{ "name": "FDA AI-Enabled Device Evidence Tracker", "publisher": "The Physician AI Handbook", "author": "Bryan Tegomoh, MD, MPH", "url": "https://physicianaihandbook.com/appendices/fda-ai-device-tracker.html", "license": "https://creativecommons.org/licenses/by/4.0/", "version": "1.0.0", "date_modified": "2026-10-30", "fda_source": { "list_page": "https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices", "csv_export": "https://www.fda.gov/media/178541/download?attachment", "retrieved": "2026-10-30", "list_page_content_current_as_of": "2026-09-04", "csv_sha256": "4db7f69d21acbf1632259a45b85d4744b5028f42313daa433b73020802d90402", "csv_sha256_note": "SHA-256 of the FDA CSV export with line endings normalized to LF" }, "grading": { "graded_on": "2026-10-30", "graded_device_families": 33, "by_grade": { "A": 8, "B": 11, "C": 13, "D": 1 }, "definitions": { "A": "Randomized trial, or prospective study with a concurrent comparison group, measuring patient outcomes or care processes with the device in clinical use; peer reviewed.", "B": "Prospective peer-reviewed accuracy or performance study in the intended population and setting, including published FDA pivotal studies.", "C": "Retrospective peer-reviewed validation only, such as reader studies on enriched case sets or retrospective cohorts.", "D": "No peer-reviewed study of the device found at the grading date; FDA decision summary only." } }, "summary": { "total": 1614, "earliest_decision_date": "1995-09-29", "latest_decision_date": "2026-06-29", "by_pathway": { "510(k)": 1553, "De Novo": 40, "PMA": 21 }, "by_panel": { "Radiology": 1230, "Cardiovascular": 154, "Neurology": 73, "Anesthesiology": 30, "Gastroenterology-Urology": 27, "Hematology": 22, "Pathology": 10, "Ophthalmic": 10, "General and Plastic Surgery": 9, "Clinical Chemistry": 9, "Orthopedic": 8, "Dental": 7, "Microbiology": 7, "General Hospital": 6, "Obstetrics and Gynecology": 5, "Clinical Toxcicology": 5, "Ear Nose & Throat": 1, "Immunology": 1 }, "by_year": { "1995": 2, "1997": 1, "1998": 2, "2001": 2, "2002": 1, "2004": 1, "2005": 1, "2006": 1, "2008": 5, "2010": 2, "2011": 3, "2012": 5, "2013": 4, "2014": 6, "2015": 6, "2016": 18, "2017": 27, "2018": 65, "2019": 80, "2020": 114, "2021": 129, "2022": 162, "2023": 226, "2024": 235, "2025": 335, "2026": 181 }, "by_year_pathway": { "1995": { "510(k)": 0, "De Novo": 0, "PMA": 2 }, "1997": { "510(k)": 1, "De Novo": 0, "PMA": 0 }, "1998": { "510(k)": 0, "De Novo": 0, "PMA": 2 }, "2001": { "510(k)": 1, "De Novo": 0, "PMA": 1 }, "2002": { "510(k)": 0, "De Novo": 0, "PMA": 1 }, "2004": { "510(k)": 1, "De Novo": 0, "PMA": 0 }, "2005": { "510(k)": 1, "De Novo": 0, "PMA": 0 }, "2006": { "510(k)": 0, "De Novo": 0, "PMA": 1 }, "2008": { "510(k)": 5, "De Novo": 0, "PMA": 0 }, "2010": { "510(k)": 2, "De Novo": 0, "PMA": 0 }, "2011": { "510(k)": 2, "De Novo": 0, "PMA": 1 }, "2012": { "510(k)": 4, "De Novo": 0, "PMA": 1 }, "2013": { "510(k)": 3, "De Novo": 1, "PMA": 0 }, "2014": { "510(k)": 5, "De Novo": 1, "PMA": 0 }, "2015": { "510(k)": 6, "De Novo": 0, "PMA": 0 }, "2016": { "510(k)": 17, "De Novo": 0, "PMA": 1 }, "2017": { "510(k)": 23, "De Novo": 2, "PMA": 2 }, "2018": { "510(k)": 58, "De Novo": 7, "PMA": 0 }, "2019": { "510(k)": 80, "De Novo": 0, "PMA": 0 }, "2020": { "510(k)": 113, "De Novo": 1, "PMA": 0 }, "2021": { "510(k)": 122, "De Novo": 6, "PMA": 1 }, "2022": { "510(k)": 160, "De Novo": 1, "PMA": 1 }, "2023": { "510(k)": 219, "De Novo": 6, "PMA": 1 }, "2024": { "510(k)": 225, "De Novo": 9, "PMA": 1 }, "2025": { "510(k)": 329, "De Novo": 2, "PMA": 4 }, "2026": { "510(k)": 176, "De Novo": 4, "PMA": 1 } } }, "changelog": [ { "version": "1.0.0", "date": "2026-10-30", "change": "First release. FDA list downloaded October 30, 2026 (list page content current as of September 4, 2026); 33 device families graded." } ], "graded_devices": [ { "tracker_id": "viz-lvo", "device_family": "Viz LVO (ContaCT)", "company": "Viz.ai", "specialty": "Radiology: stroke imaging", "representative_submission": "DEN170073", "function": "Flags suspected large vessel occlusion on CT angiography and alerts the stroke team by phone", "evidence_grade": "A", "study_label": "Martinez-Gutierrez et al., 2023, JAMA Neurology", "study_doi": "10.1001/jamaneurol.2023.3206", "study_design": "Stepped-wedge cluster randomized trial at 4 comprehensive stroke centers; 243 patients treated with thrombectomy", "study_finding": "Door-to-groin time was 11.2 minutes shorter after activation of automated LVO detection with secure messaging (95% CI 4.2 to 18.2); functional independence did not differ in exploratory analysis (odds ratio 1.3, 95% CI 0.42 to 4.0)", "second_study_label": "Sachdev et al., 2026, AJNR", "second_study_doi": "10.3174/ajnr.A9418", "second_study_note": "Retrospective single-center comparison: Viz.ai detected 108 of 147 LVOs (73%) on CT angiography versus 144 (98%) for RapidAI", "outcome_direction": "Favorable (care process)", "version_link": "Trial used the Viz.AI LVO software; version not reported in the abstract", "evidence_basis": "Full text (trial); abstract (comparison)", "notes": "Process outcome; the trial was not powered for functional outcome. Cluster activation order was random except that the academic center went last.", "representative_pathway": "De Novo", "representative_decision_date": "2018-02-13", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN170073", "first_listed_submission": "DEN170073", "first_listed_decision_date": "2018-02-13", "latest_listed_submission": "K223042", "latest_listed_decision_date": "2022-10-21", "listed_submission_count": "2", "listed_submissions": "DEN170073;K223042", "study_url": "https://doi.org/10.1001/jamaneurol.2023.3206", "second_study_url": "https://doi.org/10.3174/ajnr.A9418" }, { "tracker_id": "rapid-lvo", "device_family": "Rapid LVO", "company": "iSchemaView (RapidAI)", "specialty": "Radiology: stroke imaging", "representative_submission": "K200941", "function": "Flags suspected large vessel occlusion on CT angiography for triage", "evidence_grade": "C", "study_label": "Sachdev et al., 2026, AJNR", "study_doi": "10.3174/ajnr.A9418", "study_design": "Retrospective review of 1,589 consecutive stroke alerts at one comprehensive stroke center, both products run in parallel", "study_finding": "RapidAI detected 144 of 147 LVOs (98%) compared with 108 (73%) for