A reinforcement learning algorithm to optimize resource utilization in combat casualty care

Manivannan Subramaniyan, Xin Jin, Sridevi Nagaraja, Anders Wallqvist, Jaques Reifman · 2025

Read A reinforcement learning algorithm to optimize resource utilization in combat casualty care by Manivannan Subramaniyan, Xin Jin, Sridevi Nagaraja, Anders Wallqvist, Jaques Reifman (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12738704.txt.

Description

Five authors, led by Manivannan Subramaniyan, train in 2025 a learning system to ration fluid resuscitation for bleeding soldiers when supplies run short. Fluids right after a bleed save lives, but future wars may bring mass casualties with little fluid to spare. The team built a large fake casualty set with a proven body model.

Each fake casualty faced a choice each half hour: one fluid unit or none, over ninety minutes. The learner sought plans that healed the most casualties with the least fluid. On fresh test data, it healed over twice as many as standard care at twice the efficiency. The work targets triage tools.

Catalog record

CREATORManivannan Subramaniyan, Xin Jin, Sridevi Nagaraja, Anders Wallqvist, Jaques Reifman
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE52 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12738704

Browse the full library · About the Tower of Babel