Scientists invent AI-based robotic phlebotomist

A team of engineers has created a tabletop device that combines a robot, artificial intelligence and near-infrared and ultrasound imaging to draw blood or insert catheters to deliver fluids and drugs.

Their most recent results of this research from Rutgers University -- published in the journal Nature Machine Intelligence -- suggest that autonomous systems like the image-guided robotic device could outperform people on some complex medical tasks.

Medical robots could reduce injuries and improve the efficiency and outcomes of procedures, as well as carry out tasks with minimal supervision when resources are limited.

"Using volunteers, models and animals, our team showed that the device can accurately pinpoint blood vessels, improving success rates and procedure times compared with expert health care professionals, especially with difficult to access blood vessels," said senior author Martin L. Yarmush, Paul & Mary Monroe Chair & Distinguished Professor in the Department of Biomedical Engineering in the School of Engineering at Rutgers University-New Brunswick.

Getting access to veins, arteries and other blood vessels is a critical first step in many diagnostic and therapeutic procedures. The timeliness of procedures can be critical, but gaining access to blood vessels in many people can be quite challenging.

Failures occur in an estimated 20 per cent of procedures, and difficulties increase in people with small, twisted, rolling or collapsed blood vessels, which are common in pediatric, elderly, chronically ill and trauma patients, the study says.

In these groups, the first-stick accuracy rate is below 50 per cent and at least five attempts are often needed, leading to delays in treatment. Bleeding complications can arise when major adjacent arteries, nerves or internal organs are punctured, and the risk of complication rises significantly with multiple attempts. When nearby blood vessels are inaccessible, more invasive approaches such as central venous or arterial access are often required.

The robotic device can accurately steer needles and catheters into tiny blood vessels with minimal supervision. It combines artificial intelligence with near-infrared and ultrasound imaging to perform complex visual tasks, including identifying the blood vessels from the surrounding tissue, classifying them and estimating their depth, followed by motion tracking.