Study Watch with Irregular Pulse Monitor (Home), Study Watch with Irregular Pulse Monitor

K213357

Verily Life Sciences LLC · cleared 2022-07-19 · product code DXH · Cardiovascular

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.5)
“The Study Watch with Irregular Pulse Monitor is a miniaturized physiological data monitoring device that is intended to record, store, transfer and display single-channel electrocardiogram (ECG) rhythms. The device utilizes a band and proprietary watch that incorporates two dedicated sensing electrodes to obtain a single-channel ECG measurement. The Irregular Pulse Monitoring Algorithm is responsible for processing PPG-based data collected by the Study Watch device to provide detection of irregular pulses over the patient's wear period. The algorithm was developed using machine learning techniques.”
Algorithmmachine learning techniques processing PPG-based data
source quote (p.5)
“The Irregular Pulse Monitoring Algorithm is responsible for processing PPG-based data collected by the Study Watch device to provide detection of irregular pulses over the patient's wear period. The algorithm operates on a continuous basis by analyzing - once every 15 minutes - the prior 15-minutes of PPG-based data to detect the presence of an irregular rhythm, such as AF. The algorithm was developed using machine learning techniques.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedNo

Validation studies (1)

Prospective clinical

sample size not stated

endpoints: per-interval sensitivity; per-interval specificity

Reported performance (4 observations)

sensitivity96.1CI 95% CI: 92.7 - 98.0
source quote (p.9)
“The presented data include the primary endpoints [per-interval sensitivity 96.1% (95% CI: 92.7 - 98.0) and specificity 98.1% (95% CI: 97.2 - 99.1)]”
specificity98.1CI 95% CI: 97.2 - 99.1
source quote (p.9)
“The presented data include the primary endpoints [per-interval sensitivity 96.1% (95% CI: 92.7 - 98.0) and specificity 98.1% (95% CI: 97.2 - 99.1)]”
sensitivityas written: “In-clinic Use Sensitivity”98.3
source quote (p.8)
“In-clinic Use: Sensitivity: 98.3% Specificity: 100.0%”
specificityas written: “In-clinic Use Specificity”100
source quote (p.8)
“In-clinic Use: Sensitivity: 98.3% Specificity: 100.0%”

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

1
recalls in product code, 24mo
28
MAUDE reports in code, 12mo
+950%
vs code's own 3-yr baseline
2
drift signals on this device
  • adverse_event_inflection

    MAUDE adverse-event reports for product code DXH: 28 in the 12 months ending 2026-06, vs a 2.7/12mo average over the prior 3 windows (+950%). Code-level count — reports are not attributed to this specific device.

    first seen 2026-07-08 · openFDA /device/event.json count=date_received product_code=DXH

  • recall_reason_pattern

    Software/algorithm-related recall in product code DXH (GE Medical Systems China Co., Ltd. No. 19 Changjiang Road Development Zone National Hi-Tech Xin District Wuxi China, initiated 2026-04-21): "Software in development inadvertently made available for customer use. Use of this software version can result in clinical information being associated with the incorrect patient. " Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:98917

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/K213357