RemedyLogic AI MRI Lumbar Spine Reader
K241108Remedy Logic Inc. · cleared 2024-10-30 · product code QIH · Radiology
Premarket evidence — what FDA accepted
source quote (p.8)
“Yes”
source quote (p.8)
“Convolutional Neural Network”
source quote (p.9)
“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=200 patients · 3 site(s)
endpoints: For 4 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.; For segmentations of 14 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.; For 10 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.
standards: IEC 62304 Edition 1.1 2015-06 CONSOLIDATED VERSION, ISO 14971 Third Edition 2019-12, IEC 62366-1 Edition 1.1 2020-06 CONSOLIDATED VERSION, ISO 15223-1 Fourth edition 2021-07, NEMA PS 3.1 – 3.20 2022d
Reported performance (14 observations)
source quote (p.13)
“Artery (Axial) 0.866 0.861 0.871 0.8 Yes”
source quote (p.13)
“Disc (Axial) 0.806 0.796 0.815 0.7 Yes”
source quote (p.13)
“Disc (Sagittal) 0.914 0.910 0.918 0.7 Yes”
source quote (p.13)
“Disc Material Outside IV Space (Axial) 0.803 0.793 0.812 0.7 Yes”
source quote (p.13)
“Dural Sac (Axial) 0.926 0.924 0.929 0.8 Yes”
source quote (p.13)
“Kidney (Axial) 0.879 0.872 0.886 0.8 Yes”
source quote (p.13)
“Ligamentum Flavum (Axial) 0.740 0.736 0.744 0.7 Yes”
source quote (p.13)
“Muscle (Axial) 0.946 0.945 0.947 0.8 Yes”
source quote (p.13)
“Sacrum (Sagittal) 0.925 0.923 0.928 0.8 Yes”
source quote (p.13)
“Spinal Canal (Axial) 0.942 0.941 0.944 0.8 Yes”
source quote (p.13)
“Spinal Canal (Sagittal) 0.871 0.865 0.877 0.8 Yes”
source quote (p.13)
“Vein (Axial) 0.821 0.815 0.827 0.8 Yes”
source quote (p.13)
“Vertebral Arch 0.846 0.843 0.850 0.8 Yes”
source quote (p.14)
“Vertebral Body (Sagittal) 0.900 0.894 0.905 0.8 Yes”
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).