Elderly · Strong theory
UTI & Delirium Behavioral Prodrome Detection
Flags the pattern — extra night bathroom trips, poor sleep, less activity — that precedes infection.
The physics is solid; our own validation is scheduled.
How it works
Each behaviour leaves its own trace in the WiFi field: trips to the bathroom, restless movement in bed, quieter days than usual. None of these alone means anything. When several drift away from that person's own normal at the same time, the system tells the family or nurse it may be worth a check-up.
In the physics: Each behavior has a distinct observable: bathroom visits are RTI transition events on the bedroom-bathroom path; sleep fragmentation is elevated in-bed Doppler burst rate; apathy is reduced total daily Doppler energy; hesitancy is increased micro-Doppler dwell at doorway transitions. No single signal is diagnostic — the correlated multi-axis deviation from the resident's own manifold is.
See it work
This is real pipeline output for Elderly, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
WiMANS/OPERAnet for the activity feature layer; own retrospective pilot: deploy in 20 units for 6 months, align anomaly scores against nursing records of UTI/delirium diagnoses (target: median 3-day lead time).
Who it is for
For geriatric nurse practitioners and value-based-care operators: 'The house calls the doctor before the confusion starts' — a 72-hour head start on the #1 cause of avoidable elderly hospitalization.
runtime Runs today in LatentField 2.0 as sleep_quality_proxy
The matching solution
Complete first-room estimateAging-in-Place Guardian3 nodes · ~$130 parts · 60 min Request kit, subscribe, or set up →Compatible DIY hardware options
15 min · beginner
60 min · intermediate