Rapid ICH

K193087

iSchemaView Incorporated · cleared 2020-03-31 · product code QAS · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.5)

“RAPID is a software-only device consisting of one or more RAPID Servers (dedicated or virtual and an iSchemaView Server).”

Algorithmartificial intelligence algorithm; deep learning algorithm trained on medical images

source quote (p.3)

“RAPID ICH uses an artificial intelligence algorithm to analyze images and highlight cases with suspected ICH on a server or standalone desktop application in parallel to the ongoing standard of care image interpretation. The predicate and subject devices process CT images using similar techniques and a similar artificial intelligence algorithm. Specifically, the subject and predicate software utilize a deep learning algorithm trained on medical images.”

Adaptive (vs locked)FDA source did not state this

PCCPNo

Cybersecurity addressedYes

source quote (p.5)

“All iSchemaView Server data is stored on encrypted hard disks. It also provides a user interface for accessing RAPID data. It connects to a firewalled Data Center Network and has its own firewall for additional cyber/data security. The iSchemaView Server connects to one or more RAPID Servers via WAN. Available types of connection include VPN (Virtual Private Network - RFC2401 and RFC4301 Standards) Tunnel and SSH (Secure Shell).”

Validation studies (1)

Retrospective clinical

n=336 cases · 6 site(s)

endpoints: evaluate the software's performance in identifying noncontrast CT head images containing intracranial hemorrhage (ICH) findings; RAPID ICH's time to notification of suspicion non-suspicion

standards: EN ISO 14971:2012, IEC 62304:2015, NEMA PS 3.1 - 3.20

Reported performance (3 observations)

sensitivity0.899CI 95% CI: 0.847 – 0.935

source quote (p.10)

“Specifically, sensitivity was observed to be Se: 0.899 (95% CI: 0.847 – 0.935)”

specificity0.943CI 95% CI: 0.895 – 0.970

source quote (p.10)

“and Sp: 0.943 (95% CI: 0.895 – 0.970).”

time_to_resultas written: “time to notification of suspicion non-suspicion”2.28CI 95% CI: 2.24 - 2.33

source quote (p.10)

“In addition, a secondary endpoint measure was RAPID ICH's time to notification of suspicion non-suspicion as 2.28 min (95% CI: 2.24 - 2.33) was achieved.”

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) K233582 (decision 2024-04-22) from iSchema View Inc. for a matching device line ("Rapid") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K233582
re_clearance
The FDA AI/ML device list shows a newer 510(k) K223396 (decision 2023-02-01) from iSchema View Inc. for a matching device line ("Rapid RV/LV") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K223396
re_clearance
The FDA AI/ML device list shows a newer 510(k) K213165 (decision 2022-02-08) from iSchema View Inc. for a matching device line ("Rapid") — a new clearance for the same line is a change event.
first seen 2026-07-08 · k_number:K213165

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).