MAUDE-Atlas v1.0.0 — Sample (100,003 FDA Medical Device Reports)

MAUDE-Atlas v1.0.0 — Full Dataset (25.7M Reports): Full dataset page: https://sentineldata.com.ua/dataset/maude-atlas-fda-medical-device-safety-database-25-7m-reports A non-synthetic global medical-device safety atlas built from the FDA MAUDE database via the openFDA device/event endpoint. Contains 25,711,469 post-market reports, enriched with GUDID (UDI), enforcement recalls, 510(k), PMA, and classification data, and coded with the official FDA MDR adverse-event terminology (embedding IMDRF annex A-G). Features deduplicated clusters (MinHash/LSH, Jaccard >= 0.85), leakage-controlled splits (train/val/test/test_ood with 20% product-code holdout), and ready-to-use benchmarks (severity classification, signal detection, link prediction). This is a free stratified sample of MAUDE-Atlas v1.0.0 100,003 real (non-synthetic) canonical reports, stratified by event_type_std and decade (seed=20260830). The sample includes all linked tables: devices_enriched, patients, mdr_texts, problem codes, event clusters, and splits for the sampled reports, plus the full terminology table. Sample Composition: Reports: 100,003 Patients: 100,009 MDR Texts: 247,259 Patient Problem Codes: 210,946 Key Features: Real FDA MAUDE data (non-synthetic) Stratified by event type and decade Includes full set of linked tables Exact-match problem coding with official FDA MDR terminology Leakage-controlled splits ... Full description with all tables is on the Wiki page of this project. Full dataset and purchase: https://sentineldata.com.ua/dataset/maude-atlas-fda-medical-device-safety-database-25-7m-reports . Zenodo copy: https://doi.org/10.5281/zenodo.22204785

Authors

Publication Details

Journal
Open Science Framework
Published
2026-11-07
DOI
https://doi.org/10.17605/osf.io/c7xvz
Primary Topic
Pharmacovigilance and Adverse Drug Reactions
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

MAUDE-Atlas v1.0.0 — Sample (100,003 FDA Medical Device Reports)

Chekerskyi Maksym
2 links
Open Science Framework
Pharmacovigilance and Adverse Drug Reactions
article

MAUDE-Atlas v1.0.0 — Sample (100,003 FDA Medical Device Reports)

Chekerskyi Maksym
article en

Abstract

MAUDE-Atlas v1.0.0 — Full Dataset (25.7M Reports): Full dataset page: https://sentineldata.com.ua/dataset/maude-atlas-fda-medical-device-safety-database-25-7m-reports A non-synthetic global medical-device safety atlas built from the FDA MAUDE database via the openFDA device/event endpoint. Contains 25,711,469 post-market reports, enriched with GUDID (UDI), enforcement recalls, 510(k), PMA, and classification data, and coded with the official FDA MDR adverse-event terminology (embedding IMDRF annex A-G). Features deduplicated clusters (MinHash/LSH, Jaccard >= 0.85), leakage-controlled splits (train/val/test/test_ood with 20% product-code holdout), and ready-to-use benchmarks (severity classification, signal detection, link prediction). This is a free stratified sample of MAUDE-Atlas v1.0.0 100,003 real (non-synthetic) canonical reports, stratified by event_type_std and decade (seed=20260830). The sample includes all linked tables: devices_enriched, patients, mdr_texts, problem codes, event clusters, and splits for the sampled reports, plus the full terminology table. Sample Composition: Reports: 100,003 Patients: 100,009 MDR Texts: 247,259 Patient Problem Codes: 210,946 Key Features: Real FDA MAUDE data (non-synthetic) Stratified by event type and decade Includes full set of linked tables Exact-match problem coding with official FDA MDR terminology Leakage-controlled splits ... Full description with all tables is on the Wiki page of this project. Full dataset and purchase: https://sentineldata.com.ua/dataset/maude-atlas-fda-medical-device-safety-database-25-7m-reports . Zenodo copy: https://doi.org/10.5281/zenodo.22204785

Open Science Framework
Good health and well-being
Openalex Percentile: Top 16%
Pharmacovigilance and Adverse Drug Reactions
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon