Courtney J Bearnot, Eta N Mbong, Rigo F Muhayangabo, Razia Laghari, Kelsey Butler, Monique Gainey, Shiromi M Perera, Ian C Michelow, Oliver Y Tang, Adam C Levine, Andrés Colubri, Adam R Aluisio

Derivation and Internal Validation of a Mortality Prognostication Machine Learning Model in Ebola Virus Disease Using Iterative Point-of-Care Biomarkers

  • Infectious Diseases
  • Oncology
Save to CiteDrive Show PDF

Abstract Background Although multiple prognostic models for Ebola Virus Disease (EVD) mortality exist, few incorporate biomarkers and none has used longitudinal point-of-care (POC) serum testing throughout Ebola Treatment Center (ETC) care. Methods This retrospective study evaluated adult EVD patients during the tenth outbreak in the Democratic Republic of Congo. Ebola virus RT-PCR cycle threshold (Ct) and POC serum biomarker values were collected throughout ETC treatment. Four iterative prognostic mortality machine learning models were created. The base model used age and admission Ct as predictors. Ct and biomarkers from treatment days one and two (D1,2), three and four (D3,4) and five and six (D5,6) associated with mortality, were iteratively added to the model to yield mortality risk estimates. Receiver operating characteristic curves for each iteration provided time-period specific Area Under Curve (AUC) with 95% confidence intervals (CIs). Results Of 310 EVD-positive cases, mortality occurred in 46.5%. Biomarkers predictive of mortality were elevated creatinine kinase, aspartate aminotransferase, blood urea nitrogen (BUN), alanine aminotransferase, and potassium, and low albumin during D1,2, elevated c-reactive protein (CRP), BUN, and potassium during D3,4, and elevated CRP and BUN during D5,6. The AUC substantially improved with each iteration: base model 0.74 (95% CI 0.69–0.80), D1,2 0.84 (95% CI 0.73–0.94), D3,4 0.94 (95% CI 0.88–1.0), and D5,6 0.96 (95% CI 0.90–1.0). Conclusions This is the first study to utilize iterative POC biomarkers to derive dynamic prognostic mortality models. This novel approach demonstrates that utilizing biomarkers drastically improved prognostication up to six days into patient care.

Need a simple solution for managing your BibTeX entries? Explore CiteDrive!

  • Web-based, modern reference management
  • Collaborate and share with fellow researchers
  • Integration with Overleaf
  • Comprehensive BibTeX/BibLaTeX support
  • Save articles and websites directly from your browser
  • Search for new articles from a database of tens of millions of references
Try out CiteDrive

More from our Archive