Viz.ai, and correctly classified 94% versus 91% of LVO-negative cases", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Version not reported in the abstract", "evidence_basis": "Abstract", "notes": "Single center. No randomized or prospective outcome study of this product was found.", "representative_pathway": "510(k)", "representative_decision_date": "2020-07-09", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K200941", "first_listed_submission": "K200941", "first_listed_decision_date": "2020-07-09", "latest_listed_submission": "K221248", "latest_listed_decision_date": "2022-05-31", "listed_submission_count": "2", "listed_submissions": "K200941;K221248", "study_url": "https://doi.org/10.3174/ajnr.A9418", "second_study_url": "" }, { "tracker_id": "aidoc-briefcase-ich", "device_family": "Aidoc BriefCase (intracranial hemorrhage triage)", "company": "Aidoc", "specialty": "Radiology: neuroimaging", "representative_submission": "K180647", "function": "Triage and notification software for CT findings; this row grades the intracranial hemorrhage module only", "evidence_grade": "C", "study_label": "Chavoshi et al., 2025, npj Digital Medicine", "study_doi": "10.1038/s41746-025-02244-3", "study_design": "Retrospective evaluation of 101,944 non-contrast head CTs in a 17-facility academic health system; reference labels extracted from reports by a language model", "study_finding": "Sensitivity 82.2% and specificity 97.6% for detecting intracranial hemorrhage; sensitivity was lower for subacute (45.5%) and chronic (54.8%) bleeds", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Commercial BriefCase ICH Triage as deployed 2023 to 2025", "evidence_basis": "Full text", "notes": "Listed BriefCase triage entries cover several findings; evidence for the hemorrhage module does not transfer to other modules.", "representative_pathway": "510(k)", "representative_decision_date": "2018-08-01", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K180647", "first_listed_submission": "K180647", "first_listed_decision_date": "2018-08-01", "latest_listed_submission": "K261317", "latest_listed_decision_date": "2026-05-14", "listed_submission_count": "27", "listed_submissions": "K180647;K190072;K190896;K192383;K193298;K201020;K203508;K214043;K213721;K213886;K221240;K221314;K222277;K222329;K220709;K221330;K222692;K230020;K232751;K241727;K242837;K243548;K250248;K251406;K253265;K251195;K261317", "study_url": "https://doi.org/10.1038/s41746-025-02244-3", "second_study_url": "" }, { "tracker_id": "aidoc-care", "device_family": "Aidoc CARE multi-triage CT", "company": "Aidoc", "specialty": "Radiology: body CT", "representative_submission": "K252970", "function": "Foundation-model triage of multiple acute findings on CT", "evidence_grade": "D", "study_label": "", "study_doi": "", "study_design": "No peer-reviewed study of the cleared product found", "study_finding": "FDA 510(k) summary is the only public performance source located", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Not assessed", "version_link": "", "evidence_basis": "PubMed search, 2026-10-30", "notes": "Grade D reflects absent published evidence at the grading date, not evidence of poor performance.", "representative_pathway": "510(k)", "representative_decision_date": "2026-01-07", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K252970", "first_listed_submission": "K252970", "first_listed_decision_date": "2026-01-07", "latest_listed_submission": "K253578", "latest_listed_decision_date": "2026-02-26", "listed_submission_count": "2", "listed_submissions": "K252970;K253578", "study_url": "", "second_study_url": "" }, { "tracker_id": "transpara", "device_family": "Transpara", "company": "ScreenPoint Medical", "specialty": "Radiology: breast screening", "representative_submission": "K181704", "function": "Assigns a malignancy risk score to screening mammograms and marks suspicious regions", "evidence_grade": "A", "study_label": "Lång et al., 2023, Lancet Oncology (MASAI)", "study_doi": "10.1016/S1470-2045(23)00298-X", "study_design": "Randomised, controlled, non-inferiority screening-accuracy trial at 4 Swedish screening sites; 80,033 women; prespecified clinical safety analysis", "study_finding": "Cancer detection was 6.1 versus 5.1 per 1,000 screened with AI-supported versus standard double reading (ratio 1.2, 95% CI 1.0 to 1.5), with 44.3% lower screen-reading workload", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable for workload; the higher detection rate was not statistically significant (p=0.052)", "version_link": "Transpara 1.7.0, which is on the FDA list as K210404", "evidence_basis": "Abstract", "notes": "The trial's primary endpoint, interval cancer rate, was still in follow-up at this publication. Swedish double-reading workflow.", "representative_pathway": "510(k)", "representative_decision_date": "2018-11-21", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K181704", "first_listed_submission": "K181704", "first_listed_decision_date": "2018-11-21", "latest_listed_submission": "K241831", "latest_listed_decision_date": "2024-11-25", "listed_submission_count": "6", "listed_submissions": "K181704;K192287;K193229;K210404;K221347;K241831", "study_url": "https://doi.org/10.1016/S1470-2045(23)00298-X", "second_study_url": "" }, { "tracker_id": "lunit-insight-mmg", "device_family": "Lunit INSIGHT MMG", "company": "Lunit", "specialty": "Radiology: breast screening", "representative_submission": "K211678", "function": "Detects and scores suspicious findings on screening mammograms", "evidence_grade": "B", "study_label": "Dembrower et al., 2023, Lancet Digital Health (ScreenTrustCAD)", "study_doi": "10.1016/S2589-7500(23)00153-X", "study_design": "Prospective, population-based, paired-reader non-inferiority study at one Stockholm hospital; 55,581 women", "study_finding": "One radiologist plus AI detected 261 cancers versus 250 for two radiologists (relative proportion 1.04, 95% CI 1.00 to 1.09)", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (detection)", "version_link": "INSIGHT MMG version 1.1.6", "evidence_basis": "Full text", "notes": "Single site, Philips equipment, Swedish double reading with consensus. Funding included