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

## TL;DR

The study creates a machine learning model to predict Ebola mortality using blood test results collected over six days of treatment.

## Contribution

The first dynamic mortality model for Ebola using iterative point-of-care biomarkers, improving prediction accuracy over time.

## Key findings

- Biomarkers like creatinine kinase and C-reactive protein improved mortality prediction when added to the model over time.
- The model's accuracy increased from 0.74 to 0.96 as more biomarker data was incorporated.
- The model extends mortality prediction up to day 6 of patient care, surpassing previous models.

## Abstract

Although multiple prognostic models exist for Ebola virus disease mortality, few incorporate biomarkers, and none has used longitudinal point-of-care serum testing throughout Ebola treatment center care.

This retrospective study evaluated adult patients with Ebola virus disease during the 10th outbreak in the Democratic Republic of Congo. Ebola virus cycle threshold (Ct; based on reverse transcriptase polymerase chain reaction) and point-of-care serum biomarker values were collected throughout Ebola treatment center care. Four iterative machine learning models were created for prognosis of mortality. The base model used age and admission Ct as predictors. Ct and biomarkers from treatment days 1 and 2, days 3 and 4, and days 5 and 6 associated with mortality were iteratively added to the model to yield mortality risk estimates. Receiver operating characteristic curves for each iteration provided period-specific areas under curve with 95% CIs.

Of 310 cases positive for Ebola virus disease, mortality occurred in 46.5%. Biomarkers predictive of mortality were elevated creatinine kinase, aspartate aminotransferase, blood urea nitrogen (BUN), alanine aminotransferase, and potassium; low albumin during days 1 and 2; elevated C-reactive protein, BUN, and potassium during days 3 and 4; and elevated C-reactive protein and BUN during days 5 and 6. The area under curve substantially improved with each iteration: base model, 0.74 (95% CI, .69–.80); days 1 and 2, 0.84 (95% CI, .73–.94); days 3 and 4, 0.94 (95% CI, .88–1.0); and days 5 and 6, 0.96 (95% CI, .90–1.0).

This is the first study to utilize iterative point-of-care biomarkers to derive dynamic prognostic mortality models. This novel approach demonstrates that utilizing biomarkers drastically improved prognostication up to 6 days into patient care.

This is the first study to utilize iterative point-of-care biomarkers to derive a dynamic prognostic mortality model for Ebola virus disease. This model overcomes the limitations of previous models by extending prognostication to day 6 of patient care.