receipt
Imaging specialist-performed ultrasounds could be avoided in 35.32% of patients.AbstractValidating Artificial Intelligence Guidance for Ultrasound Acquisition and Remote Interpretation (medRxiv preprint, version 2) · medrxiv.org
Because of AI guidance, operators with no ultrasound training could scan for deep vein thrombosis, and a specialist ultrasound could be avoided in 35.32% of patients, with triage sensitivity of 92.86%.
receipt
Imaging specialist-performed ultrasounds could be avoided in 35.32% of patients.AbstractValidating Artificial Intelligence Guidance for Ultrasound Acquisition and Remote Interpretation (medRxiv preprint, version 2) · medrxiv.org
triage sensitivity was 92.86%AbstractValidating Artificial Intelligence Guidance for Ultrasound Acquisition and Remote Interpretation (medRxiv preprint, version 2) · medrxiv.org
A multicenter prospective study of 594 patients compared AI-guided leg compression ultrasounds acquired by non-trained operators and read remotely against imaging-specialist ultrasounds, and reports triage sensitivity, specificity and the share of specialist scans that could be avoided.
Sources
- primaryValidating Artificial Intelligence Guidance for Ultrasound Acquisition and Remote Interpretation (medRxiv preprint, version 2)medrxiv.org
Editor's notes
verify: the source gives no study period in the text read (abstract only), so achieved dates and the window grade are left empty. verify: the abstract calls the study multicenter, double-blinded, prospective and nonrandomized and registered as NCT06652568; the registry record was not read. verify: "could be avoided" is the authors' estimate from the paired design, not a measured change in how many specialist scans were done.
History
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-sonnet-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Speculative
- Source 0 could be read only in part (an abstract or a summary), not the full document.
- Not dated yet (Actual patients underwent comparative scans, but study dates cannot be established; specialist scans avoided were estimated rather than observed.).
- The two checkers disagreed on attribution: the drafter said only-path and the verifier said bundled. The entry shows the drafter's grade, only-path; treat that grade as unsettled.
- Record
- data/verifications/thinksono-ai-guided-dvt-ultrasound-non-expert-triage/2026-11-17.json · The abstract supports the reported diagnostic performance and estimated 35.32% potential reduction in specialist scans among actual patients. It does not establish realized scan avoidance, isolate AI's contribution, or date the study.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. It is marked speculative: The source is a press release, a news report, or the organisation's own announcement, or the benefit has not yet been measured against anything or dated, or the two checking models disagreed on a grade. Every number is still quoted from the source, and both checking models support it. The models grading an AI registry have an interest in the answer. Cross-vendor checking and the receipts on this page are how the registry handles that, not a claim to have removed it. How the gate works · Dispute this entry
Cite this entry
“Because of AI guidance, operators with no ultrasound training could scan for deep vein thrombosis, and a specialist ultrasound could be avoided in 35.32% of patients, with triage sensitivity of 92.86%.” Because of AI, updated Nov 17, 2026. https://becauseofai.org/entry/thinksono-ai-guided-dvt-ultrasound-non-expert-triage@misc{becauseofai_thinksono_ai_guided_dvt_ultrasound_non_expert_triage,
title = {Because of AI guidance, operators with no ultrasound training could scan for deep vein thrombosis, and a specialist ultrasound could be avoided in 35.32% of patients, with triage sensitivity of 92.86%.},
howpublished = {\url{https://becauseofai.org/entry/thinksono-ai-guided-dvt-ultrasound-non-expert-triage}},
note = {Because of AI registry, updated Nov 17, 2026},
year = {2026}
}