PVAD IQ Software
K252235Ultrasight , Ltd. · cleared 2025-12-18 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.5)
“PVAD IQ is a Software as a Medical Device (SaMD) solution designed to support clinicians in the positioning of Percutaneous Ventricular Assist devices (PVADs) through ultrasound image-based assessment.”
source quote (p.7)
“Deep Convolutional Neural Networks for Landmark Detection and Classification”
source quote (p.6)
“PVAD IQ software is an ultrasound image processing software implementing non-adaptive machine learning algorithms trained with clinical data and intended for automated analysis of transthoracic echocardiography (TTE) using ultrasound clips.”
source quote (p.9)
“This submission includes a Predetermined Change Control Plan (PCCP) detailing the proposed device modifications.”
source quote (p.9)
“The device underwent comprehensive software validation and cybersecurity testing in accordance with the FDA’s Guidance “Content of Premarket Submissions for Device Software Functions” and “Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions”.”
Validation studies (1)
Standalone
n=186 patients
endpoints: Distance measurement: a mean absolute error (MAE) with a 95% confidence interval (CI) upper bound below 0.5 cm.; Acceptability classification requirement: Cohens kappa above 0.6.; Landmark detection of inlet and aortic annulus requirement: AUC above 0.8.; Landmark position requirement: MAE below 0.5 cm.
Reported performance (3 observations)
source quote (p.8)
“Landmark detection of inlet and aortic annulus requirement: AUC above 0.8. result: Inlet: 0.92 (0.9-0.94). Annulus: 0.98 (0.95, 1)”
source quote (p.8)
“Acceptability classification requirement: Cohens kappa above 0.6. result: 0.71 with a 95% CI of (0.66–0.75)”
source quote (p.8)
“Landmark detection of inlet and aortic annulus requirement: AUC above 0.8. result: Inlet: 0.92 (0.9-0.94). Annulus: 0.98 (0.95, 1)”
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
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).