When a large vessel occlusion (LVO) is missed or caught late, the consequences compound by the minute. That's why independent validation of AI stroke-detection tools matters so much — not as a checkbox, but as the difference between a workflow that catches a treatable occlusion and one that lets it slip through.
A study from Good Samaritan Hospital, HCA in San Jose, California, gives healthcare organizations exactly that kind of evidence. Recently published in the American Journal of Neuroradiology (AJNR), the DUEL study ran two AI-powered LVO detection solutions side by side, in the same comprehensive stroke center, across more than 1,500 consecutive stroke alerts over two years. Few published comparisons of this kind reach that scale.
DUEL study results: RapidAI vs. Viz.ai LVO detection rates
The hospital's neurosciences, stroke services, radiology, and quality teams retrospectively reviewed CTA data from 1,589 consecutive stroke alerts, collected prospectively in parallel over the two-year period. After excluding cases not sent to the software or compromised by poor contrast bolus, metal artifact, or brain hemorrhage, 1,523 cases remained. Of those, 147 — about 1 in 10 — had a confirmed LVO, defined as occlusion or high-grade stenosis of the intracranial ICA or MCA M1 segment.
RapidAI caught 144 of those 147 cases. That's a 98% sensitivity. Viz.ai caught 108, or 73.5% — a statistically significant difference (P<0.0001).
The specificity numbers told a similar story, though the margin was tighter: RapidAI correctly cleared 94% of LVO-negative cases, against 91% for Viz.ai (P=0.004).
A missed detection isn't just a technical footnote. In raw terms, Viz.ai didn't flag 39 confirmed LVOs, and the study authors point out what that can mean in practice: delayed diagnosis and delayed treatment in a disease where delay has profound implications.
Why the DUEL study's real-world design matters for LVO software evaluation
Most AI performance claims come from development datasets — curated, controlled, built to make the algorithm look good. DUEL wasn't that. It was 1,589 real stroke alerts, in order, with nothing excluded except the genuinely unqualified scans.
That design answers a more useful question than "does this algorithm work in principle." It answers "does this algorithm hold up on a Tuesday night in the ED." A single-center study has its limits — replication elsewhere would only strengthen the case — but a two-year, consecutive, unselected cohort of this size is a meaningfully higher bar than most published comparisons clear.
What the DUEL study means for stroke center AI adoption decisions
Trust in clinical AI isn’t built by a vendor’s spec sheet. It’s built on rigorous clinical validation and independent, peer-reviewed evidence demonstrating how technology performs in real-world practice.
The publication of the DUEL study in AJNR adds another important layer of evidence for hospitals evaluating AI solutions. Rather than relying solely on vendor claims or controlled testing environments, health systems can look to published research showing how these tools performed across more than 1,500 consecutive stroke alerts in routine clinical practice.
At RapidAI, this commitment to rigorous clinical validation extends beyond stroke. As health systems increasingly adopt AI across service lines, independent real-world evidence remains essential to ensuring radiologists and clinicians can trust the technology supporting prompt treatment decisions.
Frequently asked questions
Q: Does a single-center study like this apply to other hospitals?
DUEL is one of the largest consecutive, real-world comparisons of LVO detection software published to date, which gives it more weight than smaller studies. That said, it reflects one hospital's stroke volume, imaging protocols, and patient population over a specific two-year window. Results at other institutions — with different scanners, contrast protocols, or patient demographics — could vary, and independent replication at additional sites would help confirm how broadly these findings generalize.
Q: How should a hospital evaluating LVO detection software use a study like this?
A large, consecutive, real-world comparison like DUEL is a useful data point, but it shouldn't be the only one. Hospitals should look at performance across their own case mix, confirm how a platform performs on the occlusion types and imaging protocols most relevant to their patient population, and weigh workflow factors — like processing speed and integration with existing health IT systems — alongside raw sensitivity and specificity. Requesting site-specific validation data or a pilot period before full deployment is a reasonable next step for any institution making this decision.
Q: What does the difference in LVO detection rates mean clinically?
The study found that RapidAI detected 144 of 147 confirmed LVOs, while Viz.ai detected 108. In practical terms, that means there were confirmed stroke cases that RapidAI identified but Viz.ai did not. For clinicians, a missed LVO can delay diagnosis, treatment decisions, and ultimately patient care. While every hospital should evaluate technology within its own clinical environment, independent real-world evidence like DUEL helps illustrate how differences in detection performance can translate into meaningful differences for patients requiring urgent treatment.
Study reference: AJNR, DOI: 10.3174/ajnr.A9418
Sachdev H, Hudson A, Ong K, Marklein S, Flores M. Detection of Large Vessel Occlusion Using AI: Evaluating Performance of RapidAI LVO vs Viz.ai LVO in 1,589 Consecutive Code Strokes (DUEL). American Journal of Neuroradiology. Published online May 14, 2026. DOI: 10.3174/ajnr.A9418. https://www.ajnr.org/content/early/2026/05/14/ajnr.A9418.long
