Johnson & Johnson Funds AI Surgery Tools to Reduce Errors, Speed Training

Johnson & Johnson's Polyphonic™ digital ecosystem for surgery has been developed to address a longstanding problem in medicine: surgical knowledge and insights remain isolated within individual operating rooms. The company is investing in artificial intelligence through its Polyphonic AI Fund for Surgery QuickFire Challenge, which invites researchers, startups, healthcare institutions and established companies to submit AI-powered proposals that tackle real clinical problems at scale. Selected awardees receive funding, mentorship and technical support to accelerate development. According to Raymond Fryrear II, Vice President and Chief Scientific Officer of Polyphonic at Johnson & Johnson, the initiative exists to close "the gap between cool demos and those that actually change practice in the OR."

Curium Life's SurgiMeasure, founded by Dr. Vinayak Rengan, a pediatric and neonatal surgeon with 10 years of experience, uses a combination of computer vision, deep learning and depth algorithms to convert surgical video into structured geometric data. The tool measures anatomical distances during laparoscopic and robotic surgeries—a task historically requiring surgeon intuition and experience. Dr. Rengan explains that in procedures like hysterectomy, the ureter (a thin tube about the thickness of a phone charger cable) sits behind the uterus, and even highly skilled surgeons risk nicking it with their instruments. SurgiMeasure is designed to function "like a glorified parking assist, where it starts beeping when you get too close to another car," alerting surgeons before they approach sensitive anatomy. The concept originated in 2016 when Dr. Rengan, then a surgical resident, realized that some surgeons are much better than others at identifying complications before they occur, regardless of training duration. This insight led him to ask: "What if we were able to bring in that kind of experience for every procedure in every operating room?"

C1DO1, launched in 2019 by Dr. Julián Varas, a professor of surgery and head of surgical simulations at Catholic University of Chile, takes a different approach to improving surgical outcomes through education. Dr. Varas' research showed that after just 16 training sessions with detailed feedback and targeted mentoring, new surgeons performed as well as traditionally trained surgeons with five years' experience. The platform's name references William Stewart Halsted, who created the first formal surgical residency program in the U.S. in the late 1800s, and his teaching method: "See one, then I will supervise you, then you will perform the surgery on your own and finally you will return home and teach others." The C1DO1 platform works by having surgeons submit videos of themselves performing real or simulated procedures; the videos are reviewed independently by human experts and AI, and surgeons receive personalized feedback, video tutorials and procedure checklists. By accumulating information over time, the platform can continually assess a surgeon's skills and gauge improvement, significantly reducing the learning curve—helping surgeons reach mastery after 10 to 20 cases rather than the hundreds typically required. Dr. Varas sees potential to extend the platform beyond surgeons to nurses, physical therapists and other healthcare professionals.

The Polyphonic ecosystem is designed as an open digital platform that allows a broad range of partners, applications and innovations to work together. While innovations are not required to be built on Polyphonic, the QuickFire Challenge is intended to foster solutions that can benefit from and potentially integrate with the ecosystem, helping bring AI innovations into operating rooms around the world.

For years, surgical knowledge and insights remained locked within individual operating rooms, with valuable information from surgical video, device data and clinical insights difficult to share or leverage to improve care across the field. Johnson & Johnson's Polyphonic represents an attempt to break down those silos by creating a unified digital ecosystem that connects operating rooms through data and AI. Raymond Fryrear II, Vice President and Chief Scientific Officer of Polyphonic at Johnson & Johnson, frames the challenge as conducting an orchestra where "the sheet music keeps changing and the instruments are all tuned differently." The Polyphonic AI Fund for Surgery QuickFire Challenge exists to identify and fund innovations that address real clinical problems and can operate at real-world scale—innovations that historically "languish in the gap between cool demos and those that actually change practice in the OR," according to Dr. Fryrear.

The 2026 awardees reflect this focus on practical, operating-room-ready solutions. Curium Life's SurgiMeasure stems from Dr. Vinayak Rengan's frustration with guesswork in pediatric and neonatal surgery; he observed that experienced surgeons could rely on intuition to measure anatomical distances, but less experienced surgeons could not do so with the same accuracy. His tool converts surgical video into geometric data to provide objective measurements, with the end goal of emitting warnings when surgeons approach sensitive tissue. Similarly, C1DO1 emerged from Dr. Julián Varas' research showing that specialized training with detailed feedback could accelerate surgical skill; after just 16 intensive training sessions, new surgeons performed as well as traditionally trained surgeons with five years' experience. By combining Large Language Models with computer vision to review surgical videos and provide personalized feedback, C1DO1 condenses the typical learning curve from hundreds of cases to 10 to 20 cases.

No comments yet. Be the first to share your thoughts!