Radiology · Acute care suite
Aidoc
Aidoc Medical
Across more than 20 FDA clearances and 1,600+ medical centres worldwide, Aidoc has become the de-facto acute-care AI platform — the broadest regulatory footprint in radiology AI, deep real-world data exceeding 100 million analysed cases, and a consistent peer-reviewed performance record across ICH, PE, and now multi-condition abdominal triage.
Performance Metrics
Clinical Evidence
Aidoc's deepest publication record centres on ICH detection. A prospective validation at a high-volume UK trauma centre (Zia et al., Scientific Reports 2022, n=1,446 prospective scans) found 85.7% sensitivity (95% CI 80.3–90.2%) and 96.8% specificity on BriefCase v1.3. A large real-world evaluation across 37 US radiology practices (n=332,809 head CTs, 2023–2024) reported assisted-radiologist sensitivity of 93.6% and specificity of 100% for ICH. A separate 17-facility academic health-system study (n=101,944 non-contrast head CTs, 2023–2025; npj Digital Medicine 2025) found 82.2% sensitivity and 97.6% specificity on the standalone model, with noted degradation for subacute and small (≤10 mm) haemorrhages. For the CARE Multi-Triage CT Body module (K252970, cleared January 2026), FDA-reviewed pivotal data showed mean sensitivity 97% (up to 98.5%) and mean specificity 98% (up to 99.7%) across 14 abdominal indications. The evidence base is predominantly prospective multicentre; no industry-sponsored RCT has been published as of the review date, and 81% of external validation studies in the broader radiology-AI literature show some performance degradation on independent datasets — a caveat that applies to Aidoc's ICH model on chronic and subacute subtypes.
| Study | Design | n | Sensitivity | Specificity | AUC | Published |
|---|---|---|---|---|---|---|
| Zia A, Fletcher C, Bigwood S, et al. | ProspectiveProspective | 1,446 | 85.7% | 96.8% | — | Scientific Reports, Nov 2022 |
| Multi-centre retrospective — 37 US radiology practices | RetrospectiveRetrospective | 332,809 | 93.6% | 100% | — | Unpublished / conference data, 2024 |
| Real-world evaluation — 17-facility academic health system | RetrospectiveRetrospective | 101,944 | 82.2% | 97.6% | — | npj Digital Medicine, 2025 |
Clinical Pulse
Verified clinician sentiment
Verified clinician reviews launching soon · Apply to contribute →
Reviews are signed by clinicians verified against their regulator's public register.
Inside the algorithm
Editorial featureHow Aidoc reaches a verdict.
Five stages — from raw input to verdict — drawn from manufacturer documentation and the public regulatory record.
- INGEST
- NORMALISE
- DETECT
- LOCALISE
- VERDICT
Stage 01 · INGEST
Continuous CT acquisition is read in the background.
The aiOS™ platform sits behind the and inspects every CT examination as it arrives — non-contrast head, chest, abdomen, cervical spine, contrast-enhanced thoracic. The same pipeline analyses studies in the background regardless of the indication noted on the requisition.
No additional acquisition or contrast is required. The platform does not modify the image, drive the scanner, or queue a follow-up study; ingest is purely passive.
Input
DICOM CT series
Inference
Background, continuous
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 Aidoc device recalls or FDA safety communications have been identified in publicly available databases as of June 2026. The system is a triage overlay — it does not alter images or drive autonomous treatment — which limits the harm surface. Users should be aware of documented sensitivity degradation for subacute and small ICH subtypes (see clinical notes); reliance on a negative Aidoc flag for these subtypes without independent radiologist review is not warranted by the published performance data.
Intended Use & Indications
Aidoc's aiOS™ platform analyses non-contrast and contrast-enhanced CT examinations continuously in the background and raises structured triage flags when findings meeting algorithmic thresholds are detected. Cleared indications span intracranial haemorrhage (ICH), pulmonary embolism (PE), aortic dissection (type A and B), large and medium vessel occlusion, cervical-spine fracture, rib fracture, pneumothorax, incidental PE, and fourteen abdominal conditions via the CARE Multi-Triage CT Body module (K252970). The system is a clinical decision-support tool; final diagnostic and treatment decisions remain with the treating clinician.