Perioperative medicine & outcomes
Artificial Intelligence-Driven Clinical Decision Support for Postoperative Delirium Prevention: A Pragmatic Randomized Controlled Trial
Authors' conclusion
In this pragmatic randomized controlled trial, less than 20% of the sample had documented delirium assessments due to variability in routine POD screening practices, limiting our ability to conclude that artificial intelligence-driven clinical decision support was not effective in preventing postoperative delirium. However, based on our secondary outcome analyses, the intervention did not significantly change best practice adherence. Further work is needed to determine the best way to use these tools effectively.
Study context
- Population
- Patients with preoperative cognitive impairment identified immediately before surgery using a validated natural language processing algorithm, Mini-Mental State Examination scores, or diagnostic codes, at The Mount Sinai Hospital in New York City, June 20, 2023, to August 31, 2024identified as having cognitive impairment immediately before surgery and randomized, 1255/7294 (17.2%) had documented postoperative delirium assessments · intervention 3,624 · control 3,670
- Participants
- 7,294 patients
- Comparison
- Intervention vs control
- Interventionn = 3,624
- Controln = 3,670
- Primary endpoint
- Postoperative delirium (POD), assessed with the 4 A's Test
- Follow-up
- Within seven days postoperatively
Methodological detailsembedded within routine clinical care
- Embedded within routine clinical care
Primary result
As reported in the abstract
P = 0.37
Secondary outcomes
| Outcome | P value |
|---|---|
| Adherence to 12 perioperative best practices (secondary)No statistically significant differences | all P > .05 |
Postoperative delirium among patients with documented delirium assessments (overall)
- Patients with documented postoperative delirium assessments
- 1255/7294 (17.2%)
- Of those assessed, developed postoperative delirium
- 426/1255 (34%)
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →