By Dave Pearson

Deep reinforcement learning enabled by AI can help physicians figure out whether opioids would truly be better than other interventions for patients suffering pain in intensive care units.

Research presenting the finding was presented at a conference in Europe last week, and Psychology Today breaks down the details in an article posted online July 25.

“Deep reinforcement learning has contributed to AI milestone achievements in chess, various Atari games, shogi (Japanese chess) and Go,” explains PT writer Cami Rosso. “In healthcare, deep reinforcement learning has been applied toward chemotherapy dosing for cancer patients in clinical trials, ICU heparin dosing and the dosing of intravenous fluids and vasopressor for sepsis patients, among other purposes.”

In the new study, PhD candidate Daniel Lopez-Martinez of MIT and colleagues used data from more than 40,000 hospitalizations to understand what safe and efficacious opioid interventions should look like.