Every claim we hold, and how far we can stand behind it.
142 claims across 39 products. 30% are confirmed against the source text by the evidence gate; 39% come from a class with no vendor interest. Everything below is browsable, filterable, and available as JSON.
| Evidence class | Claims | Confirmed | What it can support |
|---|---|---|---|
| Peer-reviewed study | 19 | 5 | Independent review before publication. The only class that survives a sceptical committee unaided. |
| Regulatory filing | 4 | 0 | A statement made to a regulator, where being wrong has consequences. |
| Independent report | 32 | 9 | Analysis by someone with no stake in the sale. |
| Customer case | 4 | 3 | A real deployment, but selected and framed by someone with an interest. |
| Press release | 63 | 23 | The vendor's own announcement. Useful for dates and facts, not for outcomes. |
| Vendor page | 20 | 2 | Marketing copy. Establishes what is claimed, never that it is true. |
Showing 19 of 19 matching claims (142 in the full corpus) · 26% of this selection is confirmed · clear filters
Real-world AI scribe study (JMIR 2026) participant on Heidi: My hospital has been piloting Heidi, and I have used it extensively in the emergency department (ED)
Provenance
- Claim ID
- clm_07d8295a7406b9118434
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13472498/
Peer-reviewed Nature Health study (SAFEMOM) of Ada integrated into South Africa's government-run MomConnect WhatsApp maternal health platform found safe health-seeking behavior rose nearly a third and appropriate care-seeking rose more than 40%; an independent physician panel rated Ada's recommendations safe in 98% of cases
Provenance
- Claim ID
- clm_e424d6e33e196547ba29
- Version
- 1
- Workflow
- Clinical Evidence & Decision Support
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://doi.org/10.1038/s44360-026-00125-x
JMIR Med Inform 2026 prospective study: Abridge was chosen as the AI platform and integrated with the Epic EMR at Hawaii Pacific Health Medical Group.
Provenance
- Claim ID
- clm_a5941d994b2af01d6698
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13289844/
JMIR Med Inform 2026: Abridge was chosen as the AI platform and integrated with the Epic EMR.
Provenance
- Claim ID
- clm_00b51ce1cd925912e9d6
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- interoperability
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13289844/
JMIR Med Inform 2026 prospective Abridge study: Signal metrics found a 21% decrease in time spent on notes per day among high users.
Provenance
- Claim ID
- clm_2d77987ee04fa4cb752f
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- economic value
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13289844/
Prospective multi-centre study (Open Forum Infectious Diseases, 2026) of qXR version 3 AI-based chest X-ray screening across 3 public health facilities in Chhattisgarh, India: of 2,745 CXRs screened, 363 patients were presumptive for TB and 162 confirmed cases were found (44.63% positivity among presumptive cases), and an 80.21% increase in TB case notifications was observed during the AI-implemented period versus baseline (P < .001).
Provenance
- Claim ID
- clm_326a114cde5f51400f91
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12810203/
Multi-country head-to-head accuracy comparison (Annals of the American Thoracic Society, 2026) of 7 automated chest X-ray algorithms on 3,901 chest X-rays from India, Madagascar, the Philippines, South Africa, Tanzania, Uganda, and Vietnam found qXR achieved the WHO minimum target accuracy for a tuberculosis triage test (>=90% sensitivity with >=70% specificity), with specificity of 70% or greater at 90% sensitivity.
Provenance
- Claim ID
- clm_36833a1aa15ec821791a
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://doi.org/10.1093/annalsats/aaoag011
Applied Clinical Informatics (2026): early implementation of DAX Copilot in a pediatric hematology-oncology division across 11,544 outpatient encounters (Jan-Jul 2025) found that for encounters of 40 minutes or less, median documentation time was 11 minutes with DAX versus 24 minutes without - an approximately 30% lower documentation time (95% CI 19.9-38.4%; p<0.001).
Provenance
- Claim ID
- clm_61a71bb995cf683609ed
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC13192280/
Real-world performance evaluation of the Aidoc Medical Briefcase ICH Triage model across 101,944 non-contrast head CT examinations from 74,142 patients in a 17-facility academic health system (April 2023-April 2025) demonstrated 82.2% sensitivity, 97.6% specificity, and 96.6% accuracy for intracranial hemorrhage detection (npj Digital Medicine).
Provenance
- Claim ID
- clm_c0fa19558e3ea5d6059f
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12823562/
NEJM AI randomized trial (Dec 2025): among 238 outpatient physicians across 14 specialties (Nov 4, 2024-Jan 3, 2025) randomized to Microsoft Dragon Ambient eXperience (DAX) Copilot, Nabla, or usual care, DAX was used in 33.5% of 24,696 visits; DAX users showed no significant change in time-in-note (-1.7%; 95% CI -9.4% to +5.9%; P=0.66) but significant improvements in burnout measures (Mini-Z +2.83; PTL -39.9) versus control.
