K-numberK242171
Device nameTechCare Trauma
ApplicantMilvue
Product codeQBS
Device classClass II
Decision dateJan 17, 2025
DecisionSubstantially Equivalent
Regulation892.2090
AI Summary extracted from FDA summary PDF · never regenerated
Intended use

TechCare Trauma is a software-as-a-medical-device (SaMD) that uses artificial intelligence to analyze 2D X-ray radiographs and aid clinicians in detecting, localizing, and characterizing fractures and elbow joint effusions across multiple anatomical sites in patients of all ages, from neonates through adults. Results are not intended for standalone clinical decision-making but rather to assist clinicians in various care settings including primary care, emergency medicine, and specialty care.

Technological characteristics

TechCare Trauma uses supervised deep learning methodology, processes DICOM image sources automatically without manual intervention, generates annotated secondary capture images with bounding boxes and DICOM structured reports, and operates via two fixed confidence-based operating points (DOUBT for high sensitivity, YES for high specificity). It can be deployed on-premises or in the cloud and integrates with PACS systems and multiple imaging hardware manufacturers, mirroring the predicate device's architecture but excluding spine analysis and adding elbow joint effusion detection capabilities.

Test standards cited

Not stated in this summary. The document references FDA guidance documents on software premarket submissions and device software changes but does not cite specific ISO, IEC, ASTM, or other consensus standards.

Substantial equivalence argument

Both devices are Class II radiological CADe/x software regulated under 21 CFR 892.2090 with product code QBS, operate on identical 2D X-ray image modality using supervised deep learning, and share the same fundamental technological principles and deployment architecture. Performance testing demonstrated TechCare Trauma achieves ROC-AUC of 0.962 (adults) and 0.962 (pediatrics) for fracture detection and 0.965 (adults) and 0.976 (pediatrics) for elbow joint effusion detection, with clinical reader studies showing significant performance improvements over unaided reading. The minor differences—exclusion of spine, addition of elbow joint effusion indication, and expanded neonatal/infant population—do not raise new safety or effectiveness questions because all indications were assessed in the performance studies and demonstrated maintained performance across all populations and anatomical regions.

Extracted by AI from the official FDA summary PDF →
Source

View the full FDA submission: accessdata.fda.gov

Researching this as a predicate?
Want a transparent AI-ranking score, AI-discovered related predicates, ongoing safety and warning-letter monitoring, full predicate chain lineage, and a drafted SE rationale — all saved to your own project? That's what an account adds.
Start free trial →

Everything you need for a 510(k) submission. Nothing you don't.

14-day free trial. No setup. Cancel anytime.

Start free trial →
Building an AI or ML-enabled device? Predicate search, PCCP tracking, and AI-specific FDA intelligence — built exclusively for AI/ML devices. Try AIFDA Intel →