TrenchesAI builds AI tools for perioperative medicine — starting with a conversational chart navigator that learns how clinicians work. Physician-designed. Built for the clinical reality of complex patients and incomplete charts.
Every surgical patient needs a complete preoperative evaluation. The chart contains the information. But finding it, synthesizing it, and flagging what's missing takes 25–30 minutes per case — and that time compounds across thousands of surgeries every month.
Preoperative clinicians navigate multiple Epic tabs, unreliable problem lists, disappearing e-consults, and outside records that don't integrate cleanly — every case, every time.
Abnormal studies with no follow-up. Specialists seen but no perioperative guidance documented. Medications stopped when they shouldn't be. These omissions create risk.
Without a consistent framework, note completeness depends on who's reviewing, how much time they have, and how complex the chart is. Standardization is elusive.
As surgical volume grows, preoperative medicine is the bottleneck. The answer isn't more clinicians — it's giving the clinicians you have better tools.
Peer-reviewed benchmarking studies show AI with retrieval-augmented generation outperforms human clinicians on structured perioperative reasoning tasks. The question is not whether this works — it's whether it's built correctly.
Accuracy on surgical fitness assessment vs. 86% for human anesthesiologists
Ke et al. — npj Digital Medicine, 2025
Time saved per case with AI-assisted preoperative documentation
Ke et al. — npj Digital Medicine, 2025
Projected annual savings per institution from AI-assisted perioperative workflows
Ke et al. — npj Digital Medicine, 2025
We start with a conversational chart navigator embedded in the preoperative workflow. The clinician drives — the system retrieves, summarizes, and flags. Every interaction is logged, and the system learns each clinician's workflow over time. The note generator emerges from observed behavior, not upfront assumptions.
Clinicians ask questions in plain language. The system retrieves cardiology notes, echoes, labs, anesthesia history, clearance documentation — faster than any dot phrase.
A defined set of clinical standards every note must address. The system flags gaps. The clinician decides. The floor is the same for everyone — the path to it is theirs.
Every query, sequence, and retrieval is logged. Patterns surface aggregate gaps in regional protocols. A clinical committee reviews and raises the floor — deliberate, not autonomous.
The same platform follows the patient from POM to the OR to PACU. Each clinician who touches the case uses the same system and trains it on their own workflow.
We're working with perioperative medicine programs to validate this approach. If you're a health system, clinical leader, or engineer interested in what we're building, we'd like to hear from you.
contact@trenchesmd.ai