Lunit.", "representative_pathway": "510(k)", "representative_decision_date": "2021-11-17", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K211678", "first_listed_submission": "K211678", "first_listed_decision_date": "2021-11-17", "latest_listed_submission": "K260320", "latest_listed_decision_date": "2026-04-23", "listed_submission_count": "2", "listed_submissions": "K211678;K260320", "study_url": "https://doi.org/10.1016/S2589-7500(23)00153-X", "second_study_url": "" }, { "tracker_id": "icad-dbt", "device_family": "PowerLook Tomo Detection / ProFound AI for DBT", "company": "iCAD", "specialty": "Radiology: breast screening", "representative_submission": "P160009", "function": "Detects suspicious soft-tissue lesions and calcifications on digital breast tomosynthesis", "evidence_grade": "C", "study_label": "Conant et al., 2019, Radiology: Artificial Intelligence", "study_doi": "10.1148/ryai.2019180096", "study_design": "Retrospective multireader study; 24 radiologists read 260 DBT exams (65 cancers) with and without AI", "study_finding": "Reader AUC for detecting malignant lesions rose from 0.795 without AI to 0.852 with AI; reading time fell 52.7%", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (reader study)", "version_link": "PowerLook Tomo Detection 2.0, on the FDA list as K182373", "evidence_basis": "Full text", "notes": "Enriched case set; several authors were iCAD employees.", "representative_pathway": "PMA", "representative_decision_date": "2017-03-24", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpma/pma.cfm?id=P160009", "first_listed_submission": "P160009", "first_listed_decision_date": "2017-03-24", "latest_listed_submission": "K240417", "latest_listed_decision_date": "2024-11-08", "listed_submission_count": "5", "listed_submissions": "P160009;K182373;K191994;K203822;K240417", "study_url": "https://doi.org/10.1148/ryai.2019180096", "second_study_url": "" }, { "tracker_id": "koios-ds", "device_family": "Koios DS", "company": "Koios Medical", "specialty": "Radiology: breast ultrasound", "representative_submission": "K190442", "function": "Classifies breast ultrasound lesions into risk categories", "evidence_grade": "C", "study_label": "Mango et al., 2020, AJR", "study_doi": "10.2214/AJR.19.21872", "study_design": "Retrospective multicenter reader study; 900 lesions read by 15 physicians with and without decision support", "study_finding": "Mean reader AUC for classifying lesions rose from 0.83 with ultrasound alone to 0.87 with decision support", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (reader study)", "version_link": "Koios DS for Breast", "evidence_basis": "Abstract", "notes": "Enriched case mix (47.8% malignant).", "representative_pathway": "510(k)", "representative_decision_date": "2019-07-03", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K190442", "first_listed_submission": "K190442", "first_listed_decision_date": "2019-07-03", "latest_listed_submission": "K242130", "latest_listed_decision_date": "2024-11-15", "listed_submission_count": "3", "listed_submissions": "K190442;K212616;K242130", "study_url": "https://doi.org/10.2214/AJR.19.21872", "second_study_url": "" }, { "tracker_id": "annalise-cxr", "device_family": "Annalise Enterprise CXR", "company": "Annalise-AI (Harrison.ai)", "specialty": "Radiology: chest radiography", "representative_submission": "K213941", "function": "Triage of specified findings on chest radiographs, such as pneumothorax", "evidence_grade": "C", "study_label": "Seah et al., 2021, Lancet Digital Health", "study_doi": "10.1016/S2589-7500(21)00106-0", "study_design": "Retrospective multireader multicase study; 20 radiologists, 2,568 enriched cases, 127 findings", "study_finding": "Macroaveraged reader AUC across 127 findings rose from 0.713 unassisted to 0.808 with the model", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (reader study)", "version_link": "Multi-finding research model underlying Annalise CXR; FDA entries cover triage of specific findings, not all findings studied", "evidence_basis": "Abstract", "notes": "Company-funded and largely company-authored.", "representative_pathway": "510(k)", "representative_decision_date": "2022-02-24", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K213941", "first_listed_submission": "K213941", "first_listed_decision_date": "2022-02-24", "latest_listed_submission": "K222268", "latest_listed_decision_date": "2023-03-28", "listed_submission_count": "3", "listed_submissions": "K213941;K222179;K222268", "study_url": "https://doi.org/10.1016/S2589-7500(21)00106-0", "second_study_url": "" }, { "tracker_id": "lunit-insight-cxr", "device_family": "Lunit INSIGHT CXR Triage", "company": "Lunit", "specialty": "Radiology: chest radiography", "representative_submission": "K211733", "function": "Sorts chest radiographs into normal, non-urgent, and urgent for worklist triage", "evidence_grade": "B", "study_label": "Sridharan et al., 2024, European Journal of Radiology", "study_doi": "10.1016/j.ejrad.2024.111783", "study_design": "Prospective clinical evaluation in Singapore (authors' design label); 43 radiologists blinded to AI output", "study_finding": "For the urgent category, sensitivity 82% and specificity 99% against radiologist classification", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "LUNIT INSIGHT CXR Triage", "evidence_basis": "Abstract", "notes": "Graded from the abstract; site count not stated there.", "representative_pathway": "510(k)", "representative_decision_date": "2021-11-10", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K211733", "first_listed_submission": "K211733", "first_listed_decision_date": "2021-11-10", "latest_listed_submission": "K211733", "latest_listed_decision_date": "2021-11-10", "listed_submission_count": "1", "listed_submissions": "K211733", "study_url": "https://doi.org/10.1016/j.ejrad.2024.111783", "second_study_url": "" }, { "tracker_id": "gleamer-boneview", "device_family": "BoneView", "company": "Gleamer", "specialty": "Radiology: musculoskeletal", "representative_submission": "K212365", "function": "Identifies and highlights fractures on radiographs as a concurrent reading aid", "evidence_grade": "C", "study_label": "Guermazi et al., 2022, Radiology", "study_doi": "10.1148/radiol.210937", "study_design": "Retrospective multireader multicase study; 480 exams, 24 readers from six specialties, fracture prevalence set at 50%", "study_finding": "Per-patient sensitivity for fractures rose from 64.8% without AI to 75.2% with