AI Orthopaedics Tool

Hip-replacement planning for the direct anterior approach. Detection places the landmarks, the overlay goes on automatically or by hand, and the surgeon adjusts size, orientation and femur rotation before signing anything. It computes delta leg length and offset. Planning that took hours takes minutes.

Built at: DevTechGuru
Scale: 5,000+ clinical cases.
Category: Healthcare AI

Clinical cases: 5,000+

Context

Planning a joint replacement took hours per case, across tools that didn't talk to each other. The ML side already had a segmentation model. Nobody had built a workflow around it.

Challenge

Surgeons sign every plan. The model had to produce something one would sign.

Non-negotiables

Patient privacy
Clear reasoning behind every suggestion

Calls I made

01
Surgeon in control
The model proposes, the surgeon decides. Every step is reviewed and signed off by a clinician.
02
Simple data layer
Kept the underlying schema flat so patient data stays isolated and easy to audit.

Trade-offs accepted

Guided manual review sits on every case, so planning time bottoms out at whatever a surgeon takes to read the screen.

Outcome

Pre-operative planning time fell by roughly 40% on the first ward it shipped to, and every case on that ward goes through the tool now. The client measured that 40%, not me. 5,000+ clinical cases have been planned in it.

Stack