TechCare Trauma

K242171

Milvue · cleared 2025-01-17 · product code QBS · Radiology

Premarket evidence — what FDA accepted

Device typesamd

source quote (p.8)

“The TechCare Trauma device is a software as Medical Device (SaMD).”

AlgorithmSupervised Deep Learning

source quote (p.14)

“Supervised Deep Learning”

Adaptive (vs locked)No

source quote (p.11)

“TechCare Trauma operates based on two fixed operating points, which determine the result status of each finding:”

PCCPNo

Cybersecurity addressedNo

Validation studies (2)

Bench

n=7,744 images · 4 site(s)

endpoints: image-level Area Under The Curve (AUC) of the Receiver Operating Characteristic (ROC)

Reader study (MRMC)

n=769 cases · 4 site(s)

endpoints: diagnostic accuracy of readers aided by TechCare Trauma is superior to the diagnostic accuracy of readers unaided by TechCare Trauma, as determined by the case-level AUC of the ROC curves (primary endpoint)

Reported performance (24 observations)

sensitivity0.906CI 0.891; 0.919

source quote (p.19)

“Se (High Sp) 0.906 [0.891; 0.919]”

specificity0.9CI 0.887; 0.912

source quote (p.19)

“Sp (High Sp) 0.900 [0.887; 0.912]”

aurocas written: “auc”0.962CI 0.957 - 0.967

source quote (p.17)

“Fracture - Adult (4109) 0.962 [0.957 - 0.967]”

aurocas written: “AUC Fracture - Pediatric”0.962CI 0.955 - 0.969

source quote (p.17)

“Fracture - Pediatric (2872) 0.962 [0.955 - 0.969]”

aurocas written: “AUC EJE - Adult”0.965CI 0.936 - 0.986

source quote (p.17)

“EJE - Adult (280) 0.965 [0.936 - 0.986]”

aurocas written: “AUC EJE - Pediatric”0.976CI 0.963 - 0.986

source quote (p.17)

“EJE - Pediatric (483) 0.976 [0.963 - 0.986]”

sensitivityas written: “Sensitivity EJE - Adult (Se (High Sp))”0.821CI 0.719; 0.893

source quote (p.19)

“Se (High Sp) 0.821 [0.719; 0.893]”

specificityas written: “Specificity EJE - Adult (Sp (High Sp))”0.98CI 0.949; 0.993

source quote (p.19)

“Sp (High Sp) 0.980 [0.949; 0.993]”

sensitivityas written: “Sensitivity Fracture - Pediatric (Se (High Sp))”0.9CI 0.882; 0.916

source quote (p.19)

“Se (High Sp) 0.900 [0.882; 0.916]”

specificityas written: “Specificity Fracture - Pediatric (Sp (High Sp))”0.927CI 0.913; 0.938

source quote (p.19)

“Sp (High Sp) 0.927 [0.913; 0.938]”

sensitivityas written: “Sensitivity EJE - Pediatric (Se (High Sp))”0.669CI 0.587; 0.744

source quote (p.19)

“Se (High Sp) 0.669 [0.587; 0.744]”

specificityas written: “Specificity EJE - Pediatric (Sp (High Sp))”0.977CI 0.954; 0.989

source quote (p.19)

“Sp (High Sp) 0.977 [0.954; 0.989]”

aurocas written: “Reader ROC AUC Adult fracture (aided)”0.955CI 0.924; 0.979

source quote (p.20)

“Reader ROC AUC significantly improved from 0.865 [0.822; 0.907] to 0.955 [0.924; 0.979]”

sensitivityas written: “Reader Sensitivity Adult fracture (aided)”0.983CI 0.966-0.996

source quote (p.20)

“Reader Sensitivity significantly improved from 0.807 (95% CI: 0.737-0.865) to 0.983 (95% CI: 0.966-0.996)”

specificityas written: “Reader Specificity Adult fracture (aided)”0.827CI 0.734-0.901

source quote (p.20)

“Reader Specificity improved from 0.815 (95% CI: 0.724-0.886) to 0.827 (95% CI: 0.734-0.901)”

aurocas written: “Reader ROC AUC Adult EJE (aided)”0.914CI 0.862; 0.959

source quote (p.20)

“Reader ROC AUC significantly improved from 0.851 [0.783; 0.913] to 0.914 [0.862; 0.959]”

sensitivityas written: “Reader Sensitivity Adult EJE (aided)”0.983CI 0.954-1.000

source quote (p.20)

“Reader Sensitivity significantly improved from 0.872 (95% CI: 0.789-0.940) to 0.983 (95% CI: 0.954-1.000)”

specificityas written: “Reader Specificity Adult EJE (aided)”0.746CI 0.645-0.845

source quote (p.21)

“Reader Specificity improved from 0.738 (95% CI: 0.635-0.835) to 0.746 (95% CI: 0.645-0.845)”

aurocas written: “Reader ROC AUC Pediatric fracture (aided)”0.931CI 0.892; 0.963

source quote (p.21)

“Reader ROC AUC significantly improved from 0.857 [0.810; 0.899] to 0.931 [0.892; 0.963]”

sensitivityas written: “Reader Sensitivity Pediatric fracture (aided)”0.964CI 0.940-0.984

source quote (p.21)

“Reader Sensitivity significantly improved from 0.804 (95% CI: 0.747-0.864) to 0.964 (95% CI: 0.940-0.984)”

specificityas written: “Reader Specificity Pediatric fracture (aided)”0.797CI 0.700-0.882

source quote (p.21)

“Reader Specificity remained the same at 0.797 (95% CI: 0.700-0.873) to 0.797 (95% CI: 0.700-0.882)”

aurocas written: “Reader ROC AUC Pediatric EJE (aided)”0.941CI 0.890; 0.978

source quote (p.21)

“Reader ROC AUC significantly improved from 0.877 [0.824; 0.929] to 0.941 [0.890; 0.978]”

sensitivityas written: “Reader Sensitivity Pediatric EJE (aided)”0.975CI 0.939-1.000

source quote (p.21)

“Reader Sensitivity significantly improved from 0.825 (95% CI: 0.742-0.895) to 0.975 (95% CI: 0.939-1.000)”

specificityas written: “Reader Specificity Pediatric EJE (aided)”0.851CI 0.769-0.926

source quote (p.21)

“Reader Specificity improved from 0.839 (95% CI: 0.764-0.914) to 0.851 (95% CI: 0.769-0.926)”

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

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).