AI; specificity was noninferior", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (reader study)", "version_link": "Gleamer BoneView", "evidence_basis": "Abstract and publisher methods", "notes": "Funded by Gleamer, which built the study sample and design.", "representative_pathway": "510(k)", "representative_decision_date": "2022-03-01", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K212365", "first_listed_submission": "K212365", "first_listed_decision_date": "2022-03-01", "latest_listed_submission": "K222176", "latest_listed_decision_date": "2023-03-02", "listed_submission_count": "2", "listed_submissions": "K212365;K222176", "study_url": "https://doi.org/10.1148/radiol.210937", "second_study_url": "" }, { "tracker_id": "optellum-vnc", "device_family": "Optellum Virtual Nodule Clinic", "company": "Optellum", "specialty": "Radiology: chest CT", "representative_submission": "K202300", "function": "Estimates malignancy risk for indeterminate pulmonary nodules on CT", "evidence_grade": "C", "study_label": "Kim et al., 2022, Radiology", "study_doi": "10.1148/radiol.212182", "study_design": "Retrospective multireader multicase study; 300 chest CTs, 12 readers (radiologists and pulmonologists)", "study_finding": "Readers' average AUC for malignancy rose from 0.82 to 0.89 with the tool; interobserver agreement improved", "second_study_label": "Massion et al., 2020, AJRCCM", "second_study_doi": "10.1164/rccm.201903-0505OC", "second_study_note": "Development and retrospective external validation of the underlying LCP-CNN model", "outcome_direction": "Favorable (reader study)", "version_link": "Virtual Nodule Clinic version 2.0.0", "evidence_basis": "Full text", "notes": "Enriched set, 50% malignant.", "representative_pathway": "510(k)", "representative_decision_date": "2021-03-05", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K202300", "first_listed_submission": "K202300", "first_listed_decision_date": "2021-03-05", "latest_listed_submission": "K202300", "latest_listed_decision_date": "2021-03-05", "listed_submission_count": "1", "listed_submissions": "K202300", "study_url": "https://doi.org/10.1148/radiol.212182", "second_study_url": "https://doi.org/10.1164/rccm.201903-0505OC" }, { "tracker_id": "heartflow-ffrct", "device_family": "HeartFlow FFRct Analysis", "company": "HeartFlow", "specialty": "Cardiology: coronary CT", "representative_submission": "K152733", "function": "Computes fractional flow reserve from coronary CT angiography", "evidence_grade": "A", "study_label": "Curzen et al., 2021, European Heart Journal (FORECAST)", "study_doi": "10.1093/eurheartj/ehab444", "study_design": "Randomized trial; 1,400 patients with stable chest pain at 11 UK centres", "study_finding": "CT angiography with selective FFRct did not change 9-month cardiac costs or major adverse events compared with standard care, but reduced invasive angiography (19% versus 25%)", "second_study_label": "Douglas et al., 2015, European Heart Journal (PLATFORM)", "second_study_doi": "10.1093/eurheartj/ehv444", "second_study_note": "Prospective multicenter comparison of consecutive cohorts at 11 sites: among patients with planned invasive angiography, no obstructive disease was found in 12% with FFRct-guided care versus 73% with usual care", "outcome_direction": "Mixed (fewer invasive tests; no cost or event difference)", "version_link": "Earlier HeartFlow versions; the first entry on the FDA list is K152733", "evidence_basis": "Abstract", "notes": "Earlier HeartFlow authorizations that are not on the FDA AI list are not shown.", "representative_pathway": "510(k)", "representative_decision_date": "2016-01-13", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K152733", "first_listed_submission": "K152733", "first_listed_decision_date": "2016-01-13", "latest_listed_submission": "K250902", "latest_listed_decision_date": "2025-07-18", "listed_submission_count": "7", "listed_submissions": "K152733;K161772;K182035;K190925;K203329;K213857;K250902", "study_url": "https://doi.org/10.1093/eurheartj/ehab444", "second_study_url": "https://doi.org/10.1093/eurheartj/ehv444" }, { "tracker_id": "cathworks-ffrangio", "device_family": "FFRangio", "company": "CathWorks", "specialty": "Cardiology: invasive angiography", "representative_submission": "K182149", "function": "Derives fractional flow reserve from routine coronary angiograms", "evidence_grade": "B", "study_label": "Fearon et al., 2019, Circulation (FAST-FFR)", "study_doi": "10.1161/CIRCULATIONAHA.118.037350", "study_design": "Prospective multicenter international accuracy study; 10 centers, 301 patients, 319 vessels", "study_finding": "Per-vessel sensitivity 94% and specificity 91% for predicting pressure-wire FFR of 0.80 or less", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "FFRangio as used in FAST-FFR", "evidence_basis": "Abstract", "notes": "", "representative_pathway": "510(k)", "representative_decision_date": "2018-12-19", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K182149", "first_listed_submission": "K182149", "first_listed_decision_date": "2018-12-19", "latest_listed_submission": "K192442", "latest_listed_decision_date": "2019-12-09", "listed_submission_count": "2", "listed_submissions": "K182149;K192442", "study_url": "https://doi.org/10.1161/CIRCULATIONAHA.118.037350", "second_study_url": "" }, { "tracker_id": "caption-guidance", "device_family": "Caption Guidance", "company": "Caption Health (Bay Labs at authorization)", "specialty": "Cardiology: echocardiography", "representative_submission": "DEN190040", "function": "Guides novice operators in real time to acquire diagnostic echocardiographic views", "evidence_grade": "B", "study_label": "Narang et al., 2021, JAMA Cardiology", "study_doi": "10.1001/jamacardio.2021.0185", "study_design": "Prospective multicenter diagnostic study at 2 hospitals; 8 nurses without echo experience scanned 240 patients", "study_finding": "Nurse scans with AI guidance were judged diagnostic for left ventricular size, function, and pericardial effusion in 237 of 240 patients (98.8%)", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (image acquisition)", "version_link": "Deep-learning guidance software as tested in 2019", "evidence_basis": "Abstract", "notes": "Measures image quality, not patient outcomes.", "representative_pathway": "De