Deep Capsule® (Deep Capsule US)
K250655Digestaid - Artificial Intelligence Development SA · cleared 2026-03-12 · product code QZF · Gastroenterology-Urology
Premarket evidence — what FDA accepted
source quote (p.4)
“Deep Capsule® is an artificial intelligence (AI) assisted reading tool designed to aid small bowel capsule endoscopy reviewers in decreasing the time to review capsule endoscopy images for adult patients in whom the capsule endoscopy images were obtained for suspected small bowel bleeding.”
source quote (p.7)
“The Deep Capsule detection algorithm is based on convolutional neural networks using different deep learning models.”
source quote (p.8)
“Regarding the cybersecurity, documentation included recommended information from the FDA guidance document "FDA Cybersecurity in Medical Devices: Quality System Considerations and Content of Premarket Submissions" This includes threat identification, vulnerability assessment, likelihood and impact assessment, cybersecurity mitigation information, security policies and controls, continuous monitoring and review activities, regular auditing and cybersecurity testing.”
Validation studies (3)
Standalone
n=272 patients
endpoints: Sensitivity; Specificity; AUC
Standalone
n=96,082 images
endpoints: Sensitivity; Specificity; AUC
Retrospective clinical
n=330 patients · 7 site(s)
endpoints: Diagnostic yield; sensitivity; specificity; positive predictive value; negative predictive value; mean reading time
Reported performance (5 observations)
source quote (p.26)
“0.972 (0.947 - 0.986)”
source quote (p.26)
“0.125 (0.055 - 0.261)”
source quote (p.26)
“AUC = 0.816 95% CI: 0.690-0.942”
source quote (p.26)
“0.890 (0.850 - 0.920)”
source quote (p.26)
“0.385 (0.177 - 0.645)”
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).