RIGOR · Stage 2 · Post-deployment

What happens to AI devices after clearance.

Adverse-event trends, recalls, and performance-drift signals, mapped to each device on FDA's AI-enabled device list. Every signal is an observable with a source — never a judgment.

Live cohort — snapshotted AI/ML devices

0

devices snapshotted — refreshed weekly, rolling

Latest snapshot 2026-07-08

In a product code with a recall in the last 24 months709 of 1,466
MAUDE reports above the code's own 3-year baseline512 of 806

Of devices where the trend is computable.

Carry a device-specific drift signal608 of 1,466

Own line re-cleared, own applicant's recall, or predicate neighbors.

Carry any signal, incl. code-level947 of 1,466

Includes a software recall anywhere in the device's product code.

Applicant matched a recent FDA warning letter28 of 1,466

Of devices scanned while the letters feed was live.

Every figure is a presencerate with its denominator inline — never pooled across devices. Recall and MAUDE counts are product-code-level (MAUDE reports are not reliably attributable to a specific device). Descriptive only: “this code had N software-related recalls” — never “this device is unsafe.”

Drift signals by kind

Software/algorithm recall in the product code667 devices · 6108 signals
Re-clearance of the same device line528 devices · 1603 signals
Adverse-event inflection (MAUDE vs own baseline)190 devices · 190 signals
Recall activity among predicate-sharing devices7 devices · 10 signals

Machine access

Query the same cohort over MCP — device_postmarket_lookup, postmarket_search, cohort_postmarket_stats
curl -s https://radar.healthai.com/api/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"postmarket_search",
                 "arguments":{"panel":"Radiology","has_drift_signal":true}}}'

The premarket half lives at Precedent — same corpus, same K-numbers, clearance to runtime.

Get drift-signal updates for the cohort

Weekly snapshots surface new drift signals — adverse-event inflections, re-clearances, software-recall patterns. Get notified when the cohort picture moves.

Statistical pattern analysis of public FDA / CMS data — descriptive decision-support, not legal, regulatory, coding, or reimbursement advice. Verify against primary sources. A Health AI product · machine access over MCP.