16 Bit

By 16 Bit
· Canada
AI software that estimates the likelihood of low bone density on routine frontal X-rays of adults aged 50 and over, flagging patients for a DXA scan as a pre-screening aid for radiologists.
Radiology
FDA Cleared
Regulatory status
FDA Cleared
Deployment
Clinical role
Adjunct (decision support)
Headquarters
Canada
AI type

Precise indication

Analyses routine frontal X-rays (chest, thoracic or lumbar spine, pelvis, knee, hand/wrist) of patients aged 50 and over to flag possible low bone density at the hip or lumbar spine. It is a pre-screening aid for radiologists, not a diagnosis, and must not be used to rule out low bone density.

Regulatory status

Listed in the FDA AI-Enabled Medical Devices list (1 device(s), latest decision 2024, FDA panel: Radiology). Exact clearance number(s) to be confirmed.

Clinical evidence

Vendor-supported
Independent

Auriat et al., JBMR Plus 2025, retrospective single-centre study in Ottawa, 4,878 patients with DXA: AUC 0.84 for low bone density and 0.82 for osteoporosis; at a score cut-off of 7, sensitivity was 60% and specificity 87% for low bone density (vendor supplied the software only).

Real-world deployment

Interoperability

DICOM routing from PACS, result returned as a new PACS series; optional HL7 output to dictation systems (vendor-claimed)

European status

No named European hospital or country found. The vendor states CE marking in 2026, but its cloud service Rho Direct is not available in the European Economic Area.

Editorial verdict

Limits and uncertainties

– Pre-screening aid only: it does not diagnose osteoporosis, replace DXA or rule out low bone density.
– At a high-specificity cut-off, about 4 in 10 patients with low bone density were missed (Ottawa study).
– Most studies are by vendor authors; one independent validation, single-centre and retrospective.
– No published data on fracture outcomes, cost-effectiveness or European patients.
– For patients aged 50 and over only; US and international versions report different outputs.

Sources

FDA, Artificial Intelligence-Enabled Medical Devices list (accessed 12 November 2026): https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-enabled-medical-devices Regulator — FDA, De Novo database entry DEN230023 (Rho, 16 Bit Inc.), accessdata.fda.gov, April 2024 https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/denovo.cfm?id=DEN230023 Vendor — 16 Bit, Home page (product, customers, regulatory list), 16bit.ai, accessed November 2026 https://16bit.ai/ Vendor — 16 Bit, Rho product page (intended use, integration, Rho Direct availability), 16bit.ai, accessed November 2026 https://16bit.ai/rho Vendor — 16 Bit, Trust and regulatory page (FDA, Health Canada, CE 2862, hosting), 16bit.ai, accessed November 2026 https://16bit.ai/trust Study (vendor-authored) — Bilbily et al., Opportunistic Screening of Low Bone Mineral Density From Standard X-Rays, J Am Coll Radiol, April 2024 https://pubmed.ncbi.nlm.nih.gov/37805012/ Study (vendor-authored) — Syme et al., Clinical impact of adopting an AI-driven opportunistic bone health screening software, Skeletal Radiology, 2026 https://pubmed.ncbi.nlm.nih.gov/41670644/ Study (independent) — Auriat et al., Evaluating an AI software for opportunistic low BMD and osteoporosis screening: a validation study, JBMR Plus, December 2025 https://pmc.ncbi.nlm.nih.gov/articles/PMC12790272/

This profile is not medical advice or an endorsement. Hospitals should perform their own due diligence (regulatory compliance, GDPR, cybersecurity, integration, local clinical validation). How we evaluate

At a glance
Vendor
16 Bit
Headquarters
Canada
AI type
Specialty
Clinical role
Adjunct (decision support)
CE marking
Notified body
EU AI Act
Data hosting
On-premises (customer network)
Last verified
Reviewed by
How we evaluate

Every profile documents the precise indication, regulatory status, vendor-supported and independent evidence, real-world deployment, limits and dated sources.

A independent systematic review or prospective multicentre study · B at least one independent peer-reviewed study · C peer-reviewed, vendor-supported · D vendor claims only.

Read the methodology →

Spotted an error?

Vendors, authors and clinicians can request a correction. Corrections are dated on the profile.