MSKai
K240793MSKai · cleared 2024-12-16 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.6)
“MSKai is a medical device (software) for inspecting and evaluating T2-weighted magnetic resonance imaging (MRI) of the lumbar spine.”
source quote (p.8)
“Mask Region-based Convolutional Neural Network”
source quote (p.6)
“User-confirmed/defined settings control the sensitivity of the software for labelling measurements in an image. The user (not the software) controls identifying out-of-range measurements, and, in every case once an out-of-range measurement is identified, the user must confirm or reject its presence.”
source quote (p.11)
“Remedy Logic conforms to the cybersecurity requirements by implementing a process of preventing unauthorized access, modifications, misuse or denial of use, or the unauthorized use of information that is stored, accessed or transferred from a medical device to an external recipient, per FDA Guidance for Industry and Food and Drug Administration Staff, Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions, issued on September 27, 2023, as well as FDA Guidance for Industry and Food and Drug Administration Staff, Postmarket Management of Cybersecurity in Medical Devices, issued on December 28, 2016. The vulnerability assessment and penetration testing demonstrated satisfactory security performance.”
Validation studies (1)
Retrospective clinical
n=238 patients · 5 site(s)
endpoints: For measurements, the maximum Mean Absolute Error (MAE) as defined as the upper limit of the 95% confidence interval for MAE is below a predetermined allowable error limit (MAE limit) for each measurement listed below. Table 10.; For segmentations of anatomical structures: the minimum Mean Dice Coefficient, defined as the lower limit of the 95% confidence interval for MDC, is above a predetermined allowable limit (MDC Limit) for each segmentation listed below. Table 9a.
standards: IEC 62304:2006/AMD 1:2015, ISO 14971:2019, IEC 62366-1:2015+AMD1:2020, ISO 15223-1:2016, NEMA PS 3.1 - 3.20 (2016)
Reported performance (1 observation)
source quote (p.14)
“0.968 0.92-0.98”
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).