A few years ago, Kevin DeMarco’s aunt was an operating room nurse who asked DeMarco – upon learning he was programming robots for a living – if there was a robot that could prepare surgical equipment. After investigating the matter with a colleague at Georgia Tech, where DeMarco was working as a member of the research faculty, he decided to leave his position to create the robot his aunt had built. ever mused.
In this mission, DeMarco co-founded RIF Roboticsone of the startups in TechCrunch Disrupt Battlefield 200. Led by DeMarco, Sergio García-Vergara and third co-founder, Collin Faril, an industrial designer by trade, RIF Robotics looks to use combines AI and robotics to relieve medical staff of the burden of mundane tasks so they can focus on clinical work.
Image credits: RIF Robotics
The aseptic process – cleaning medical equipment – is also challenging for technicians who spend hours each day inspecting and cleaning instruments. Some devices require more than 100 steps for sterilization, and the pace in busy hospitals can be relentless.
The costs can also add up. One research estimates that just 20 instrument failures leading to an operating room delay can cost a hospital up to $3,385. Over a year, the cost to the hospital would be about $48,000, the study found.
RIF does not solve the cleaning problem. But the startup claims its prototype product, developed in less than two months, can save surgeons time by identifying, classifying and manipulating four different instruments. and assemble a small surgical tray. Two machine learning systems – an image segmentation system and an object classifier, trained on synthetic and realistic image sets of surgical instruments – help the robotic arm to hold and move. move tools.
DeMarco told TechCrunch in an interview: “The major challenges facing the aseptic processing industry are the lack of experienced surgical technicians, instrument level monitoring, infection tracing and cost retrieval. “Medical device manufacturers care about how their equipment is used and degraded in the field. Tool-level data will also help them decide where to send sales reps. Hospitals are interested in device-level data because it will help them operate more efficiently by improving device-level monitoring and device testing. Currently, most hospitals only monitor at the tray level, but the industry wants to be able to monitor at the instrument level.”
Image credits: RIF Robotics
Future prototypes will be able to recognize more tools and determine if there is “biological waste” (i.e. blood and bone) on the surface of the tool, and assess sharpness. and the overall condition of the instrument. But even in its current form, DeMarco believes RIF has created a product that hospitals will use.
“Three hospitals in Atlanta and the Department of Veterans Affairs are interested in our product,” he said. “We have a collaborative research and development agreement with the Veterans Affairs Association that allows us to do pilot studies and customer discovery at their facility… [We’ll deploy] three alpha versions of our system at local Atlanta hospitals, where we already have existing connections. “
RIF is kicking off now – DeMarco claims the company has a write rate of less than $1,000 per month. But the team is not naive about the long road ahead. RIF is preparing after a $800,000 debt seed round and hopes to hire a medical device industry expert once the round closes. The company, which is a pre-revenue company, is also expected to require three rounds of funding and nearly four years before reaching profitability.
The co-founders of RIF Robotics pose for a photo in an exfoliating state.
There is also competition from vendors such as RST Automation, which sells semi-automated medical instrument identification and organization systems. Steris and R-Solution Medical – two other competitors, although not direct rivals – are developing robots to transport and store surgical trays and equipment.
DeMarco claims that RIF’s solution is more likely. But the proof will be in the pudding – RIF aims to turn its prototype into a manufacturable product by the fall of 2023.
“The healthcare industry is starving for innovation,” said DeMarco. “We are protecting ourselves from potential difficulties by developing products and solutions that are directly demanded by the industry and end users.”
