All apps

Safety case mgmt · Drug safety officers / PV scientists

CuRE Canary

Pharmacovigilance — case management, MedDRA coding, E2B(R3), and OMOP-native signal detection.

What it does

Pharmacovigilance — case management, MedDRA coding, E2B(R3), and OMOP-native signal detection. One sealed evidence chain from AE source to regulator acknowledgment — the submitted E2B payload and the ACK/MDN live in the same Part 11 envelope as the case.

Key capabilities

  • AE case management
  • MedDRA coding + AI-drafted case narratives
  • E2B(R3) regulatory export
  • Signal detection (PRR / ROR / EB05) on OMOP
  • EVDAS / eRMR signal-source integration
  • Literature monitoring + ICSR-from-literature
  • AI-drafted aggregate-report narratives (DSUR/PBRER)
  • Cross-app subject safety-context panel

What sets it apart

  • One sealed evidence chain from AE source to regulator acknowledgment — the submitted E2B payload and the ACK/MDN live in the same Part 11 envelope as the case.
  • EVDAS/eRMR signal management (the EMA obligation live since 12-Feb-2026) and a Cascade code-break that drives the expedited-reporting clock — the safety system and the IRT on one substrate.
  • Aggregate reports, RSI/expectedness, WHODrug, live gateways, safety letters, and pharmacoepi signal evaluation run on the same OMOP evidence base.
  • Signal detection runs on the same OMOP as analytics — no separate PV warehouse.
  • E2B(R3) export and MedDRA coding are first-class, not bolted-on integrations.
CuRE Canary · Signal detection
Live demo — synthetic data, runs in your browser

Find a safety signal, live

Pick a drug–event pair from a synthetic spontaneous-reporting database, drag the observed co-report count, and watch the disproportionality statistics — PRR, ROR (both with 95% confidence intervals), the chi-square, and DuMouchel's Empirical-Bayes EBGM / EB05 — recompute in your browser, then the pair's triage move between validated, watchlist, and dismissed.

A synthetic spontaneous-reporting database of 60,000 reports across 5 drugs and 7 events.

Event +Event −
Drug +a = 288b = 1,312
Drug −c = 1,512d = 56,888

Drag above the expected count to manufacture disproportionality — watch EB05 shrink low counts back toward the null.

EB05 ≥ 2.0 and ≥ 3 co-reports ⇒ validated. Product default is 2.

Anticoagulant-XGI haemorrhage
Validated signal
PRR
6.95
95% CI 6.19–7.81
ROR
8.26
95% CI 7.20–9.48
EB05
5.42
EBGM 6.00
χ² (Yates)
1265.7
obs 288 vs exp 48.0

EBGM is the Empirical Bayes Geometric Mean of the reporting ratio under a two-component Gamma-Poisson (DuMouchel MGPS) posterior; EB05 is its conservative 5th-percentile lower bound — the score Canary triages on because it self-corrects for the small counts that inflate raw PRR/ROR.

All pairs · ranked by EB05

6 validated3 watch26 dismissed
Drug → EventaPRREB05Disposition
SSRI-Z → Serotonin syndrome12118.1510.99Validated signal
Statin-Y → Rhabdomyolysis13814.879.48Validated signal
Biologic-V → Injection-site reaction10511.598.39Validated signal
Anticoagulant-X → GI haemorrhage2886.955.42Validated signal
NSAID-W → Acute kidney injury1915.003.97Validated signal
NSAID-W → GI haemorrhage1633.412.79Validated signal
SSRI-Z → Nausea2291.421.24Watchlist
SSRI-Z → Headache1821.311.13Watchlist
NSAID-W → Nausea2381.211.07Watchlist
Statin-Y → Acute kidney injury491.320.97Dismissed
Anticoagulant-X → Acute kidney injury481.210.89Dismissed
Statin-Y → Serotonin syndrome121.210.62Dismissed

Every statistic is computed in your browser from the synthetic 2×2 tables — no backend. Notice a high raw count is not enough: a common event like a background headache can post a big a yet stay dismissed once EB05 shrinks it against how often it is reported anyway. That shrinkage is what separates a real signal from reporting volume.

Why this is more than a toy

These are the FDA/EMA/WHO-UMC disproportionality formulas — Evans (2001) PRR, van Puijenbroek (2002) ROR, and DuMouchel's (1999) Multi-item Gamma-Poisson Shrinker — ported faithfully from CuRE's signal-detection methodology, including the product's default MGPS prior and the EB05 ≥ 2 triage rule. The key move a real PV engine makes, and this demo shows, is shrinkage: a common event with a big raw count stays dismissed once EB05 corrects for how often it is reported anyway. In the product, Canary runs this over an OMOP-native report store and routes validated signals into case management.

See CuRE Canary in action

Every research ecosystem is unique. Let's discuss how CuRE can be configured for your needs.