EarliPoint

K230337

EarliTec Diagnostics, Inc · cleared 2023-06-29 · product code QPF · Neurology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“The EarliPoint System is intended for use by healthcare providers to objectively diagnose and assess children for ASD using software algorithm to analyze a child's response to an external stimulus in the form of videos.”
Algorithmsoftware algorithm, Artificial intelligence software
source quote (p.4)
“The EarliPoint System is intended for use by healthcare providers to objectively diagnose and assess children for ASD using software algorithm to analyze a child's response to an external stimulus in the form of videos. Artificial intelligence software analyzes the eye-tracking data and provides a diagnosis for ASD.”
Adaptive (vs locked)No
PCCPNo
Cybersecurity addressedNo

Validation studies (3)

Bench

sample size not stated

endpoints: identifications of blinks; saccades; non-missing samples; fixation accuracy

standards: IEC 60601-1:2005/AMD1:2012/AMD2:2020, IEC 60601-1-2:2014/AMD1:2020, IEC 62304

Bench

sample size not stated

endpoints: equivalency of the current device's data analysis software to the predicate data analysis software

standards: IEC 62304

Prospective clinical

n=500 patients · 6 site(s)

endpoints: evaluate the sensitivity and specificity of the EarliPoint System diagnosis relative to the expert clinical diagnosis; correlated the three EarliPoint Severity Indices of social disability, verbal ability and nonverbal ability against the corresponding expert clinical instruments of ADOS-2 and Mullen

Reported performance (4 observations)

sensitivity0.71CI 64.6% - 76.9%
source quote (p.7)
“71% (157/221) 64.6% - 76.9%”
specificity0.807CI 75.3% - 85.4%
source quote (p.7)
“80.7% (205/254) 75.3% - 85.4%”
sensitivityas written: “Sensitivity (EarliPoint CertainDx)”0.78CI 70.5%, 84.3%
source quote (p.7)
“78.0% (117/150) 70.5%, 84.3%”
specificityas written: “Specificity (EarliPoint CertainDx)”0.854CI 79.5% - 90.2%
source quote (p.7)
“85.4% (158/185) 79.5% - 90.2%”

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
0
MAUDE reports in code, 12mo
—
vs code's own 3-yr baseline
2
drift signals on this device
  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K253442 (decision 2026-03-05) from Earlitec Diagnostics for a matching device line ("EarliPoint Assessment") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K253442

  • re_clearance

    The FDA AI/ML device list shows a newer 510(k) K243891 (decision 2025-03-26) from EarliTec Diagnostics for a matching device line ("EarliPoint System") — a new clearance for the same line is a change event.

    first seen 2026-07-08 · k_number:K243891

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 Neurology 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/K230337