Ultrasound · Regional-anaesthesia anatomy identification and labelling
Nerveblox
Smart Alfa Teknoloji San. Ve Tic. A.S.
Nerveblox answers the question every regional-anaesthesia trainee faces at the probe: which of these grey structures is the nerve, and which is the artery next to it. It carries a respectable regulatory footprint — a 2021 CE mark with a manufacturer-stated EU MDR re-certification, and a 2025 FDA clearance reporting 97 percent anatomical-structure identification accuracy in its validation — and a distribution deal that matters: since late 2025 it ships inside GE HealthCare's Venue point-of-care ultrasound family. Two honest limits hold it at one mark: the peer-reviewed evidence is small prospective volunteer work from Turkish investigator groups, with both registered trials manufacturer-sponsored and no independent external validation or patient-outcome trial yet, and the clearance scope is deliberately narrow — scanning support before the needle, never guidance during it.
Performance Metrics
Clinical Evidence
The load-bearing performance figures come from the FDA 510(k) validation: per the clearance documentation for K250818, Nerveblox demonstrated 97 percent anatomical-structure identification accuracy, with a true-positive rate of 98 percent and a true-negative rate of 90 percent, and expert assessments reported that the AI highlighting reduced the perceived risk of adverse events in 61.67 percent of cases and the perceived risk of block failure in 66.36 percent. These are manufacturer-submitted validation data, and the perceived-risk endpoints are expert opinion measures, not observed complication rates. The US validation dataset was collected in a completed single-centre prospective study of 40 healthy volunteers scanned by three expert anaesthesiologists in Brooklyn, New York (NCT06878911, sponsored by Smart Alfa, completed February 2025). The peer-reviewed record is prospective but small and closely held: a 2021 accuracy study in the Journal of Anesthesia scanned 40 healthy volunteers across four block regions (interscalene, supraclavicular, infraclavicular, TAP), with trainees scanning until the software reported 100 percent scan success and experts validating image quality on a 5-point scale; a 2023 Annals of Anatomy study by the same Gazi University group extended the method to eight regions in 40 volunteers with two expert validators on a 6-point scale, finding expert scores largely concordant but with significant differences by sex in some regions (PECS, popliteal, rectus sheath) and by BMI in others — the same subgroup sensitivity the 2021 paper had flagged for TAP labelling, where accuracy correlated inversely with age and BMI. A 2023 case report in Agri describes three uncomplicated AI-assisted blocks. The published record comes from Turkish investigator groups, and the two registered accuracy trials (NCT05807737, NCT06878911) are manufacturer-sponsored — the Agri case report is from a different institution and the Annals of Anatomy paper declares no competing interests; an independent external validation of the kind published for the competing ScanNav Anatomy PNB has not yet appeared for Nerveblox. No trial has tested whether the highlighting changes block success, complication rates or procedure time in patients.
| Study | Design | n | Sensitivity | Specificity | AUC | Published |
|---|---|---|---|---|---|---|
| Gungor I, et al. (Gazi University; manufacturer-sponsored registration) | ProspectiveProspective | 40 | not reported (expert image-quality validation) | not reported (expert image-quality validation) | — | J Anesth 2021;35:591–594 — four block regions, trainees scanning to 100% software scan-success, 5-point expert validation |
| Gungor I, Gunaydin B, Buyukgebiz Yesil BM, et al. (same group) | ProspectiveProspective | 40 | not reported (expert scoring) | not reported (expert scoring) | — | Ann Anat 2023;250:152143 — eight block regions, 6-point scale, two expert validators; subgroup differences by sex and BMI in some regions |
Inside the Auris+ Listing
Five more sections complete this device’s Auris+ Listing.
Decision Ledger
ProPro unlocks a private, cross-vendor log of every case you read on this device — what the AI called, what you concluded, and a one-line reason if you overrode it. Ready for the EU AI Act's deployer logging obligations when they land in 2028.
Clinical Evidence Deep Dive
ProPro unlocks the structured clinical-evidence summary — study count, target patient population, and a tabular accuracy-metrics view drawn from peer-reviewed sources.
Peer-Reviewed Publications
ProPro unlocks the curated peer-reviewed publication list with PubMed cross-links — the citation backbone of every editorial verdict.
Post-Market & Regulatory Conditions
ProPro unlocks the post-market surveillance summary, recall record, and the conditions of approval that bound real-world use.
AI Algorithm Version History
ProPro unlocks the chronological record of algorithm version changes — what changed when, drawn from manufacturer changelogs and regulatory filings.
Regulatory Approvals
Safety Record
No recall and no adverse-event report for Nerveblox surfaced in public reporting as of August 2026. The FDA MAUDE and enforcement databases could not be queried directly from this environment, so this is recorded as an absence of search-surfaced reports, not a verified empty register query. The device's harm surface is bounded by its clearance scope: it operates only during pre-procedural scanning, is explicitly not used during needle insertion, and the clinician retains responsibility for structure identification and block conduct. The residual risk the literature flags is automation bias — a mislabelled structure accepted without verification — and the published volunteer studies note reduced labelling accuracy in higher-BMI subgroups for some regions, where image quality degrades.
Intended Use & Indications
Nerveblox analyses the live ultrasound image during the pre-procedural scan for a peripheral nerve or plane block and overlays colour-coded highlights and labels on the anatomical structures the clinician needs to recognise — nerves, muscles, vessels, bone and pleura — before a block needle is placed. The US clearance covers use by qualified healthcare professionals for adult patients, explicitly prior to any needle intervention: the software is a scanning and image-interpretation aid, not a needle-guidance system, and it is not used in combination with needles or during needle insertion. Block regions supported include the interscalene, supraclavicular, infraclavicular and axillary brachial plexus, cervical plexus, PECS I and II, transversus abdominis plane, rectus sheath, femoral nerve, adductor canal, popliteal sciatic and erector spinae plane. The software runs on cart-based and handheld ultrasound platforms; a separate Android build for handheld use is CE-marked in Europe, and in the US market Nerveblox ships as an integrated feature of GE HealthCare's Venue point-of-care ultrasound family.