Provenance
- Claim ID
- clm_dd375bd99918073f92db
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12768499/
Blinded PDQI-9 evaluation (Frontiers in Artificial Intelligence, 2025) of 97 clinical encounters across five specialties compared LLM-generated ambient notes from Suki's production system against physician-authored Gold notes: overall quality scores were comparable (4.20/5 ambient vs 4.25/5 gold, p = 0.04), ambient notes scored higher on thoroughness (4.22 vs 3.80, p < 0.001) and organization (p = 0.03), and reviewers overall preferred ambient notes 47% vs 39%, though hallucinations were detected in 31% of ambient vs 20% of gold notes (p = 0.01).
Provenance
- Claim ID
- clm_93f1e478d301f2abd57c
- Version
- 1
- Workflow
- Ambient Clinical Documentation
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12586549/
Meta-analysis of six retrospective real-world studies encompassing 9,102 CTPA scans, all assessing the Aidoc or CINA-PE FDA-approved algorithms for acute pulmonary embolism detection, found pooled sensitivity of 93% (95% CI 88%-95%) and specificity of 98% (95% CI 93%-100%) (Cureus).
Provenance
- Claim ID
- clm_15d57030cdd4dbabf213
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12604435/
Mayo Clinic study in J Prim Care Community Health (2025 Apr 16;16:21501319251332215, doi 10.1177/21501319251332215) found OpenEvidence 'provided accurate, evidence-based recommendations in all cases, aligning with physician plans' across five common chronic conditions, with mean scores of clarity 3.55±0.60, relevance 3.75±0.44, support 3.35±0.49, and satisfaction 3.60±0.60.
Provenance
- Claim ID
- clm_565ce01a474e2b680115
- Version
- 1
- Workflow
- Clinical Evidence & Decision Support
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC12033599/
CERTAIN study (European Heart Journal - Cardiovascular Imaging, 2024): in 750 consecutive patients at 5 expert CCTA sites, Cleerly AI-QCT analysis improved physicians' confidence two- to five-fold at every step of the care pathway, changed diagnosis or management in 57.1% (428) of patients (P<0.001), and reduced the need for downstream non-invasive and invasive testing by 37.1% (P<0.001) versus conventional visual CCTA interpretation.
Provenance
- Claim ID
- clm_a7d0185737df3457a3b3
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC11139521/
Journal of Investigative Dermatology study (Dulmage et al., 2021;141:1230-1235, doi 10.1016/j.jid.2020.08.027) of VisualDx's point-of-care AI system found 'The AI system achieved an accuracy of 68% in determining the single most likely morphology from the test image bank', while primary care physicians scored 36% without aids and 68% with a visual guide (P < 0.001); on 222 images across Fitzpatrick skin types the AI achieved 70% accuracy in Fitzpatrick I-III and 68% in Fitzpatrick IV-VI (P = 0.79).
Provenance
- Claim ID
- clm_19dcf624d235238fa2b7
- Version
- 1
- Workflow
- Clinical Evidence & Decision Support
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://doi.org/10.1016/j.jid.2020.08.027
Independent BMJ Open peer-reviewed vignette study (Gilbert et al., 2020) compared digital symptom assessment apps, including Ada, against GPs for suggesting conditions and urgency advice
Provenance
- Claim ID
- clm_796e5c36fb879e0a483b
- Version
- 1
- Workflow
- Clinical Evidence & Decision Support
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC7745718/
Lunit INSIGHT MMG (Lancet Digital Health 2020): the AI algorithm was developed and validated on 170,230 mammography examinations from five institutions; in a multicentre, observer-blinded reader study of 320 mammograms read by 14 radiologists, AI performance (AUROC 0.940) significantly exceeded radiologists without assistance (AUROC 0.810, p<0.0001), and AI assistance improved radiologists' performance to AUROC 0.881 (p<0.0001).
Provenance
- Claim ID
- clm_9953a345495ad65fe703
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://doi.org/10.1016/S2589-7500(20)30003-0
Cluster-randomized controlled trial in J Med Libr Assoc (2019 Apr 1;107(2):151-162, doi 10.5195/jmla.2019.581) evaluated VisualDx as a clinical evidence technology for skin problems in primary care: 'Thirty-two PCPs and 433 patients participated', and time from index visit to skin problem resolution was similar in both groups (hazard ratio=0.92; 95% CI 0.70, 1.21; p=0.54).
Provenance
- Claim ID
- clm_fa1a96f540b206b3d969
- Version
- 1
- Workflow
- Clinical Evidence & Decision Support
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://pmc.ncbi.nlm.nih.gov/articles/PMC6466492/
PLATFORM trial (JACC 2015): in 584 patients with suspected coronary disease, FFRCT-guided care reduced mean total medical costs by 32% in the planned-invasive stratum versus usual care ($7,343 vs $10,734; p<0.0001) over 90-day follow-up.
Provenance
- Claim ID
- clm_d313d88fef3ff93bd06f
- Version
- 1
- Workflow
- Imaging & Diagnostic AI
- Dimension
- evidence strength
- Retrieved
- 2026-08-27
- Reviewer
- healthit-gate-v1
- Source URL
- https://doi.org/10.1016/j.jacc.2015.09.051