Eko Foundation Analysis Software with Transformers (EFAST)

K251494

Eko Health, Inc. · cleared 2025-08-12 · product code DQD · Cardiovascular

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.5)
“Eko Foundation Analysis Software with Transformers (EFAST) is a cloud-based Software as a Medical Device (SaMD) intended to provide clinical decision support to healthcare professionals (HCP) in the evaluation of patients' heart sounds (phonocardiogram, PCG) and electrocardiograms (ECGs).”
Algorithmsignal processing techniques and machine learning (Deep Neural Networks)
source quote (p.5)
“The software employs signal processing techniques and machine learning (Deep Neural Networks) to perform simultaneous analysis of recorded heart sounds and ECG data (when available), and identify the presence of murmurs associated with Structural Heart Disease, and determine murmur timing including the timing of S1, S2 heart sounds.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedYes
source quote (p.10)
“The performance characteristics for the Eko Foundation Analysis Software with Transformers (EFAST) have been evaluated with the following non-clinical testing: software unit, integration, and system-level verification testing consistent with the IEC 62304 standard, and cybersecurity testing.”

Validation studies (3)

Retrospective clinical

n=615 patients · 3 site(s)

endpoints: Structural Murmur Classification performance; Heart Sound Timing

Retrospective clinical

n=314 patients · 2 site(s)

endpoints: ECG Rhythm Classification performance; Atrial Fibrillation detection

Bench

sample size not stated

endpoints: mean absolute percentage error of heart-rate algorithm

Reported performance (10 observations)

sensitivity83.4CI 95% CI: 80.2 - 86.6
source quote (p.11)
“Structural Murmur Classification Sensitivity (%) EFAST 83.4 (95% CI: 80.2 - 86.6)”
specificity86CI 95% CI: 82.2 - 89.8
source quote (p.11)
“Structural Murmur Classification Specificity (%) EFAST 86.0 (95% CI: 82.2 - 89.8)”
sensitivityas written: “S1 Detection Sensitivity”98.58CI 95% CI:97.21-99.38
source quote (p.11)
“S1 Detection Sensitivity (%) EFAST 98.58 (95% CI:97.21-99.38)”
sensitivityas written: “S2 Detection Sensitivity”94.81CI 95% CI: 92.59-96.53
source quote (p.11)
“S2 Detection Sensitivity (%) EFAST 94.81 (95% CI: 92.59-96.53)”
ppvas written: “S1 Detection PPV”93.27CI 95% CI: 90.94-95.15
source quote (p.11)
“S1 Detection PPV (%) EFAST 93.27 (95% CI: 90.94-95.15)”
ppvas written: “S2 Detection PPV”94.29CI 95% CI: 91.99-96.09
source quote (p.11)
“S2 Detection PPV (%) EFAST 94.29 (95% CI: 91.99-96.09)”
sensitivityas written: “Atrial Fibrillation Detection Overall Sensitivity”94.7CI 95% CI: 91.5 - 97.8
source quote (p.13)
“Atrial Fibrillation Detection Overall Sensitivity (%) EFAST 94.7 (95% CI: 91.5 - 97.8)”
specificityas written: “Atrial Fibrillation Detection Overall Specificity”94.1CI 95% CI: 92.1 - 96.1
source quote (p.13)
“Atrial Fibrillation Detection Overall Specificity (%) EFAST 94.1 (95% CI: 92.1 - 96.1)”
ppvas written: “PPV High Likelihood (All Ages)”90.5CI 95% CI: 86.7 - 94.3
source quote (p.12)
“All Ages 90.5 (95% CI: 86.7 - 94.3)”
ppvas written: “PPV Moderate Likelihood (All Ages)”64.7CI 95% CI: 55.8 - 73.7
source quote (p.12)
“All Ages 64.7 (95% CI: 55.8 - 73.7)”

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

0
recalls in product code, 24mo
1
MAUDE reports in code, 12mo
+200%
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/K251494