PeekMed web

K250042

Peek Health, S.A. · cleared 2025-03-19 · product code QIH · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.4)

“PeekMed web is a system designed to help healthcare professionals carry out pre-operative planning for several surgical procedures, based on their imported patients' imaging studies. This medical device consists of a decision support tool for qualified healthcare professionals to quickly and efficiently perform the pre-operative planning for several surgical procedures, using medical imaging with the additional capability of planning the 2D or 3D environment. Being software it does not interact with any part of the body of the user and/or patient.”

Algorithmnew ML model variants for segmentation and landmarking

source quote (p.11)

“The subject device includes new ML. The subject device includes new ML model variants for segmentation. The subject device includes new ML model variants for landmarking.”

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)

Retrospective clinical

n=375 cases

endpoints: DICE no less than 90%; HD-95 no more than 8; STD DICE between +/- 10%; Precision more than 85%; Recall more than 90%

Retrospective clinical

n=345 cases

endpoints: MRE no more than 7mm; STD MRE between +/- 5mm

Retrospective clinical

n=347 cases

endpoints: Accuracy no less than 90%; Precision no less than 85%; Recall no less than 90%; F1 score no less than 90%

Retrospective clinical

n=198 cases

endpoints: MAP no less than 90%; Precision no less than 85%; Recall no less than 90%

Reported performance (10 observations)

diceas written: “DICE”stated without valueCI no less than 90%

source quote (p.15)

“DICE is no less than 90%”

diceas written: “STD DICE”stated without valueCI between +/- 10%

source quote (p.15)

“STD DICE is between +/- 10%”

ppvas written: “Precision (Segmentation)”stated without valueCI more than 85%

source quote (p.15)

“Precision is more than 85%”

sensitivityas written: “Recall (Segmentation)”stated without valueCI more than 90%

source quote (p.15)

“Recall is more than 90%”

accuracyas written: “Accuracy (Classification)”stated without valueCI no less than 90%

source quote (p.15)

“Accuracy is no less than 90%.”

ppvas written: “Precision (Classification)”stated without valueCI no less than 85%

source quote (p.15)

“Precision is no less than 85%”

sensitivityas written: “Recall (Classification)”stated without valueCI no less than 90%

source quote (p.15)

“Recall is no less than 90%”

f1as written: “F1 score”stated without valueCI no less than 90%

source quote (p.15)

“F1 score is no less than 90%”

ppvas written: “Precision (Detection)”stated without valueCI no less than 85%

source quote (p.15)

“Precision is no less than 85%”

sensitivityas written: “Recall (Detection)”stated without valueCI no less than 90%

source quote (p.15)

“Recall is no less than 90%”

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

recalls in product code, 24mo

MAUDE reports in code, 12mo

—

vs code's own 3-yr baseline

drift signals on this device

re_clearance
The FDA AI/ML device list shows a newer 510(k) K252856 (decision 2025-12-22) from Peek Health, S.A. for a matching device line ("PeekMed web") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K252856
re_clearance
The FDA AI/ML device list shows a newer 510(k) K252452 (decision 2025-11-12) from Peek Health, S.A. for a matching device line ("PeekMed web") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K252452
re_clearance
The FDA AI/ML device list shows a newer 510(k) K251096 (decision 2025-07-14) from Peek Health, S.A. for a matching device line ("PeekMed web") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K251096

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).