Chinese Study Tests AI Assisted Ultrasound for Detecting Carotid Artery Plaque

May 27, 2026
Researchers in Shanghai found that general practitioners could identify carotid artery plaque in high-risk patients using AI assisted portable ultrasound, though performance varied among practitioners.

General practitioners in Shanghai successfully used an AI assisted portable ultrasound to detect carotid artery plaque in high risk patients, according to a press release about a new study published in the Annals of Family Medicine.

Seven general practitioners completed a structured training program combining classroom and hands-on sessions before scanning 169 patients from four community health centers. The AI software analyzed ultrasound images in real time and marked potential plaque on screen for the operator. Each scan was also reviewed by senior ultrasound specialists, whose assessments served as the benchmark.

The general practitioners correctly identified about 87 percent of patients with plaque and correctly ruled out plaque in about 91 percent of those without it. Missed cases were mostly found at the carotid artery fork, an area where the researchers noted the AI system or user adaptation might be limited. Each scan took approximately eight minutes to complete.

The authors described this as the first study in China to test structured AI assisted ultrasound training for general practitioners in real clinical settings. They recommended that wider use of this method should include standardized training and further validation in larger practitioner groups.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.