QP-Prostate® CAD

K242683

Quibim S.L. · cleared 2025-03-18 · product code QDQ · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“QP-Prostate® CAD is an artificial intelligence-based Computed Aided Detection and Diagnosis (CADe/CADx) image processing software.”

AlgorithmAI-based algorithms trained with pathology data, Neural Networks and Machine Learning

source quote (p.5)

“QP-Prostate® CAD uses AI-based algorithms trained with pathology data to detect suspicious lesions for clinically significant prostate cancer. Both devices are artificial intelligence-based, but they differ in algorithm methodology (e.g. ProstatID™™ is based on random forest and QP-Prostate® CAD is based on Neural Networks and Machine Learning).”

Adaptive (vs locked)No

PCCPFDA source did not state this

Cybersecurity addressedFDA source did not state this

Validation studies (2)

Retrospective clinical

n=247 images

Reader study (MRMC)

n=228 cases

endpoints: performance advantage of using QP-Prostate® CAD output compared to not using its output for diagnosis of csPCa lesions by clinical readers, determined by the AUCaided versus AUCunaided at case level; performance advantage of using QP-Prostate® CAD output compared to not using its output for diagnosis of csPCa lesions by clinical readers, determined by sensitivity and specificity of the readers with and without QP-Prostate® CAD at case level

Reported performance (6 observations)

sensitivity0.677CI 95% CI: 0.593-0.761

source quote (p.11)

“Sensitivity (high suspicion marker) 0.677 (95% CI: 0.593-0.761)”

aurocas written: “auc”0.732CI 95% CI: 0.668-0.791

source quote (p.11)

“AUC-ROC 0.732 (95% CI: 0.668-0.791)”

false_positive_rate_per_imageas written: “False Positive Rate per Case (high suspicion marker, any biopsy source)”0.417CI 95% CI: 0.313-0.522

source quote (p.11)

“False Positive Rate per Case (high suspicion marker, any biopsy source) 0.417 (95% CI: 0.313-0.522)”

sensitivityas written: “Sensitivity (high and moderate suspicion markers)”0.795CI 95% CI: 0.722-0.861

source quote (p.11)

“Sensitivity (high and moderate suspicion markers) 0.795 (95% CI: 0.722-0.861)”

false_positive_rate_per_imageas written: “False Positive Rate per Case (high and moderate suspicion markers, any biopsy source)”0.855CI 95% CI: 0.709-0.996

source quote (p.11)

“False Positive Rate per Case (high and moderate suspicion markers, any biopsy source) 0.855 (95% CI: 0.709-0.996)”

aurocas written: “ΔAUC (AUCaided- AUCunaided)”0.019CI 95% CI: 0.001-0.038

source quote (p.12)

“ΔAUC (AUCaided- AUCunaided) 0.019 (95% CI: 0.001-0.038)”

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

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).