Using Machine Learning to Determine a Suitable Patient Population for Anakinra for the Treatment of COVID‐19 Under the Emergency Use Authorization

• DOI: 10.1002/cpt.3191
• Publication Date: 2024-02-13T09:14:12Z
• Authors: Qi Liu; Raj Nair; Ruihao Huang; Hao Zhu; Austin Anderson; Ozlem Belen; Van Tran; Rebecca Chiu; Karen Higgins; Jianmeng Chen; Lei He; Suresh Doddapaneni; Shiew‐Mei Huang; Nikolay P. Nikolov; Issam Zineh
• Keywords: SuPAR

A randomized, double‐blind, placebo‐controlled study (SAVEMORE trial) provided data to support an Emergency Use Authorization (EUA) of anakinra in hospitalized adults with positive results direct severe acute respiratory syndrome‐coronavirus 2 viral testing pneumonia requiring supplemental oxygen (low‐ or high‐flow oxygen) who are at risk progressing failure and likely have elevated plasma soluble urokinase plasminogen activator receptor (suPAR). Currently, the suPAR assay is not commercially available United States. An alternative method was needed identify patients that best reflect population clinical trial selected based on level ≥ 6 ng/mL baseline. machine learning approach from SAVEMORE used develop a scoring rule External validation conducted different (SAVE). This high predictive value, specificity, reasonable sensitivity, biological relevance expected As such, it included EUA fall within authorized for whom known potential benefits outweigh risks anakinra.