Alibaba DAMO Academy’s AI model reportedly spots life‑threatening aortic emergencies in seconds

Breakthrough claim: seconds‑fast detection on routine CT

Alibaba DAMO Academy (阿里巴巴达摩院), together with The First Affiliated Hospital, Zhejiang University School of Medicine (浙江大学医学院附属第一医院), has reportedly developed an AI model named iAorta that can identify acute aortic syndrome (AAS) from routine non‑contrast CT scans in a matter of seconds. It has been reported that the work—designed for emergency chest‑pain workflows—has been published in Nature Medicine (自然·医学), an international top journal, marking another high‑profile clinical result from a major Chinese tech lab.

Study results and clinical impact

According to the parties, iAorta was tested in an emergency chest‑pain cohort of more than 10,000 patients and precisely flagged 21 cases of acute aortic syndrome, helping those patients receive timely treatment. The developers say the system can shorten definitive diagnosis to within two hours for many patients who would otherwise wait longer for specialist imaging such as CT angiography. Fast detection matters: AAS is rare but rapidly fatal if missed. Seconds‑level triage for a condition that mimics ordinary chest pain could save lives.

Why this matters beyond China

For Western readers: AAS (a tear or rupture in the aorta) presents with non‑specific symptoms and often requires contrast vascular imaging to confirm. Many hospitals—especially during nights or in smaller facilities—lack immediate access to advanced angiographic scans. An AI that flags high‑risk scans on routine plain CT could change emergency workflows and prioritize scarce resources. It also demonstrates how Chinese tech‑hospital partnerships are pushing applied AI into acute care.

Publication, verification and geopolitical context

The claims come from the developers and have been reported by Alibaba; independent peer scrutiny, external validation and regulatory approval will determine clinical adoption. Reportedly appearing in Nature Medicine gives the work visibility, but real‑world rollout faces the usual hurdles: multicenter validation, regulatory clearance and integration into hospital IT. All this unfolds amid broader geopolitical tensions—export controls on advanced chips and scrutiny of Chinese AI firms—that shape how such technologies scale internationally. Can a Chinese‑built model win regulatory trust and clinical uptake beyond its home market? Time will tell.