e a previsão feita pelos modelos mostrou uma mediana de 9.405 (IC95%: 9.105-9.738). A identificação do período de ocorrência de um surto de SRAG é possível por meio de modelos preditivos gerados com o uso de redes neurais e algoritmos que aplicam séries temporais.

Resumen: Brotes de síndrome respiratorio agudo grave (SRAG) ocurren todos los años, con picos estacionales que varían entre regiones geográficas. La notificación de los casos es importante para preparar las redes de atención a la salud para el cuidado y hospitalización de los pacientes. Por lo tanto, los gestores de salud deben tener herramientas adecuadas de planificación de recursos para las temporadas de SRAG. Este estudio tiene el objetivo de predecir brotes de SRAG con base en modelos generados con aprendizaje automático utilizando datos de hospitalización por SRAG. Se incluyeron datos sobre casos de hospitalización por SRAG en Brasil desde 2013 hasta 2020, salvo los casos causados por la COVID-19. Se prepararon estos datos para alimentar una red neural configurada para generar modelos predictivos para series temporales. Se implementó la red neural con una herramienta de canalización. Se generaron los modelos para las cinco regiones brasileñas y se validaron para diferentes años de brotes de SRAG. Con el uso de redes neurales, se pudo generar modelos predictivos para los picos de SRAG, el volumen de casos por temporada y para el inicio del periodo pre-epidémico, con una buena correlación de incidencia semanal (R2 = 0,97; IC95%: 0,95-0,98, para la temporada de 2019 en la Región Sudeste). Los modelos predictivos tuvieron una buena predicción del volumen de casos notificados de SRAG; así, se observaron 9.936 casos en 2019 en la Región Sur, y la predicción de los modelos mostró una mediana de 9.405 (IC95%: 9.105-9.738). La identificación del periodo de ocurrencia de un brote de SRAG es posible a través de modelos predictivos generados con el uso de redes neurales y algoritmos que aplican series temporales.

SARS-CoV-2 laboratory surveillance during the first year of the COVID-19 pandemic in southern Brazil

ABSTRACT Background: Brazil has one of the highest numbers of COVID-19 cases and deaths. Rio Grande do Sul (RS) in southern Brazil is one of the leading states in terms of case numbers. As part of the national public health network, the State Central Laboratory (LACEN-RS) changed its routine in 2020 to focus on the diagnosis of COVID-19. This study evaluated the laboratory surveillance of COVID-19 suspected cases analyzed at the LACEN-RS in 2020. Methods: Viral detection was performed using RT-qPCR in samples from patients with respiratory infection who met the study criteria. Viral RNA was isolated using commercial manual kits or automated extractors, and SARS-CoV-2 RT-qPCR was performed using the Bio-Manguinhos/Rio de Janeiro, IBMP/Paraná, or Allplex 2019-nCoV assay. In total, 360 representative SARS-CoV-2 samples were sequenced using the Illumina platform. Results: In total, 31,197 of 107,578 (positivity rate = 29%) tested positive for SARS-CoV-2. The number of RT-qPCR tests performed per month followed the COVID-19 epidemic curve observed for the state, with peaks in July-August and December. Females accounted for 63% of the samples, whereas the positivity rate was higher among males (33.1% males vs. 26.5% females). The positivity rate was higher in adults aged 50-79 years compared to the overall positivity rate. The majority of cases were observed in the capital, Porto Alegre, and the metropolitan region. Ten distinct lineages were identified, with B.1.1.28, B.1.1.33, and P.2 being the most frequent. Conclusions: Here, we describe laboratory surveillance of COVID-19 to identify priorities for epidemiological surveillance actions in RS.

Epidemiological investigation reveals local transmission of SARS-CoV-2 lineage P. 1 in Southern Brazil / Investigação epidemiológica revela transmissão local da variante P. 1 do SARS-CoV-2 no Sul do Brasil / Una investigación epidemiológica revela la transmisión local de la variante P. 1 del SARS-CoV-2 en el sur de Brasil

Since its detection in December of 2020, the SARS-CoV2 lineage P.1, descendent of B.1.1.28 lineage, has been identified in several places in Brazil and abroad. This Variant of Concern was considered highly prevalent in Northern Brazil and now is rapidly widening its geographical range. Here, we present epidemiological and genomic information of the first case of P1 lineage in Rio Grande do Sul state, in a patient without reported travel history and a tracked transmission chain. These findings occurred in a tourist destination representing an important hub receiving tourists from diverse places.(AU)

Desde a sua detecção em dezembro de 2020, a linhagem P.1 do SARS-CoV2, descendente da linhagem B.1.1.28, foi identificada em diversos locais no Brasil e no mundo. Essa variante de preocupação era considerada altamente frequente no Norte do Brasil e agora está ampliando rapidamente sua distribuição geográfica. Aqui, apresentamos informações epidemiológicas e genômicas do primeiro caso da linhagem P.1 no Rio Grande do Sul em um paciente sem histórico de viagens relatado e com cadeia de transmissão identificada. Esses achados ocorreram em um destino turístico que representa um importante pólo de recepção de turistas de diversas localidades.(AU)

