Smile Dx®
K242437Cube Click, Inc. · cleared 2025-05-14 · product code MYN · Radiology
Premarket evidence — what FDA accepted
Device typesamd
source quote (p.4)
“Smile Dx® is a computer-assisted detection (CADe) software designed to aid dentists in the review of digital files of bitewing and periapical radiographs of permanent teeth.”
Algorithmcomputer vision machine learning algorithm(s)
source quote (p.13)
“Utilizes computer vision machine learning algorithm(s).”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this
Validation studies (4)
Standalone
n=867 cases
Standalone
n=352 cases
Standalone
n=200 cases
Reader study (MRMC)
n=352 cases
endpoints: sensitivity; specificity; alternative free response receiver operating characteristic (AFROC)
Reported performance (16 observations)
sensitivity0.839CI [12.8%, 26.4%]
source quote (p.18)
“For caries detections, reader sensitivity improved from 64.3% without device to 83.9% with device, an increase of 19.6% [12.8%, 26.4%].”
specificity0.902CI [13.5%, 19.9%]
source quote (p.18)
“For caries detections, reader specificity improved from 73.6% without device to 90.2% with device, a difference of 16.7% [13.5%, 19.9%].”
sensitivityas written: “Periapical Radiolucency Sensitivity (Standalone)”0.861CI [80.2%, 91.9%]
source quote (p.16)
“86.1% [80.2%, 91.9%]”
sensitivityas written: “Bitewing Bone Level Detection - Sensitivity (Standalone)”0.955CI [94.3%, 96.7%]
source quote (p.17)
“95.5% [94.3%, 96.7%]”
specificityas written: “Bitewing Bone Level Detection - Specificity (Standalone)”0.94CI [91.1%, 96.6%]
source quote (p.17)
“94.0% [91.1%, 96.6%]”
sensitivityas written: “Periapical Bone Level Detection - Sensitivity (Standalone)”0.873CI [85.4%, 89.2%]
source quote (p.17)
“87.3% [85.4%, 89.2%]”
specificityas written: “Periapical Bone Level Detection - Specificity (Standalone)”0.921CI [89.9%, 94.1%]
source quote (p.17)
“92.1% [89.9%, 94.1%]”
sensitivityas written: “Normal Anatomy Sensitivity (Pixel-level) (Standalone)”0.861CI [85.4%, 86.8%]
source quote (p.17)
“86.1% [85.4%, 86.8%]”
sensitivityas written: “Normal Anatomy Sensitivity (Contour-level) (Standalone)”0.952CI [94.5%, 96%]
source quote (p.17)
“95.2% [94.5%, 96%]”
specificityas written: “Normal Anatomy Specificity (Contour-level) (Standalone)”0.935CI [91.6%, 95.8%]
source quote (p.17)
“93.5% [91.6%, 95.8%]”
sensitivityas written: “Restorations Sensitivity (Pixel-level) (Standalone)”0.831CI [80.3%, 86.4%]
source quote (p.17)
“83.1% [80.3%, 86.4%]”
sensitivityas written: “Restorations Sensitivity (Contour-level) (Standalone)”0.909CI [88.2%, 93.9%]
source quote (p.17)
“90.9% [88.2%, 93.9%]”
specificityas written: “Restorations Specificity (Contour-level) (Standalone)”0.996CI [99.3%, 99.8%]
source quote (p.17)
“99.6% [99.3%, 99.8%]”
sensitivityas written: “PARL Reader Sensitivity Improvement (MRMC)”0.191CI [13.6%, 24.7%]
source quote (p.18)
“For PARL detections, reader sensitivity improved from 70.7% without device to 89.8% with device, an increase of 19.1% [13.6%, 24.7%].”
specificityas written: “Caries Reader Specificity Improvement (MRMC)”0.167CI [13.5%, 19.9%]
source quote (p.18)
“For caries detections, reader specificity improved from 73.6% without device to 90.2% with device, a difference of 16.7% [13.5%, 19.9%].”
specificityas written: “PARL Reader Specificity Improvement (MRMC)”0.047CI [3%, 6.4%]
source quote (p.18)
“For PARL detections, reader specificity improved from 92.6% without device to 97.3% with device, a difference of 4.7% [3%, 6.4%].”
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). 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).