The catheter was outfitted with a sensor on the end that transmitted photos to researchers and also acted as a haptic antenna of sorts, inspired by the ways rats use whiskers and cockroaches use antennae to find their way, periodically tapping on the walls of the heart. Machine learning algorithms analyzed the images and taps to determine where the catheter was and help it navigate to the desired valve.
The robotic catheter was tested in 83 trials on five pigs. It was able to find its way to the correct location 95 percent of the time and caused no damage to ventricular walls.
Though the self-driving catheter did not arrive at the desired valve faster than a manually directed one can, the researchers noted in the study that the algorithm will be able to learn from each procedure, improving both speed and accuracy. Additionally, autonomous navigation would allow clinicians to focus on critical analysis of the information gathered from the catheter rather than spending time and energy on the tedious task of instrument control.
More articles about AI:
Viewpoint: How health systems can integrate AI into stroke treatment
Cleveland Clinic, Case Western receive $3M NIH grant for machine learning-based imaging analysis
AI-powered neural decoder can turn thoughts into speech
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.