Novo", "representative_decision_date": "2020-02-07", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN190040", "first_listed_submission": "DEN190040", "first_listed_decision_date": "2020-02-07", "latest_listed_submission": "K243065", "latest_listed_decision_date": "2025-01-15", "listed_submission_count": "4", "listed_submissions": "DEN190040;K200755;K201992;K243065", "study_url": "https://doi.org/10.1001/jamacardio.2021.0185", "second_study_url": "" }, { "tracker_id": "us2ai", "device_family": "Us2.ai", "company": "Us2.ai (Eko.ai Pte. Ltd.)", "specialty": "Cardiology: echocardiography", "representative_submission": "K210791", "function": "Automated echocardiographic measurement and reporting", "evidence_grade": "C", "study_label": "Tromp et al., 2022, Lancet Digital Health", "study_doi": "10.1016/S2589-7500(21)00235-1", "study_design": "Multicohort validation against manual measurements in existing datasets, with a 142-study prospective re-measurement subset", "study_finding": "Automated measurements agreed with expert sonographer measurements across cohorts from Asia, Canada, Taiwan, and the US", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Research workflow underlying the product", "evidence_basis": "Abstract", "notes": "Graded conservatively: the prospective component is a small re-measurement subset.", "representative_pathway": "510(k)", "representative_decision_date": "2021-07-27", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K210791", "first_listed_submission": "K210791", "first_listed_decision_date": "2021-07-27", "latest_listed_submission": "K233676", "latest_listed_decision_date": "2024-04-01", "listed_submission_count": "2", "listed_submissions": "K210791;K233676", "study_url": "https://doi.org/10.1016/S2589-7500(21)00235-1", "second_study_url": "" }, { "tracker_id": "echogo-hf", "device_family": "EchoGo Heart Failure", "company": "Ultromics", "specialty": "Cardiology: echocardiography", "representative_submission": "K240013", "function": "Detects heart failure with preserved ejection fraction from one apical four-chamber echo clip", "evidence_grade": "C", "study_label": "Akerman et al., 2023, JACC: Advances", "study_doi": "10.1016/j.jacadv.2023.100452", "study_design": "Model development with an independent multisite test set of 646 cases and 638 controls", "study_finding": "In independent testing, sensitivity 87.8% for identifying HFpEF; 7.3% of studies were nondiagnostic", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Research model preceding EchoGo Heart Failure 2.0", "evidence_basis": "Full text", "notes": "Case-control design; supported by Ultromics.", "representative_pathway": "510(k)", "representative_decision_date": "2024-09-23", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K240013", "first_listed_submission": "K240013", "first_listed_decision_date": "2024-09-23", "latest_listed_submission": "K240013", "latest_listed_decision_date": "2024-09-23", "listed_submission_count": "1", "listed_submissions": "K240013", "study_url": "https://doi.org/10.1016/j.jacadv.2023.100452", "second_study_url": "" }, { "tracker_id": "anumana-ecg-ai-lef", "device_family": "ECG-AI Low Ejection Fraction", "company": "Anumana", "specialty": "Cardiology: electrocardiography", "representative_submission": "K232699", "function": "Flags adults likely to have low left ventricular ejection fraction from a 12-lead ECG", "evidence_grade": "A", "study_label": "Yao et al., 2021, Nature Medicine (EAGLE)", "study_doi": "10.1038/s41591-021-01335-4", "study_design": "Pragmatic cluster randomized trial; 120 primary care teams, 45 clinics, 22,641 adults", "study_finding": "New diagnoses of low EF within 90 days were 2.1% with AI results versus 1.6% with usual care (odds ratio 1.32)", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (diagnosis yield)", "version_link": "Trial tested the Mayo Clinic AI-ECG algorithm later licensed to Anumana; trial threshold EF 50% or less, cleared indication EF 40% or less", "evidence_basis": "Abstract", "notes": "Outcome is new diagnosis, not clinical events.", "representative_pathway": "510(k)", "representative_decision_date": "2023-09-28", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K232699", "first_listed_submission": "K232699", "first_listed_decision_date": "2023-09-28", "latest_listed_submission": "K250652", "latest_listed_decision_date": "2025-07-28", "listed_submission_count": "2", "listed_submissions": "K232699;K250652", "study_url": "https://doi.org/10.1038/s41591-021-01335-4", "second_study_url": "" }, { "tracker_id": "eko-low-ef", "device_family": "Eko Low Ejection Fraction Tool (ELEFT)", "company": "Eko Health", "specialty": "Cardiology: point-of-care screening", "representative_submission": "K233409", "function": "Flags low ejection fraction from single-lead ECG recorded by an ECG-enabled stethoscope", "evidence_grade": "B", "study_label": "Bachtiger et al., 2022, Lancet Digital Health", "study_doi": "10.1016/S2589-7500(21)00256-9", "study_design": "Prospective, observational, multicentre study in London; 1,050 patients referred for echocardiography", "study_finding": "AUROC 0.85 for identifying LVEF of 40% or lower at the pulmonary auscultation position", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "AI-ECG retrained for single-lead input on the Eko DUO stethoscope; equivalence to the cleared tool is not stated", "evidence_basis": "Full text", "notes": "", "representative_pathway": "510(k)", "representative_decision_date": "2024-03-28", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K233409", "first_listed_submission": "K233409", "first_listed_decision_date": "2024-03-28", "latest_listed_submission": "K233409", "latest_listed_decision_date": "2024-03-28", "listed_submission_count": "1", "listed_submissions": "K233409", "study_url": "https://doi.org/10.1016/S2589-7500(21)00256-9", "second_study_url": "" }, { "tracker_id": "eko-murmur", "device_family": "Eko Murmur Analysis Software", "company": "Eko Health", "specialty": "Cardiology: auscultation", "representative_submission": "K213794", "function": "Detects heart murmurs from digital stethoscope recordings", "evidence_grade": "B", "study_label": "Chorba et al., 2021, Journal of the American Heart Association", "study_doi": "10.1161/JAHA.120.019905", "study_design": "Algorithm trained on prior recordings and tested in 962 patients