DASI Dimensions (V1.0)
K231324DASI Simulations · cleared 2024-01-08 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.3)
“DASI Dimensions is a standalone, non-invasive, clinical decision support software solution that is intended for use by cardiologists and radiologists in context of the aortic stenosis population.”
source quote (p.4)
“The report is generated using proprietary algorithms that (a) detect key aortic root control points with the assistance of a static deep learning artificial intelligence (AI) model and (b) calculate anatomical measurements relevant for pre-TAVR evaluation.”
source quote (p.4)
“static deep learning artificial intelligence (AI) model”
source quote (p.7)
“(ii) Cybersecurity testing (TP130 and TR130) was conducted to ensure that there were no unidentified vulnerabilities and that the appropriate risk control measures were implemented to protect from known vulnerabilities when the device is subject to a source of threat. The testing showed that appropriate risk control measures were implemented.”
Validation studies (6)
Bench
sample size not stated
endpoints: success rate of points
Bench
sample size not stated
endpoints: error in primary outputs; error in secondary outputs
Retrospective clinical
n=40 patients
endpoints: success rate of AI generated control points; mean percentage error in primary outputs (annulus area and perimeter); mean percentage difference in secondary outputs (sinus of valsalva diameters, sinotubular junction diameters, ascending aorta diameter); mean percentage difference in tertiary output (aortic valve angle)
Reader study (MRMC)
n=14 cases
endpoints: inter-operator agreement (precision); accuracy to clinician ground truth measurements
Bench
n=6 other
endpoints: effectiveness of risk management measures; system success rate; user interface intuitiveness
Bench
n=14 other
endpoints: percent errors in automatic annulus area measurements
Reported performance (1 observation)
source quote (p.6)
“Using a dataset of CTAs (n = 14), comparison of the annulus area outputs from DASI Dimensions made by trained DASI Simulations operators (n = 5) showed excellent inter-operator agreement (precision) and to clinician ground truth measurements (accuracy), with an ICC of 0.96 and ≤ 10% difference from clinician measurements in ≥95% of cases.”
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).