Overjet Caries Assist-Pediatric

K233738

Overjet, Inc · cleared 2024-03-04 · product code MYN · Radiology

Premarket evidence — what FDA accepted

Device typesamd
source quote (p.4)
“OCA-Ped is a software-only device which operates in three layers: a Network Layer, a Presentation Layer, and a Decision Layer.”
AlgorithmMachine Learning model
source quote (p.4)
“Images are pulled in from a clinic/dental office, and the Machine Learning model creates predictions in the Decision Layer and results are pushed to the dashboard, which are in the Presentation Layer.”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (2)

Reader study (MRMC)

n=636 images

endpoints: improvement in detection of caries; AUC of the WAFROC

Retrospective clinical

n=1,190 images

endpoints: Tooth level standalone sensitivity; Tooth Level standalone specificity; Standalone Dice

Reported performance (6 observations)

sensitivity0.839CI 0.816, 0.860
source quote (p.6)
“Tooth level standalone sensitivity was 83.9%, 95% CI's (0.816, 0.860).”
specificity0.975CI 0.971, 0.979
source quote (p.6)
“Tooth Level standalone specificity was 97.5%, 95% CI's (0.971, 0.979).”
diceas written: “Standalone Dice”0.79CI 0.784, 0.797
source quote (p.6)
“Standalone Dice was a mean of 79.0%, 95% CI's (0.784, 0.797).”
aurocas written: “AUC of the wAFROC improvement”0.075CI 0.062, 0.088
source quote (p.6)
“The AUC of the wAFROC averaged across all readers showed a 7.5% improvement, with 95% CI's (0.062, 0.088) in assisted readers compared to unassisted readers.”
sensitivityas written: “Average Tooth level sensitivity improvement”0.118CI 0.102, 0.137
source quote (p.6)
“Average Tooth level sensitivity across all readers increased by 11.8% (0.102, 0.137) when compared to unassisted readers.”
specificityas written: “Average specificity at the tooth level difference”-0.011CI -0.015, -0.008
source quote (p.6)
“The average specificity at the tooth level decreased slightly with a difference of -0.011 (-0.015, -0.008) between the assisted and unassisted readers.”

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
-100%
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 Radiology 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/K233738