Desde su detección en diciembre de 2020, del linaje P.1 del SARS-CoV2, derivada de la B.1.1.28, hay sido ampliamente identificada en Brasil y en todo el mundo. Esta variante preocupante es muy frecuente en el norte de Brasil y ahora está ampliando rápidamente su distribución geográfica. Aquí, presentamos información epidemiológica y genómica del primer caso de P.1 en Rio Grande do Sul en un paciente sin antecedentes de viaje y con una cadena de transmisión identificada. Estos datos se han obtenido en un destino turístico que representa un importante centro de acogida de turistas de diferentes lugares.(AU)

More than just a common cold: endemic coronaviruses OC43, HKU1, NL63, and 229E associated with severe acute respiratory infection and fatality cases among healthy adults

Respiratory viral infection can cause severe disease and hospitalization, especially among children, the elderly, and patients with comorbidities. In Brazil, the official surveillance system of severe acute respiratory infection (SARI) investigates influenza A (IAV) and B (IBV) viruses, respiratory syncytial virus (RSV), adenovirus (HAdV), and parainfluenza viruses (hPIV 1­3). In Rio Grande do Sul (RS), Brazil, many fatalities associated with SARI between 2013 and 2017 occurred among patients without underlying diseases and for whom the causative agent had not been identified using official protocols. This cross­sectional study analyzed the presence of coronaviruses (HCoV), bocavirus (HBoV), metapneumovirus (hMPV), and rhinovirus in patients who died of SARI despite not having comorbidities, and that were negative for IAV, IBV, RSV, HAdV, and hPIV. Nasopharyngeal aspirates/swabs from patients were used for nucleic acid extraction. The presence of HCoVs OC43, HKU1, NL63, and 229E; HBoV; hMPV; and rhinovirus was assessed by quantitative reverse transcription­polymerase chain reaction. Clinical data were also analyzed. Between 2013 and 2017, 16 225 cases of SARI were reported in RS; 9.8% of the patients died; 20% of all fatal cases were patients without comorbidities and for whom no pathogen was detected using standard protocols. Analysis of 271 of these cases identified HCoV in nine cases; HBoV, hMPV, and rhinovirus were detected in 3, 3, and 10 cases, respectively. Of note, patients infected with HCoV were adults. Results reinforce the importance of including coronaviruses in diagnostic panels used by official surveillance systems because besides their pandemic potential, endemic HCoVs are associated to severe disease in healthy adults.

Temporal dynamics of human mastadenovirus species in cases of respiratory illness in southern Brazil

Human mastadenovirus (HAdV) genus is related to several diseases, among them upper and lower respiratory tract illness. HAdV species B, C, D, and E are mainly associated with respiratory infections. The goal of this work was to identify the HAdV species associated with respiratory infections in hospitalized patients from southern Brazil. Samples were collected from 1996 to 2004 and 2011 to 2017. During this period, 28,524 samples were collected, and 9983 were positive for respiratory viruses, being 435 for HAdV. From these 435 samples, 57 were selected for characterization of HAdV species. For screening the presence of HAdV, a partial sequence of the DNA polymerase gene (DNApol gene) was amplified by nested PCR. Partial nucleotide sequencing was performed in positive samples, and HAdV (DNApol gene) was detected in 53 samples: species B (28;49.1%), C (16;8.0%), D (2; 3.5%), E (5; 8.7%), and untyped (2; 3.5%). Specie D was found only in 2017 and specie E in 2011 and 2012. The age of the patients ranged from < 1 to 81 years old, and 62.3%were male. No relationship between gender orage and identified HAdV species were observed. In addition, in the period of 2013­2017, 18 samples from patients who died were analyzed: 11 were related to species B, 4 to C, and 2 to D and 1 remained untyped. Circulation of HAdV species D and Evaried over the years, but species B and C were present throughout the evaluated period. In addition, respiratory infections by HAdVaffect elderly and children mainly. (AU)

Human metapneumovirus in Southern Brazil

INTRODUCTION Infections caused by respiratory viruses are important problems worldwide, especially in children. Human metapneumovirus (hMPV) is a respiratory pathogen and causes severe infections with nonspecific symptoms. This study reports the hMPV occurrence and dissemination in southern Brazil and compares the frequency of occurrence of this virus and the human respiratory syncytial virus (hRSV) in the epidemiological weeks in a three-year period (2009-2011). METHODS: In total, 545 nasopharyngeal (NP) specimens from individuals with Severe Acute Respiratory Syndrome (SARS) who were negative for other seven respiratory viruses were analyzed for the presence of hMPV. Human metapneumovirus was detected by direct immunofluorescence and real-time reverse transcription polymerase chain reaction. RESULTS: hMPV was detected in 109 patients from the main geographic regions of the southernmost state of Brazil, presenting similar overall prevalence in males (46.8%) and females (53.2%). Among children who were less than six years old, hMPV was detected in 99 samples of all age groups, with a higher frequency in infants who were less than one year old (45.7%) compared to all other age groups until six years. hMPV and hRSV infection occurred in almost the same epidemiological weeks (EWs) of each year, with peaks of incidence between EW 31/37 and EW 26/38 for the years 2009 and 2011, respectively. hMPV was further detected in several cases of SARS and it was the only virus detected in three deaths. CONCLUSIONS These findings indicate that hMPV is in circulation in southern Brazil and highlight the importance of diagnosing hMPV for influenza-like illness in the population. (AU)