| K-number | K242171 |
| Device name | TechCare Trauma |
| Applicant | Milvue |
| Product code | QBS |
| Device class | Class II |
| Decision date | Jan 17, 2025 |
| Decision | Substantially Equivalent |
| Regulation | 892.2090 |
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.
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.
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.
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.
View the full FDA submission: accessdata.fda.gov