A deep reinforcement learning model for intraoperative dosing replicated 69% of physician vasopressor decisions, with alignment to the model's recommendations associated with the lowest AKI incidence.
Cohort (n=42,547)
No
Does a deep reinforcement learning model recommending intravenous fluids and vasopressors reduce intraoperative hypotension and postoperative acute kidney injury in adult patients undergoing major surgery?
A deep reinforcement learning model for intraoperative fluid and vasopressor dosing outperformed actual physician decisions in estimated policy value and was associated with lower postoperative AKI incidence when physician actions aligned with the model.
Background: Traditional methods of surgical decision making heavily rely on human experience and prompt actions, which are variable. A data-driven system that generates treatment recommendations based on patient states can be a substantial asset in perioperative decision-making for cases of intraoperative hypotension in which suboptimal management is associated with acute kidney injury (AKI), a common and morbid postoperative complication. Methods: In this retrospective cohort study, we analyzed 50,021 surgeries from 42,547 adult patients who underwent major surgery at a quaternary care hospital between 2014 and 2020. We developed a deep reinforcement learning model to recommend the optimum doses of intravenous fluids and vasopressors during surgery to avoid intraoperative hypotension and AKI defined by Kidney Disease: Improving Global Outcomes serum creatinine criteria within three days following surgery. Results: The developed model replicated 69% of physician’s decisions for the dosage of vasopressors and proposed higher or lower dosage of vasopressors than received in 10% and 21% of the treatments, respectively. In terms of intravenous fluids, the model’s recommendations were within 0.05 ml/kg/15 min of the actual dose in 41% of the cases, with higher or lower doses recommended for 27% and 32% of the treatments, respectively. The reinforcement learning policy resulted in a higher estimated policy value compared to the physicians’ actual treatments, as well as random policies and zero-drug policies. AKI incidence was lowest in patients who received medication dosages that aligned with our agent model’s decisions. Conclusions: Our findings suggest that implementation of the model’s policy has the potential to lower postoperative AKI and improve other outcomes driven by intraoperative hypotension.
Adiyeke et al. (Tue,) conducted a cohort in Adult patients undergoing major surgery (n=42,547). Deep reinforcement learning model for dosing intravenous fluids and vasopressors vs. Physicians' actual treatments, random policies, and zero-drug policies was evaluated on Acute kidney injury (AKI) within three days following surgery. A deep reinforcement learning model for intraoperative dosing replicated 69% of physician vasopressor decisions, with alignment to the model's recommendations associated with the lowest AKI incidence.