CAM-120
A patient waiting alone in the corridor
A hospital corridor. A patient in a gown and slippers is sitting on the bench against the wall, a cannula in his hand, looking straight ahead. Beside him an empty wheelchair stands in the middle of the corridor. At the far end, the nurses' station counter, with nobody behind it. No staff walk past. IRIS counts how long he has been there and how many people are nearby; it does not know who he is or what he is waiting for.
Turn on IRIS Vision
AI-generated image
What IRIS understands
What it recognises in this scene
- patient waiting alone
- wheelchair standing idle
- corridor bench
- empty nurses' station
- doors to a room
What this camera measures
An alert says something is happening. The reading says how much.
- 18 minwaiting for
- 15 minlimit set by the hospital
- 0staff who have walked past
- 0people at the station
- 1people in the corridor
- 09:37time of the alert
The figures on this screen are an example from the illustration, not any client's measurement.
The rule
You decide once. IRIS applies it always.
If
there is a person alone in a common area, with nobody else nearby, for longer than the hospital has set
Then
- alert the nurses' station with the camera, the spot in the corridor and how long it has been
- state how many staff have walked past in that time
- keep the elapsed time, so the hospital learns in which corridors and at what hours this happens
The instruction that set it up«Tell me if a patient has been alone in a corridor for a long while, with nobody coming near them.»
What changes
What changes for whoever runs the ward
A patient brought down for a test, sitting on a corridor bench, wheelchair parked beside him and the nurses' station empty at the far end. There is no incident here: it is simply that nobody knows he is still there. And the time he spends alone in a corridor is the time in which, if he stands up and gets dizzy, there is nobody in front of him. IRIS does not care for anyone: it counts the time and tells the ward that at this spot someone has been waiting for longer than the hospital considers reasonable. Most of the time it will be enough for someone to look in and tell him how much longer — and that is exactly the point: that nobody is left forgotten in a corridor.
What people usually ask
Does IRIS know which patient this is and why he is there?
No. IRIS does not identify anyone: it does not recognise faces, it does not compare them against any database, it does not store who anyone is and it does not access any medical record or the hospital's systems. It does not know whether that person is waiting for a test, for a porter or for their discharge. All it knows is that there is a person sitting at that spot and how long they have been there. The rest is supplied by the team, who do have that information and do know what to do with it.
Where are there cameras, and where are there none?
These cameras look at common areas: corridors, waiting areas and lobbies. There is no camera in any room, in any bathroom and in any examination room, nor anywhere a patient is treated or examined. The place where someone is cared for is not watched; the place people walk through is — and only to know that someone is waiting there and since when.
Won't this end up giving a hundred alerts a shift?
It depends on how the rule is written, and the hospital writes it. It is set per area and per time band: a bench in a diagnostics corridor at nine in the morning is not the same as a lobby at eleven at night. An alert that fires constantly stops being read within a week, so the aim is not to alert a lot — it is to alert when someone has been there longer than the ward would consider normal. That threshold is tuned with the team and reviewed against what actually happens on shift.
Simulation · how IRIS works
Watch what happens. Then watch what IRIS does with it.
Not a recorded video and not a drawing: it is a summary of the real tool, with a different case each time round. The whole tool does not fit in a box.
- The rule gets built
- It goes to every camera
- Published, it watches alone
- And then it fires
Next step
When does a bad review get decided?
15 cases: 11 raise an alert when something happens and 4 only measure. You see each image as it is, and then with what IRIS understands on top.
Who is watching a whole quay at three in the morning?
14 cases: 13 raise an alert when something happens and 1 only measure. You see each image as it is, and then with what IRIS understands on top.
And the best part
Adding a camera costs what it costs;adding someone to watch it costs every single month.
Past a certain number, almost nobody is watching anything. IRIS watches them all at once and only calls you when something you said mattered happens in one of them.
Tell us your problem and we will say whether IRIS understands it, or not yet.
We reply the same working day.