Eko Analysis Software

K192004

Eko Devices Inc · cleared 2020-01-15 · product code MWI · Cardiovascular

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“The Eko Analysis Software is a cloud-based software API that allows a user to upload synchronized ECG and heart sound/phonocardiogram (PCG) data for analysis.”
AlgorithmNeural network model for rhythm and murmur detection; signal processing algorithms for heart rate, QRS duration, and EMAT.
source quote (p.4)
“The algorithm consists of the following components: Rhythm detection algorithm: A neural network model that uses ECG to detect normal sinus rhythm and atrial fibrillation. Murmur detection algorithm: A neural network model that uses heart sounds to detect the presence of murmurs. Heart rate analysis algorithm: A signal processing algorithm that uses ECG or heart sounds as appropriate to calculate heart rate. It also provides an alert if the measured heart rate is indicative of Bradycardia or Tachycardia. QRS duration algorithm: A signal processing algorithm that measures the width of the QRS pulse on a single-channel ECG. EMAT Interval algorithm: A signal processing algorithm that uses Q peak detection and S1 envelope detection to measure the Q-S1 interval, defined as electromechanical activation time or EMAT.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (5)

Retrospective clinical

n=732 cases

endpoints: Sensitivity for Normal or Atrial Fibrillation; Specificity for Normal or Atrial Fibrillation

Retrospective clinical

sample size not stated

endpoints: Sensitivity for Murmur Detection; Specificity for Murmur Detection

Retrospective clinical

sample size not stated

endpoints: Heart rate error; Bradycardia detection sensitivity; Bradycardia detection specificity; Tachycardia detection sensitivity; Tachycardia detection specificity

Retrospective clinical

sample size not stated

endpoints: Absolute Mean Error for QRS duration

Retrospective clinical

sample size not stated

endpoints: Absolute Error for EMAT

Reported performance (8 observations)

sensitivity100CI 95% CI: 93.8 – 100.0
source quote (p.7)
“Sensitivity and specificity measured in the classifiable ECGs were 100% (95% CI: 93.8 – 100.0)”
specificity96.2CI 95% CI: 93.8 - 97.7
source quote (p.7)
“and 96.2% (95% CI: 93.8 - 97.7), respectively.”
sensitivityas written: “Murmur Detection Sensitivity”87.6CI 95% CI: 84.2 – 90.5
source quote (p.7)
“Sensitivity and specificity in the Eko Heart Sound Database were 87.6% (95% CI: 84.2 – 90.5)”
specificityas written: “Murmur Detection Specificity”87.8CI 95% CI: 85.3 – 89.9
source quote (p.7)
“and 87.8% (95% CI: 85.3 – 89.9), respectively.”
sensitivityas written: “Bradycardia Detection Sensitivity”94.7CI 95% CI: 89.8 – 97.3
source quote (p.7)
“Bradycardia detection had a sensitivity and specificity of 94.7% (95% CI: 89.8 – 97.3)”
specificityas written: “Bradycardia Detection Specificity”99.7CI 95% CI: 99.4 – 99.8
source quote (p.8)
“and 99.7% (95% CI: 99.4 – 99.8) respectively.”
sensitivityas written: “Tachycardia Detection Sensitivity”93.6CI 95% CI: 90.9 – 95.6
source quote (p.8)
“Tachycardia detection had a sensitivity and specificity of 93.6% (95% CI: 90.9 – 95.6)”
specificityas written: “Tachycardia Detection Specificity”99CI 95% CI: 98.7 – 99.3
source quote (p.8)
“and 99.0% (95% CI: 98.7 – 99.3) respectively.”

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

13
recalls in product code, 24mo
342
MAUDE reports in code, 12mo
+138%
vs code's own 3-yr baseline
6
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K213794 (decision 2022-06-29) from Eko Devices, Inc. for a matching device line ("Eko Murmur Analysis Software (EMAS)") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K213794

  • adverse_event_inflection

    MAUDE adverse-event reports for product code MWI: 342 in the 12 months ending 2026-06, vs a 143.7/12mo average over the prior 3 windows (+138%). 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=MWI

  • recall_reason_pattern

    Software/algorithm-related recall in product code MWI (CHANGE HEALTHCARE CANADA COMPANY, initiated 2025-05-22): "Due to complaints, software update may cause software to unexpectedly shutdown." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97046

  • recall_reason_pattern

    Software/algorithm-related recall in product code MWI (Spectrum Medical Ltd. Harrier 4, Meteor Business Park Cheltenham Road East Gloucester United Kingdom, initiated 2025-03-19): "Medical device software marketed without FDA clearance ." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:96616

  • recall_reason_pattern

    Software/algorithm-related recall in product code MWI (GE Medical Systems, LLC, initiated 2024-12-06): "There is a software issue that can result in the loss of patient monitoring on the Portrait Central Viewer Application after 425 days of continuous run-time." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:96027

  • recall_reason_pattern

    Software/algorithm-related recall in product code MWI (A L I Technologies Ltd, initiated 2024-12-02): "Software defect concerning autosave mechanism may result in the clinician administering incorrect medication(s)." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:96025

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/K192004