Assert-IQ (DM5000); Assert-IQ (DM5300); Assert-IQ (DM5500); Merlin.net (MN7000)

K251221

Abbott · cleared 2025-09-17 · product code MXD · Cardiovascular

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.5)
“The subject of this premarket notification is the integration of two new artificial intelligence (AI) algorithms utilizing machine learning (ML) techniques for the evaluation of atrial fibrillation (AF) and Pause episodes within the Assert-IQ™™ ICM remote care component, Merlin.net MN7000.”
Algorithmdeep neural network AI models
source quote (p.5)
“Specifically, this premarket submission pertains to the addition of the proposed deep neural network AI models as integrated sub-components of the Merlin.net software, MN7000, resulting in MN7000 version v2.0.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.8)
“Design Verification: Software Verification and System Verification, including cybersecurity testing were completed to ensure the design output meets specifications outlined in the design inputs and cybersecurity requirements.”

Validation studies (4)

Retrospective clinical

n=1,498 patients · 504 site(s)

endpoints: relative sensitivity; false positive reduction; episode-based sensitivity; episode-based positive predictive value; patient sensitivity; delay in diagnosis

Prospective clinical

n=151 patients

endpoints: episode-based sensitivity; positive predictive value; patient sensitivity; delay in diagnosis

Bench

sample size not stated

endpoints: functionality per the requirements; test executions resulted in a status of Passed

Bench

sample size not stated

endpoints: algorithms were able to properly modify AF and Pause alerts; results met or exceeded the acceptance criteria

Reported performance (7 observations)

sensitivity0.994
source quote (p.10)
“the overall system performance of Assert IQ with CARE-AF achieved an episode-based sensitivity of 99.4%”
sensitivityas written: “relative sensitivity (AI Pause algorithm)”0.992
source quote (p.9)
“the AI Pause algorithm independently achieving an episode-based relative sensitivity of 99.2%”
ppvas written: “episode-based positive predictive value (CARE-Pause)”0.786
source quote (p.9)
“episode-based positive predictive value of 78.6%”
sensitivityas written: “patient sensitivity (CARE-Pause)”1
source quote (p.9)
“100% patient sensitivity”
sensitivityas written: “relative sensitivity (AI AF algorithm)”0.973
source quote (p.10)
“the AI AF algorithm independently achieving an episode-based relative sensitivity of 97.3%”
ppvas written: “positive predictive value (CARE-AF)”0.936
source quote (p.10)
“a positive predictive value of 93.6%”
sensitivityas written: “patient sensitivity (CARE-AF)”1
source quote (p.10)
“100% patient sensitivity”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

3
recalls in product code, 24mo
3444
MAUDE reports in code, 12mo
+49%
vs code's own 3-yr baseline
0
drift signals on this device

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Cardiovascular panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K251221