AI-Enabled, Ultrasound-Guided Handheld Robotic Device for Femoral Vascular Access

Abstract

Hemorrhage is a leading cause of trauma death, particularly in prehospital environments when evacuation is delayed. Obtaining central vascular access to a deep artery or vein is important for administration of emergency drugs and analgesics, and rapid replacement of blood volume, as well as invasive sensing and emerging life-saving interventions. However, central access is normally performed by highly experienced critical care physicians in a hospital setting. We developed a handheld AI-enabled interventional device, AI-GUIDE (Artificial Intelligence Guided Ultrasound Interventional Device), capable of directing users with no ultrasound or interventional expertise to catheterize a deep blood vessel, with an initial focus on the femoral vein. AI-GUIDE integrates with widely available commercial portable ultrasound systems and guides a user in ultrasound probe localization, venous puncture-point localization, and needle insertion. The system performs vascular puncture robotically and incorporates a preloaded guidewire to facilitate the Seldinger technique of catheter insertion. Results from tissue-mimicking phantom and porcine studies under normotensive and hypotensive conditions provide evidence of the technique’s robustness, with key performance metrics in a live porcine model including: a mean time to acquire femoral vein insertion point of 53 ± 36 s (5 users with varying experience, in 20 trials), a total time to insert catheter of 80 ± 30 s (1 user, in 6 trials), and a mean number of 1.1 (normotensive, 39 trials) and 1.3 (hypotensive, 55 trials) needle insertion attempts (1 user). These performance metrics in a porcine model are consistent with those for experienced medical providers performing central vascular access on humans in a hospital.

Development of a Modular Tissue Phantom for Evaluating Vascular Access Devices

“…Again, using the silicone skin layer, latex tubing for vessels, and flow loop platform, a normal ( Figure 6 A) and hypovolemic ( Figure 6 B) model were developed and used successfully for manual vascular access. While similar to the swine image sets, the vessel locations and sizes for high and low pressure were modeled after published values [ 14 ]. Next, we integrated a nerve fiber bundle to increase the complexity and potential use cases beyond vascular access.…”

“…The normovolemic and hypovolemic arteries were 7.4 mm and 5.8 mm in diameter, respectively. The veins had 7.4 mm and 4.2 mm mean diameters for normovolemic and hypovolemic states, respectively [ 14 , 20 ]. The relative orientations of the artery and vein were the same as the porcine model with the artery positioned at a constant depth of 18.4 mm beneath the tissue surface.…”

“…Once catheter placement is confirmed, lifesaving therapeutics can be administered through vascular access. CVA automation has been shown to require little training to use the device while still maintaining high performance accuracy for needle placement [ 14 ].…”

Development and Characterization of an Ex Vivo Testing Platform for Evaluating Automated Central Vascular Access Device Performance

“…Two commercially available ultrasound trainers were used: Generation II Femoral Vascular Access and Regional Anesthesia Ultrasound Training Model (CAE Blue Phantom, Sarasota, FL, USA) and Regional Anesthesia Femoral Trainer with SmarTissue (Simulab Corporation, Seattle, WA, USA). Commercially available ultrasound images [ 14 , 15 ] and previous research [ 12 , 16 , 17 , 18 , 19 ] with these trainers have shown that they contain clearly identifiable vascular structures in ultrasound compliant tissue to mimic human anatomy and were selected for use in this work. Ultrasound compliant fluid provided by respective manufacturers for each trainer were added to arteries and veins and the removal of air bubbles was ensured.…”

“…To address the expertise gaps, research, particularly prioritized by the Department of Defense [ 10 ], is being conducted to develop interventions, such as automated central vascular access devices (ACVADs). Devices such as the VuPath, by Crystalline Medical [ 11 ], and AI-GUIDE (Artificial Intelligence Guided Ultrasound Interventional Device) by the Massachusetts Institute of Technology Lincoln Laboratory [ 12 ] are in various phases of development for the semi-autonomous ultrasound guidance of needle placement. These devices, as well as many others in development by academic and industry partners, utilize ultrasound imaging to identify the central artery or vein of interest, followed by needle alignment for manual or automated needle insertion.…”