Discordance between actual care and recommendations by a reinforcement learning model for sepsis

Original source

Discordance between actual care and recommendations by a reinforcement learning model for sepsis

Comparing ICU teams' fluid and vasopressor choices with the 'AI Clinician' across 30,678 sepsis patients, larger gaps went with higher 90-day mortality only in the sicker group.

Evidence

Evidence: Peer-reviewed (evidence step 5 of 6)

Published after review by independent experts.

The story in three lines

Key finding

In patients with SOFA scores of 6 or more, greater disagreement with the RL model was linked to higher 90-day mortality (adjusted OR 1.11); not in less sick patients.

Significance

Clinical: offers a way to audit treatment-recommending AI against real ICU decisions at scale.

Takeaway

Observational; it shows association, not that following the model would save lives.

Study details (as stated by the source)

Study design

Retrospective ICU cohort analysis

Sample size

30,678 patients, 309,415 time-epochs

Outcomes

90-day mortality

Later coverage in the journal

No later coverage in the journal yet.

Corrections and updates

No corrections or updates recorded for this item.