Estimating underdiagnosis of COVID-19 with nowcasting and machine learning.

OBJECTIVE: To analyze the underdiagnosis of COVID-19 through nowcasting with machine learning in a Southern Brazilian capital city. METHODS: Observational ecological design and data from 3916 notified cases of COVID-19 from April 14th to June 2nd, 2020 in Florianópolis, Brazil. A machine-learning algorithm was used to classify cases that had no diagnosis, producing the nowcast. To analyze the underdiagnosis, the difference between data without nowcasting and the median of the nowcasted projections for the entire period and for the six days from the date of onset of symptoms were compared. RESULTS: The number of new cases throughout the entire period without nowcasting was 389. With nowcasting, it was 694 (95%CI 496-897). During the six-day period, the number without nowcasting was 19 and 104 (95%CI 60-142) with nowcasting. The underdiagnosis was 37.29% in the entire period and 81.73% in the six-day period. The underdiagnosis was more critical in the six days from the date of onset of symptoms to diagnosis before the data collection than in the entire period. CONCLUSION: The use of nowcasting with machine learning techniques can help to estimate the number of new disease cases.

Estimating underdiagnosis of COVID-19 with nowcasting and machine learning / Estimativa do subdiagnóstico de COVID-19 utilizando machine learning e nowcasting

ABSTRACT: Objective: To analyze the underdiagnosis of COVID-19 through nowcasting with machine learning in a Southern Brazilian capital city. Methods: Observational ecological design and data from 3916 notified cases of COVID-19 from April 14th to June 2nd, 2020 in Florianópolis, Brazil. A machine-learning algorithm was used to classify cases that had no diagnosis, producing the nowcast. To analyze the underdiagnosis, the difference between data without nowcasting and the median of the nowcasted projections for the entire period and for the six days from the date of onset of symptoms were compared. Results: The number of new cases throughout the entire period without nowcasting was 389. With nowcasting, it was 694 (95%CI 496-897). During the six-day period, the number without nowcasting was 19 and 104 (95%CI 60-142) with nowcasting. The underdiagnosis was 37.29% in the entire period and 81.73% in the six-day period. The underdiagnosis was more critical in the six days from the date of onset of symptoms to diagnosis before the data collection than in the entire period. Conclusion: The use of nowcasting with machine learning techniques can help to estimate the number of new disease cases.

RESUMO: Objetivo: Analisar o subdiagnóstico da COVID-19 por meio de nowcasting com machine learning em uma capital do sul do Brasil. Métodos: Estudo ecológico observacional utilizando dados de 3.916 casos notificados de COVID-19 de 14 de abril a 2 de junho de 2020 em Florianópolis, Brasil. O algoritmo de machine learning foi usado para classificar os casos que ainda não tinham diagnóstico, produzindo o nowcasting. Para analisar o subdiagnóstico, foi comparada a diferença entre os dados sem nowcasting e a mediana das projeções com nowcasting para todo o período e para os seis dias a partir da data de início dos sintomas. Resultados: O número de novos casos sem nowcasting durante todo o período foi de 389, com nowcasting foi de 694 (IC95% 496-897). No período de seis dias, o número sem nowcasting foi de 19 e 104 (IC95% 60-142) com nowcasting. O subdiagnóstico foi de 37,29% em todo o período e 81,73% no período de seis dias. O subdiagnóstico foi mais crítico em seis dias, desde a data do início dos sintomas até o diagnóstico antes da coleta de dados, do que em todo o período. Conclusão: O uso de nowcasting com técnicas de machine learning pode ajudar a estimar o número de novos casos da doença.

Adequacy of risk classification protocols for COVID-19 to WHO guidelines: a proposed instrument / Adequação de protocolos de classificação de risco para COVID-19 às orientações da OMS: uma proposta de instrumento

Objective: This article proposes to create an instrument to analyze the adequacy of risk classification protocols for COVID-19 to the guidelines of the World Health Organization (WHO) and analyzes the protocol used by Santa Catarina. Method: The descriptive research was composed of three parts: 1) extraction of information regarding risk analysis and COVID-19 from WHO documents; 2) elaboration of an instrument to analyze the adequacy of risk classification protocols for COVID-19 to the WHO guidelines; 3) application of the instrument to the protocol used in the state of Santa Catarina. Results: Five WHO documents were reviewed. The built instrument included five dimensions: risk assessment itself, exposure assessment, context assessment, risk characterization and reliability. Partial information regarding the risk assessment itself and reliability was found in the Santa Catarina government protocol. No information was found regarding the other dimensions. Discussion: The mismatch between the matrix used by the state of Santa Catarina and the WHO risk analysis guidelines is huge. Thus, without an adequate analysis of these factors, the entire strategy for implementing actions can be compromised, exposing the population of the state to risk.

Objetivo: Este artigo propõe criar um instrumento para analisar a adequação de protocolos de classificação de risco para COVID-19 às orientações da Organização Mundial de Saúde (OMS) e analisa o protocolo utilizado por Santa Catarina. Método: A pesquisa descritiva foi composta de três partes: 1) extração de informações concernentes à análise de risco e à COVID-19 dos documentos da OMS; 2) elaboração de instrumento para análise da adequação de protocolos de classificação de risco para COVID-19 às orientações da OMS; 3) aplicação do instrumento ao protocolo utilizado no estado de Santa Catarina. Resultados: Cinco documentos da OMS foram revistos. O instrumento construído contemplou cinco dimensões: avaliação do risco em si, avaliação da exposição, avaliação do contexto, caracterização do risco e confiabilidade. Informações parciais com relação à avaliação do risco em si e à confiabilidade foram encontradas no protocolo do governo catarinense. Não foram encontradas informações com relação às demais dimensões. Discussão: O desencontro entre a matriz utilizada pelo estado de Santa Catarina e as orientações para análise de risco da OMS são grandes. Assim, sem uma análise adequada desses fatores toda a estratégia de implementação de ações pode ser comprometida, expondo a população do estado a risco.