FIGURA.
CONTACT-FREE BEDSIDE SENSING
Sees the form. Never the face.
Much of what matters in a bedspace is physical: whether a patient has moved, how they are lying, whether someone reached for the bed rail. FIGURA reads that as geometry, in the room, and passes only structured observations to the clinician.
The name
Figura is the Latin for form or shape, and that is the whole of what the system perceives. It resolves the human figure into joints, limbs, and orientation, and works from that skeleton alone. There is no face, no identity, and no likeness in the data, because none is ever produced.
In the bedspace
Geometry in, observations out
Bedspace geometry
Pose only, no imagery storedPrivacy architecture
The imagery never leaves the room
Processed at the sensor
Frames are converted to pose geometry on the device in the room. The frames themselves are discarded immediately and never written to disk.
Geometry only downstream
What travels onward is a set of coordinates and derived events. There is no image, no video, and nothing from which a person could be recognised.
Nothing to breach
Because no imagery is stored anywhere in the system, there is no footage archive to secure, subpoena, or lose.
Capabilities
What it observes
- Posture and position, including prone and lateral positioning intervals
- Movement and stillness over time, at the interval the unit sets
- Bed-exit and reach-beyond-rail events for clinician review
- Presence and occupancy of the bedspace
- Every observation timestamped and written to the audit trail
Boundaries
What it will not do
- No facial recognition, no identification, and no likeness of any kind
- No stored or streamed video, and no remote viewing feature
- No autonomous alarm that bypasses the clinician
- No diagnosis. Observations are inputs to clinical judgement, never conclusions
Deployment
Where it runs, and on what
- PlacementOne sensor per bedspace, mounted to existing fixtures
- InferenceOn the sensor and the unit node, inside the institution's network
- ImageryConverted to pose geometry in the room, never stored or transmitted
- Data outPose coordinates and derived events only
- IntegrationFeeds TRINITY as one more bedside signal
- GovernanceRuns under SALVEA policy, audit, and evaluation
Compliance
Designed to operate within PIPEDA and provincial health-information acts.
- PIPEDA
- Provincial health-information acts
- HL7 FHIR
- SNOMED CT
- ICD-10-CA
Why units adopt it
Continuous observation, without a camera in the room
01 / Contact-free
Nothing is attached to the patient, so there is no additional line, lead, or skin contact to manage.
02 / Continuous
Positioning and movement are observed between rounds, not only when a clinician is at the bedside.
03 / Consentable
Because no likeness exists, the privacy conversation with patients and families starts from a much simpler place.
04 / Clinician-bounded
Every flagged event goes to a clinician for review. The system never acts on what it sees.
The safety property built into the platform, not a setting on top of it. A qualified human holds the judgement and the accountability: every model, agent, and workflow is designed to inform that person and stop at them.
A clinician decides
The system surfaces evidence, risk, and reasoning. It does not order, prescribe, or act on a patient. Every clinically consequential step waits on a named person with the authority to take it.
Approval before action
Anything sensitive routes to explicit human approval before it takes effect. The approval gate is enforced in the platform itself, not left to policy documents or user discipline.
Reasoning shown, not hidden
Every output carries what it drew on, what it was missing, and how it was formed, so the reviewing clinician can accept, question, or reject it on the evidence rather than on trust.
Accountability stays human
The operator, the custodian, the key-holder, and the approver are the institution's own people. Clinical accountability is never transferred to a model or to us.