enrolled in a prospective clinical study (NCT03458806)", "study_finding": "Sensitivity 76.3% and specificity 91.4% for detecting murmurs against echocardiography and expert annotation", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Eko murmur detection algorithm as described in 2021; an earlier Eko Analysis Software entry (K192004) is also on the FDA list", "evidence_basis": "Full text", "notes": "", "representative_pathway": "510(k)", "representative_decision_date": "2022-06-29", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K213794", "first_listed_submission": "K213794", "first_listed_decision_date": "2022-06-29", "latest_listed_submission": "K213794", "latest_listed_decision_date": "2022-06-29", "listed_submission_count": "1", "listed_submissions": "K213794", "study_url": "https://doi.org/10.1161/JAHA.120.019905", "second_study_url": "" }, { "tracker_id": "apple-irnf", "device_family": "Irregular Rhythm Notification Feature", "company": "Apple", "specialty": "Cardiology: consumer wearables", "representative_submission": "K212516", "function": "Notifies smartwatch users of pulse irregularity suggestive of atrial fibrillation", "evidence_grade": "B", "study_label": "Perez et al., 2019, NEJM (Apple Heart Study)", "study_doi": "10.1056/NEJMoa1901183", "study_design": "Prospective, siteless, single-arm pragmatic study; 419,297 participants", "study_finding": "0.52% received notifications; positive predictive value 0.84 for atrial fibrillation on a simultaneously worn ECG patch", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Algorithm version studied predates the first listed entry", "evidence_basis": "Abstract", "notes": "Funded by Apple. No comparison group.", "representative_pathway": "510(k)", "representative_decision_date": "2021-10-22", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K212516", "first_listed_submission": "K212516", "first_listed_decision_date": "2021-10-22", "latest_listed_submission": "K231173", "latest_listed_decision_date": "2023-07-21", "listed_submission_count": "2", "listed_submissions": "K212516;K231173", "study_url": "https://doi.org/10.1056/NEJMoa1901183", "second_study_url": "" }, { "tracker_id": "tempus-ecg-af", "device_family": "Tempus ECG-AF", "company": "Tempus AI", "specialty": "Cardiology: electrocardiography", "representative_submission": "K233549", "function": "Estimates risk of developing atrial fibrillation from a 12-lead ECG", "evidence_grade": "C", "study_label": "Raghunath et al., 2021, Circulation", "study_doi": "10.1161/CIRCULATIONAHA.120.047829", "study_design": "Retrospective development and validation on 1.6 million ECGs from 430,000 patients at one health system", "study_finding": "AUROC 0.85 for predicting new-onset atrial fibrillation within 1 year", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Geisinger research model; Tempus co-authors and funding", "evidence_basis": "Full text", "notes": "", "representative_pathway": "510(k)", "representative_decision_date": "2024-06-21", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K233549", "first_listed_submission": "K233549", "first_listed_decision_date": "2024-06-21", "latest_listed_submission": "K233549", "latest_listed_decision_date": "2024-06-21", "listed_submission_count": "1", "listed_submissions": "K233549", "study_url": "https://doi.org/10.1161/CIRCULATIONAHA.120.047829", "second_study_url": "" }, { "tracker_id": "viz-hcm", "device_family": "Viz HCM", "company": "Viz.ai", "specialty": "Cardiology: electrocardiography", "representative_submission": "DEN230003", "function": "Flags suspected hypertrophic cardiomyopathy on a 12-lead ECG", "evidence_grade": "C", "study_label": "Hillis et al., 2025, Circulation: Heart Failure", "study_doi": "10.1161/CIRCHEARTFAILURE.124.012667", "study_design": "Retrospective case selection at 3 hospitals; 293 HCM-positive and 2,912 HCM-negative cases", "study_finding": "Sensitivity 68.4% and specificity 99.1% for detecting HCM; positive predictive value 13.7% at an assumed 1-in-500 prevalence", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Viz HCM device", "evidence_basis": "Abstract", "notes": "", "representative_pathway": "De Novo", "representative_decision_date": "2023-08-03", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN230003", "first_listed_submission": "DEN230003", "first_listed_decision_date": "2023-08-03", "latest_listed_submission": "DEN230003", "latest_listed_decision_date": "2023-08-03", "listed_submission_count": "1", "listed_submissions": "DEN230003", "study_url": "https://doi.org/10.1161/CIRCHEARTFAILURE.124.012667", "second_study_url": "" }, { "tracker_id": "edwards-hpi", "device_family": "Acumen Hypotension Prediction Index", "company": "Edwards Lifesciences", "specialty": "Anesthesiology: intraoperative monitoring", "representative_submission": "DEN160044", "function": "Predicts intraoperative hypotension from the arterial waveform", "evidence_grade": "A", "study_label": "Wijnberge et al., 2020, JAMA (HYPE)", "study_doi": "10.1001/jama.2020.0592", "study_design": "Single-center randomized trial; 68 patients undergoing elective noncardiac surgery", "study_finding": "Median time-weighted average of hypotension was 0.10 mm Hg with the early warning system versus 0.44 mm Hg with standard care", "second_study_label": "Maheshwari et al., 2020, Anesthesiology", "second_study_doi": "10.1097/ALN.0000000000003557", "second_study_note": "Randomized pilot trial, 214 patients: index guidance did not reduce hypotension; half of alerts were not followed by treatment", "outcome_direction": "Mixed (one positive and one null randomized trial)", "version_link": "Hypotension Prediction Index software", "evidence_basis": "Full text (HYPE); abstract (Maheshwari)", "notes": "Benefit depended on a treatment protocol and on clinicians acting on alerts.", "representative_pathway": "De Novo", "representative_decision_date": "2018-03-16", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN160044", "first_listed_submission": "DEN160044", "first_listed_decision_date": "2018-03-16", "latest_listed_submission": "K183646", "latest_listed_decision_date": "2019-05-21", "listed_submission_count": "2", "listed_submissions": "DEN160044;K183646", "study_url": "https://doi.org/10.1001/jama.2020.0592", "second_study_url": "https://doi.org/10.1097/ALN.0000000000003557" }, { "tracker_id": "idx-dr", "device_family": "IDx-DR (LumineticsCore)", "company": "Digital Diagnostics", "specialty": "Ophthalmology: diabetic retinopathy", "representative_submission": "DEN180001", "function": "Autonomous detection of more-than-mild diabetic retinopathy in primary care", "evidence_grade": "A", "study_label": "Wolf et al., 2024, Nature Communications (ACCESS)", "study_doi": "10.1038/s41467-023-44676-z", "study_design": "Parallel randomized controlled trial; 164 youth aged 8 to 21 with diabetes at one pediatric center", "study_finding": "Diabetic eye exam completion within 6 months was 100% with point-of-care autonomous AI versus 22% with referral", "second_study_label": "Abràmoff et al., 2018, npj Digital Medicine", "second_study_doi": "10.1038/s41746-018-0040-6", "second_study_note": "Prospective pivotal trial, 900 adults at primary care sites: sensitivity 87.2% and specificity 90.7% for detecting more-than-mild DR against reading-center grading", "outcome_direction": "Favorable (exam completion)", "version_link": "IDx-DR as authorized in 2018; the trial population was younger than the adult indication", "evidence_basis": "Full text", "notes": "ACCESS tested youth, outside the adult indication of the 2018 authorization.", "representative_pathway": "De Novo", "representative_decision_date": "2018-04-11", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN180001", "first_listed_submission": "DEN180001", "first_listed_decision_date": "2018-04-11", "latest_listed_submission": "K213037", "latest_listed_decision_date": "2022-06-17", "listed_submission_count": "3", "listed_submissions": "DEN180001;K203629;K213037", "study_url": "https://doi.org/10.1038/s41467-023-44676-z", "second_study_url": "https://doi.org/10.1038/s41746-018-0040-6" }, { "tracker_id": "eyeart", "device_family": "EyeArt", "company": "Eyenuk", "specialty": "Ophthalmology: diabetic retinopathy", "representative_submission": "K200667", "function": "Autonomous detection of referable and vision-threatening diabetic retinopathy", "evidence_grade": "B", "study_label": "Ipp et al., 2021, JAMA Network Open", "study_doi": "10.1001/jamanetworkopen.2021.34254", "study_design": "Prospective multicenter cross-sectional diagnostic study; 893 patients at 15 primary care and eye care sites", "study_finding": "Sensitivity 95.5% and specificity 85.0% for detecting more-than-mild DR without dilation against reading-center grading", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "EyeArt version 2.1.0", "evidence_basis": "Full text", "notes": "", "representative_pathway": "510(k)", "representative_decision_date": "2020-08-03", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K200667", "first_listed_submission": "K200667", "first_listed_decision_date": "2020-08-03", "latest_listed_submission": "K223357", "latest_listed_decision_date": "2023-06-16", "listed_submission_count": "2", "listed_submissions": "K200667;K223357", "study_url": "https://doi.org/10.1001/jamanetworkopen.2021.34254", "second_study_url": "" }, { "tracker_id": "aeye-ds", "device_family": "AEYE-DS", "company": "AEYE Health", "specialty": "Ophthalmology: diabetic retinopathy", "representative_submission": "K221183", "function": "Autonomous detection of more-than-mild diabetic retinopathy, including with a handheld camera", "evidence_grade": "B", "study_label": "Dvey-Aharon et al., 2026, Frontiers in Digital Health", "study_doi": "10.3389/fdgth.2026.1907804", "study_design": "Three prospective pivotal validation studies; more than 1,200 patients; desktop and handheld cameras", "study_finding": "Sensitivity 92% to 93% and specificity 89% to 94% for detecting more-than-mild DR against reading-center grading", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "AEYE-DS pivotal versions", "evidence_basis": "Full text", "notes": "Company-authored report of the FDA pivotal studies.", "representative_pathway": "510(k)", "representative_decision_date": "2022-11-10", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K221183", "first_listed_submission": "K221183", "first_listed_decision_date": "2022-11-10", "latest_listed_submission": "K240058", "latest_listed_decision_date": "2024-04-23", "listed_submission_count": "2", "listed_submissions": "K221183;K240058", "study_url": "https://doi.org/10.3389/fdgth.2026.1907804", "second_study_url": "" }, { "tracker_id": "gi-genius", "device_family": "GI Genius", "company": "Cosmo Artificial Intelligence (Medtronic)", "specialty": "Gastroenterology: colonoscopy", "representative_submission": "DEN200055", "function": "Real-time computer-aided detection of colorectal polyps during colonoscopy", "evidence_grade": "A", "study_label": "Repici et al., 2020, Gastroenterology", "study_doi": "10.1053/j.gastro.2020.04.062", "study_design": "Multicenter randomized trial; 685 patients at 3 Italian centers", "study_finding": "Adenoma detection rate was 54.8% with computer-aided detection versus 40.4% without (relative risk 1.30)", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (adenoma detection)", "version_link": "GI Genius", "evidence_basis": "Abstract", "notes": "Adenoma detection is a surrogate; interval cancer and mortality were not measured.", "representative_pathway": "De Novo", "representative_decision_date": "2021-04-09", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN200055", "first_listed_submission": "DEN200055", "first_listed_decision_date": "2021-04-09", "latest_listed_submission": "K261369", "latest_listed_decision_date": "2026-05-29", "listed_submission_count": "6", "listed_submissions": "DEN200055;K211951;K231143;K233964;K241887;K261369", "study_url": "https://doi.org/10.1053/j.gastro.2020.04.062", "second_study_url": "" }, { "tracker_id": "dermasensor", "device_family": "DermaSensor", "company": "DermaSensor", "specialty": "Dermatology: skin cancer", "representative_submission": "DEN230008", "function": "Handheld elastic scattering spectroscopy with an algorithm that recommends investigate further or monitor", "evidence_grade": "B", "study_label": "Merry et al., 2025, Journal of Primary Care & Community Health (DERM-SUCCESS)", "study_doi": "10.1177/21501319251344423", "study_design": "Blinded, prospective, multicenter pivotal study at 22 primary care clinics in the US and Australia; 1,579 lesions", "study_finding": "Sensitivity 95.5% and specificity 20.7% for detecting skin cancer