MIT, Mass General researchers develop hand-held robot for tapping into blood vessels

Researchers at the Massachusetts Institute of Technology and Massachusetts General Hospital are developing a robotically guided hand-held device that can quickly tap into a patient’s central artery, allowing first responders and other healthcare professionals to easily apply emergency therapies with little training.

The system uses an artificial-intelligence-powered ultrasound scanner to guide needles and catheter hardware, to help stem severe bleeding, or deliver fluids and medications—all while potentially in the back of an ambulance.

“Simplistically, it’s like a highly intelligent stud-finder married to a precision nail gun,” research team member Matt Johnson told MIT News.

Dubbed the AI-Guide, the device is designed around accessing the body’s large femoral artery, which runs through the thigh. Using ultrasound scans, a simplified display guides the user to the correct location. There, a trigger pull deploys a needle into the vessel. After the system confirms that the needle has reached its target, it tells the user to insert a guidewire that can then shepherd in larger instruments, such as a catheter. 

The AI was trained on ultrasound exams collected by MGH to help establish vascular landmarks such as the femoral artery and vein, the researchers said, including in cases when the patient has lost large volumes of blood. In those situations, veins that are typically round and full can flatten. They appear different on a scan and can be more difficult to tap.

In a paper published in the journal Biosensors, volunteers with medical experience ranging from zero to as many as 15 years in the field tested the device on artificial models of human tissue, One expert used the system on sedated pigs. According to the researchers, after only two minutes of verbal instruction, every user successfully placed a needle within a blood vessel, most of them in under one minute.

“AI-Guide has the potential to be faster, more precise, safer, and require less training than current manual image-guided needle placement procedures,” said study collaborator Theodore Pierce, a radiologist at MGH. 

“The modular design also permits easy adaptation to a variety of clinical scenarios beyond vascular access, including minimally invasive surgery, image-guided biopsy, and imaging-directed cancer therapy,” Pierce added. The device’s development was also supported by the U.S. Army’s Combat Casualty Care Research Program.

Looking ahead, the developers plan to fully automate each step, including the insertion of guidewires and catheters and retraction of the needle. A new startup founded by the device’s co-inventors, AutonomUS, has secured the rights to the system and is seeking strategic partners to continue its testing and development.