Wearable surgical robot can help stem deadly blood loss | MIT News

After a traumatic accident, there is a small window of time during which medical professionals can apply life-saving treatment to victims with severe internal bleeding. Delivering this type of care is complex, and key interventions require the insertion of a needle and catheter into a central blood vessel, through which fluids, medications or other aids can be delivered. First responders, such as ambulance emergency medical technicians, are not trained to perform this procedure, so treatment can only be administered after the victim is transported to hospital. In some cases, by the time the victim arrives for treatment, it may already be too late.

A team of researchers from MIT Lincoln Laboratory, led by Laura Brattain and Brian Telfer of the Human Health and Performance Systems Group, along with physicians from the Center for Ultrasound Research and Translation (CURT) at Massachusetts General Hospital, led by Anthony Samir, developed a solution to this problem. The Artificial Intelligence Guided Ultrasound Intervention Device (AI-GUIDE) is a wearable platform technology that has the potential to help personnel with simple training to quickly place a catheter in a common femoral vessel, enabling a prompt treatment to the point of injury.

“Simply put, it’s like a very smart stud finder married to a precision nail gun.” says Matt Johnson, a research team member in the lab’s Human Health and Performance Systems Group.

AI-GUIDE is a platform consisting of custom algorithms and built-in robotics that can be paired with most commercial handheld ultrasound devices. To operate AI-GUIDE, a user first places it on the patient’s body, near where the thigh meets the abdomen. A simple targeting display guides the user to the correct location, then instructs them to pull a trigger, which precisely inserts the needle into the vessel. The device verifies that the needle has entered the blood vessel, then prompts the user to advance an integrated guidewire, a thin wire inserted into the body to guide a larger instrument, such as a catheter, through a vessel. The user then manually advances a catheter. Once the catheter is securely in place in the blood vessel, the device withdraws the needle and the user can withdraw the device.

With the catheter safely inside the vessel, responders can then administer fluids, medications, or other interventions.

As easy as pressing a button

The Lincoln Laboratory team developed the AI ​​in the device by leveraging technology used for real-time object detection in images.

“Using transfer learning, we trained the algorithms on a large set of ultrasound data acquired by our clinical collaborators at the MGH,” explains Lars Gjesteby, a member of the lab’s research team. “The images contain key landmarks of vascular anatomy, including the common femoral artery and vein.”

These algorithms interpret the visual data from the ultrasound associated with AI-GUIDE and then show the correct location of the blood vessel to the user on the screen.

“The beauty of the on-device display is that the user never needs to interpret, or even see, the ultrasound imagery,” says Mohit Joshi, the team member who designed the device. ‘display. “They are simply directed to move the device until a rectangle, representing the target vessel, is in the center of the screen.”

To the user, the device may seem as easy to use as pressing a button to advance a needle, but to ensure quick and reliable success, there’s a lot going on behind the scenes. For example, when a patient has lost a large volume of blood and becomes hypotensive, veins that would typically be round and full of blood become flat. When the needle tip reaches the center of the vein, the vein wall is likely to “try” inward, rather than being pierced by the needle. As a result, although the needle was injected into the correct place, it fails to enter the vessel.

To ensure that the needle punctures the vessel reliably, the team designed the device to be able to verify its own work.

“As AI-GUIDE injects the needle toward the center of the vessel, it searches for the presence of blood by creating suction,” says Josh Werblin, the program’s mechanical engineer. “The optics in the handle of the device trigger when blood is present, indicating successful insertion.” This technique partly explains why AI-GUIDE has shown very high injection success rates, even in hypotensive scenarios where veins are prone to constriction.

Recently the team published an article in the review Biosensors which reports AI-GUIDE needle insertion success rates. Users with medical experience ranging from zero to over 15 years tested AI-GUIDE on an artificial model of human tissue and blood vessels and an expert user tested it on a series of sedated live pigs. The team reported that after just two minutes of verbal training, all users of the device on the artificial human tissue successfully placed a needle, with all but one completing the task in less than a minute. The expert user was also able to quickly place the needle and the integrated guidewire and catheter in about a minute. The speed and accuracy of needle insertion was comparable to experienced clinicians operating in a hospital setting on human patients.

MGH collaborator and radiologist Theodore Pierce says AI-GUIDE’s design, which makes it stable and easy to use, translates directly into low training requirements and efficient performance. “AI-GUIDE has the potential to be faster, more accurate, safer, and requires less training than current image-guided manual needle placement procedures,” he says. “The modular design also allows for easy adaptation to a variety of clinical scenarios beyond vascular access, including minimally invasive surgery, image-guided biopsy, and image-guided cancer therapy. “

In 2021, the team received a R&D 100 Award for AI-GUIDE, recognizing it among the most innovative new technologies of the year available in license or on the market.

And after?

Currently, the team continues to test the device and work on fully automating every step of its operation. In particular, they want to automate the guidewire and catheter insertion steps to further reduce the risk of user error or the potential for infection.

“Retracting the needle after catheter placement reduces the risk of inadvertent injury, a serious complication in practice that can lead to the transmission of diseases such as HIV and hepatitis,” says Pierce. “We hope that a reduction in manual handling of procedural components, resulting from the complete integration of needle, guidewire and catheter, will reduce the risk of central line infection.”

AI-GUIDE was designed and tested in the new Virtual Integration Technology Lab (VITL) at Lincoln Laboratory. VITL was built to provide the laboratory with medical device prototyping capability.

“Our vision is to rapidly prototype smart medical devices that integrate AI, sensing – especially wearable ultrasound – and miniature robotics to address critical unmet military and civilian healthcare needs,” says Laura Brattain, co-leader of the AI-GUIDE project and also holds a visiting researcher position at the MGH. “By working closely with our clinical collaborators, we aim to develop capabilities that can be quickly translated into the clinical setting. We expect VITL’s role to continue to grow.

AutonomUS, a startup founded by AI-GUIDE’s MGH co-inventors, recently secured an option for the intellectual property rights to the device. AutonomUS is actively seeking investors and strategic partners.

“We see the AI-GUIDE platform technology becoming ubiquitous throughout the healthcare system,” says Johnson, “enabling faster and more accurate treatment by users with a wide range of expertise, both for pre-hospital emergency interventions and routine image-guided procedures.”

This work was supported by the U.S. Army Combat Casualty Care Research Program and Joint Program Committee – 6. Nancy DeLosa, Forrest Kuhlmann, Jay Gupta, Brian Telfer, David Maurer, Wes Hill, Andres Chamorro, and Allison Cheng provided technical inputs , and Arinc Ozturk, Xiaohong Wang, and Qian Li provided guidance on clinical use.

About Hector Hedgepeth

Check Also

Study co-authored by UMass Chan researchers finds big differences in SARS-CoV-2 infectivity

A wide variation in the amount or infectivity of SARS-CoV-2 among people in the early …