AI drug company BenevolentAI revealed on Thursday that the data published in Eli Lilly's Phase 3 randomised, double-blind, placebo-controlled study (COV-BARRIER) shows the largest clinical effect reported to date for a reduction in mortality in COVID-19 patients.

On 4 February 2020, BenevolentAI researchers published the hypothesis of COV-BARRIER in The Lancet upon identification of Baricitinib as a potential treatment for COVID-19. The ACTT-2 clinical trial is reportedly the first AI-derived hypothesis for a COVID-19 treatment.

Based on COV-BARRIER trial, the US FDA granted emergency use authorisation (EUA) to Eli Lilly's baricitinib in combination with remdesivir to treat hospitalised COVID-19 patients. The trial in 1,525 hospitalised COVID-19 patients demonstrated baricitinib reduces mortality by 38%, showing the largest clinical effect reported to date for a reduction in mortality in this patient population.

Eli Lilly's COV-BARRIER study, baricitinib was given in addition to the standard of care, which included dexamethasone in the majority of patients. The trial did not meet statistical significance on the primary endpoint, a difference in the proportion of participants progressing to the first occurrence of non-invasive ventilation including high flow oxygen or invasive mechanical ventilation or death by day 28.