Your browser doesn't support javascript.
Predicting the outcome for COVID-19 patients by applying time series classification to electronic health records.
Rodrigues, Davi Silva; Nastri, Ana Catharina S; Magri, Marcello M; Oliveira, Maura Salaroli de; Sabino, Ester C; Figueiredo, Pedro H M F; Levin, Anna S; Freire, Maristela P; Harima, Leila S; Nunes, Fátima L S; Ferreira, João Eduardo.
  • Rodrigues DS; Laboratory of Computer Applications for Health Care, School of Arts, Sciences and Humanities, Universidade de São Paulo, São Paulo, Brazil. davisilvarodrigues@gmail.com.
  • Nastri ACS; Division of Infectious Diseases, Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
  • Magri MM; Division of Infectious Diseases, Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
  • Oliveira MS; Department of Infection Control, Hospital das Clínicas, Universidade de São Paulo, São Paulo, Brazil.
  • Sabino EC; Division of Infectious Diseases, Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
  • Figueiredo PHMF; Núcleo de Vigilância Epidemiológica, Hospital das Clínicas, Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
  • Levin AS; Division of Infectious Diseases, Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
  • Freire MP; Department of Infection Control, Hospital das Clínicas, Universidade de São Paulo, São Paulo, Brazil.
  • Harima LS; Department of Infection Control, Hospital das Clínicas, Universidade de São Paulo, São Paulo, Brazil.
  • Nunes FLS; Clinical Director's Office, Hospital das Clínicas, Faculdade de Medicina, Universidade de São Paulo, São Paulo, Brazil.
  • Ferreira JE; Laboratory of Computer Applications for Health Care, School of Arts, Sciences and Humanities, Universidade de São Paulo, São Paulo, Brazil.
BMC Med Inform Decis Mak ; 22(1): 187, 2022 07 17.
Article in English | MEDLINE | ID: covidwho-1938312
ABSTRACT

BACKGROUND:

COVID-19 caused more than 622 thousand deaths in Brazil. The infection can be asymptomatic and cause mild symptoms, but it also can evolve into a severe disease and lead to death. It is difficult to predict which patients will develop severe disease. There are, in the literature, machine learning models capable of assisting diagnose and predicting outcomes for several diseases, but usually these models require laboratory tests and/or imaging.

METHODS:

We conducted a observational cohort study that evaluated vital signs and measurements from patients who were admitted to Hospital das Clínicas (São Paulo, Brazil) between March 2020 and October 2021 due to COVID-19. The data was then represented as univariate and multivariate time series, that were used to train and test machine learning models capable of predicting a patient's outcome.

RESULTS:

Time series-based machine learning models are capable of predicting a COVID-19 patient's outcome with up to 96% general accuracy and 81% accuracy considering only the first hospitalization day. The models can reach up to 99% sensitivity (discharge prediction) and up to 91% specificity (death prediction).

CONCLUSIONS:

Results indicate that time series-based machine learning models combined with easily obtainable data can predict COVID-19 outcomes and support clinical decisions. With further research, these models can potentially help doctors diagnose other diseases.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Type of study: Cohort study / Experimental Studies / Observational study / Prognostic study Limits: Humans Country/Region as subject: South America / Brazil Language: English Journal: BMC Med Inform Decis Mak Journal subject: Medical Informatics Year: 2022 Document Type: Article Affiliation country: S12911-022-01931-5

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: COVID-19 Type of study: Cohort study / Experimental Studies / Observational study / Prognostic study Limits: Humans Country/Region as subject: South America / Brazil Language: English Journal: BMC Med Inform Decis Mak Journal subject: Medical Informatics Year: 2022 Document Type: Article Affiliation country: S12911-022-01931-5