Thinking out of the box: revisiting health surveillance based on medical records

Nenhuma Miniatura disponível
Citações na Scopus
0
Tipo de produção
article
Data de publicação
2023
Título da Revista
ISSN da Revista
Título do Volume
Editora
CAMBRIDGE UNIVERSITY PRESS
Autores
SAMPAIO, V. S.
LOPES, R.
OZAHATA, M. C.
NAKAYA, H. I.
SOUSA, E.
ARAúJO, J. D.
BRAGATTE, M. A. S.
BRITO, A. F.
GRESPAN, R. M. Z.
CAPUANI, M. L. D.
Citação
ANTIMICROBIAL STEWARDSHIP AND HEALTHCARE EPIDEMIOLOGY, v.3, n.1, article ID e185, p, 2023
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
Despite the considerable advances in the last years, the health information systems for health surveillance still need to overcome some critical issues so that epidemic detection can be performed in real time. For instance, despite the efforts of the Brazilian Ministry of Health (MoH) to make COVID-19 data available during the pandemic, delays due to data entry and data availability posed an additional threat to disease monitoring. Here, we propose a complementary approach by using electronic medical records (EMRs) data collected in real time to generate a system to enable insights from the local health surveillance system personnel. As a proof of concept, we assessed data from São Caetano do Sul City (SCS), São Paulo, Brazil. We used the fever term as a sentinel event. Regular expression techniques were applied to detect febrile diseases. Other specific terms such as malaria, dengue, Zika, or any infectious disease were included in the dictionary and mapped to fever. Additionally, after tokenizing, we assessed the frequencies of most mentioned terms when fever was also mentioned in the patient complaint. The findings allowed us to detect the overlapping outbreaks of both COVID-19 Omicron BA.1 subvariant and Influenza A virus, which were confirmed by our team by analyzing data from private laboratories and another COVID-19 public monitoring system. Timely information generated from EMRs will be a very important tool to the decision-making process as well as research in epidemiology. Quality and security on the data produced is of paramount importance to allow the use by health surveillance systems.
Palavras-chave
Referências
  1. Coelho Neto G.C., Chioro A., Afinal, quantos Sistemas de Informação em Saúde de base nacional existem no Brasil?, Cad Saúde Públ, 37, (2021)
  2. Jorge M., Laurenti R., Gotlieb S., (2010)
  3. Bastos L.S., Economou T., Gomes M.F.C., Et al., A modeling approach for correcting reporting delays in disease surveillance data, Stat Med, 38, pp. 4363-4377, (2019)
  4. Ludwick D.A., Doucette J., Adopting electronic medical records in primary care: Lessons learned from health information systems implementation experience in seven countries, Int J Med Inf, 78, pp. 22-31, (2009)
  5. Leal F.E., Mendes-Correa M.C., Buss L.F., Et al., Clinical features and natural history of the first 2073 suspected COVID-19 cases in the Corona São Caetano primary care programme: a prospective cohort study, BMJ Open, 11, (2021)
  6. Luz F.E.D., Santos B.R.M.D., Sabino W., Comparative study on mortality due to cardiovascular diseases in São Caetano do Sul, São Paulo, Brazil, between 1980 and 2010, Ciênc Saúde Coletiva, 22, pp. 161-168, (2017)
  7. Mullen L., Benoit K., Keyes O., Selivanov D., Arnold J., Fast, consistent tokenization of natural language text, J Open Source Softw, 3, (2018)
  8. Nandwani P., Verma R., A review on sentiment analysis and emotion detection from text, Soc Netw Anal Min, 11, (2021)
  9. (2022)
  10. Kruse C.S., Stein A., Thomas H., Kaur H., The use of electronic health records to support population health: a systematic review of the literature, J Med Syst, 42, (2018)
  11. Beard L., Schein R., Morra D., Wilson K., Keelan J., The challenges in making electronic health records accessible to patients, J Am Med Inform Assoc, 19, pp. 116-120, (2012)