Your browser doesn't support javascript.
Personalized survival probabilities for SARS-CoV-2 positive patients by explainable machine learning.
Zucco, Adrian G; Agius, Rudi; Svanberg, Rebecka; Moestrup, Kasper S; Marandi, Ramtin Z; MacPherson, Cameron Ross; Lundgren, Jens; Ostrowski, Sisse R; Niemann, Carsten U.
  • Zucco AG; PERSIMUNE Center of Excellence, Rigshospitalet, Copenhagen, Denmark. adrian.gabriel.zucco@regionh.dk.
  • Agius R; Department of Hematology, Rigshospitalet, Copenhagen, Denmark.
  • Svanberg R; Department of Hematology, Rigshospitalet, Copenhagen, Denmark.
  • Moestrup KS; PERSIMUNE Center of Excellence, Rigshospitalet, Copenhagen, Denmark.
  • Marandi RZ; PERSIMUNE Center of Excellence, Rigshospitalet, Copenhagen, Denmark.
  • MacPherson CR; PERSIMUNE Center of Excellence, Rigshospitalet, Copenhagen, Denmark.
  • Lundgren J; PERSIMUNE Center of Excellence, Rigshospitalet, Copenhagen, Denmark.
  • Ostrowski SR; Department of Clinical Medicine, University of Copenhagen, Copenhagen, Denmark.
  • Niemann CU; Department of Clinical Immunology, Rigshospitalet, Copenhagen, Denmark. Sisse.Rye.Ostrowski@regionh.dk.
Sci Rep ; 12(1): 13879, 2022 08 16.
Article in English | MEDLINE | ID: covidwho-1991668
ABSTRACT
Interpretable risk assessment of SARS-CoV-2 positive patients can aid clinicians to implement precision medicine. Here we trained a machine learning model to predict mortality within 12 weeks of a first positive SARS-CoV-2 test. By leveraging data on 33,938 confirmed SARS-CoV-2 cases in eastern Denmark, we considered 2723 variables extracted from electronic health records (EHR) including demographics, diagnoses, medications, laboratory test results and vital parameters. A discrete-time framework for survival modelling enabled us to predict personalized survival curves and explain individual risk factors. Performance on the test set was measured with a weighted concordance index of 0.95 and an area under the curve for precision-recall of 0.71. Age, sex, number of medications, previous hospitalizations and lymphocyte counts were identified as top mortality risk factors. Our explainable survival model developed on EHR data also revealed temporal dynamics of the 22 selected risk factors. Upon further validation, this model may allow direct reporting of personalized survival probabilities in routine care.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: SARS-CoV-2 / COVID-19 Type of study: Observational study / Prognostic study Limits: Humans Language: English Journal: Sci Rep Year: 2022 Document Type: Article Affiliation country: S41598-022-17953-y

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: SARS-CoV-2 / COVID-19 Type of study: Observational study / Prognostic study Limits: Humans Language: English Journal: Sci Rep Year: 2022 Document Type: Article Affiliation country: S41598-022-17953-y