against histopathology; positive predictive value 16.6%", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "DermaSensor pivotal device", "evidence_basis": "Abstract", "notes": "Low specificity: most lesions flagged for further investigation were benign.", "representative_pathway": "De Novo", "representative_decision_date": "2024-01-12", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN230008", "first_listed_submission": "DEN230008", "first_listed_decision_date": "2024-01-12", "latest_listed_submission": "DEN230008", "latest_listed_decision_date": "2024-01-12", "listed_submission_count": "1", "listed_submissions": "DEN230008", "study_url": "https://doi.org/10.1177/21501319251344423", "second_study_url": "" }, { "tracker_id": "paige-prostate", "device_family": "Paige Prostate", "company": "Paige.AI", "specialty": "Pathology: prostate biopsy", "representative_submission": "DEN200080", "function": "Flags suspicious areas on digitized prostate biopsy slides", "evidence_grade": "C", "study_label": "da Silva et al., 2021, Journal of Pathology", "study_doi": "10.1002/path.5662", "study_design": "Independent application to 600 biopsy part-specimens from 100 consecutive patients", "study_finding": "Part-specimen sensitivity 0.99 and specificity 0.93 for identifying slides needing further review", "second_study_label": "Raciti et al., 2020, Modern Pathology", "second_study_doi": "10.1038/s41379-020-0551-y", "second_study_note": "Retrospective reader study with Paige Prostate Alpha: pathologist sensitivity rose from 74% to 90%", "outcome_direction": "Accuracy only", "version_link": "Paige Prostate (clinical-grade); the reader study used the Alpha version", "evidence_basis": "Abstract", "notes": "", "representative_pathway": "De Novo", "representative_decision_date": "2021-09-21", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN200080", "first_listed_submission": "DEN200080", "first_listed_decision_date": "2021-09-21", "latest_listed_submission": "DEN200080", "latest_listed_decision_date": "2021-09-21", "listed_submission_count": "1", "listed_submissions": "DEN200080", "study_url": "https://doi.org/10.1002/path.5662", "second_study_url": "https://doi.org/10.1038/s41379-020-0551-y" }, { "tracker_id": "sepsis-immunoscore", "device_family": "Sepsis ImmunoScore", "company": "Prenosis", "specialty": "Critical care: sepsis", "representative_submission": "DEN230036", "function": "Estimates sepsis risk within 24 hours from laboratory and clinical data once a blood culture is ordered", "evidence_grade": "B", "study_label": "Bhargava et al., 2024, NEJM AI", "study_doi": "10.1056/AIoa2400867", "study_design": "Prospective enrollment at 5 US institutions; derivation, internal validation, and external validation (698 patients) cohorts", "study_finding": "AUC 0.81 for identifying sepsis within 24 hours in the external validation cohort", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Sepsis ImmunoScore", "evidence_basis": "Abstract", "notes": "Requires that a clinician already suspects infection.", "representative_pathway": "De Novo", "representative_decision_date": "2024-04-02", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN230036", "first_listed_submission": "DEN230036", "first_listed_decision_date": "2024-04-02", "latest_listed_submission": "DEN230036", "latest_listed_decision_date": "2024-04-02", "listed_submission_count": "1", "listed_submissions": "DEN230036", "study_url": "https://doi.org/10.1056/AIoa2400867", "second_study_url": "" }, { "tracker_id": "bayesian-trews", "device_family": "Bayesian Health Sepsis Flagging Device (TREWS)", "company": "Bayesian Health", "specialty": "Critical care: sepsis", "representative_submission": "K250680", "function": "Continuous EHR-based sepsis risk flag for adults in the emergency department and inpatient units", "evidence_grade": "A", "study_label": "Adams et al., 2022, Nature Medicine", "study_doi": "10.1038/s41591-022-01894-0", "study_design": "Prospective multi-site cohort study at 5 hospitals; 590,736 patients monitored, 6,877 sepsis patients analyzed", "study_finding": "When providers confirmed the alert within 3 hours, adjusted in-hospital mortality was 3.3 percentage points lower than when they did not", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Favorable (observational)", "version_link": "TREWS, renamed Bayesian Health Sepsis Flagging Device", "evidence_basis": "Abstract", "notes": "Observational: the comparison is by provider response to the alert, not by randomization.", "representative_pathway": "510(k)", "representative_decision_date": "2026-04-30", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K250680", "first_listed_submission": "K250680", "first_listed_decision_date": "2026-04-30", "latest_listed_submission": "K250680", "latest_listed_decision_date": "2026-04-30", "listed_submission_count": "1", "listed_submissions": "K250680", "study_url": "https://doi.org/10.1038/s41591-022-01894-0", "second_study_url": "" }, { "tracker_id": "ceribell-se", "device_family": "Ceribell Status Epilepticus Monitor", "company": "Ceribell", "specialty": "Neurology: critical care EEG", "representative_submission": "K223504", "function": "Estimates seizure burden on point-of-care EEG and alerts for electrographic status epilepticus", "evidence_grade": "C", "study_label": "Sheikh et al., 2026, Epilepsia", "study_doi": "10.1002/epi.70352", "study_design": "Retrospective test of algorithm version 8 on a previously used rapid-response EEG dataset", "study_finding": "Sensitivity 100% for detecting electrographic status epilepticus at 10% to 20% burden thresholds, with specificity 0.90", "second_study_label": "", "second_study_doi": "", "second_study_note": "", "outcome_direction": "Accuracy only", "version_link": "Automated Seizure Burden Estimator version 8", "evidence_basis": "Abstract", "notes": "", "representative_pathway": "510(k)", "representative_decision_date": "2023-05-23", "representative_fda_url": "https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfPMN/pmn.cfm?ID=K223504", "first_listed_submission": "K223504", "first_listed_decision_date": "2023-05-23", "latest_listed_submission": "K223504", "latest_listed_decision_date": "2023-05-23", "listed_submission_count": "1", "listed_submissions": "K223504", "study_url": "https://doi.org/10.1002/epi.70352", "second_study_url": "" } ] }