Turn ED chaos into a signal your whole hospital can read
NEDOCS converts census, boarding, and flow inputs into five color-coded threat bands — so charge nurses, bed management, and leadership share one live picture. Now with a 2-hour forecast, a locally calibrated ED Operations Index, and direct, consented state & EMS integrations. Backed by 119 peer-reviewed studies.
Drive the reactor, ping AEDA, and open the evidence to complete the sequence.
Shift intelligence (example)
Volume and admit-hold pressure are elevated; longest boarding time is driving the score. Consider an inpatient-capacity huddle and diversion policy per local protocol—not a substitute for clinical judgment.
Drive the surge reactor
Slide the dials and watch the NEDOCS score react in real time. Cross into the red and the deck goes to alert. (Yes, it's the same math your shift would see.)
// throughput rising. monitor door-to-bed vector.
Illustration only — a simplified, playful approximation of NEDOCS drivers. Launch the full console →
Why hospitals run NEDOCS
A validated overcrowding index — not a whiteboard guess.
Boarding shows up in the score
Longest admit and inpatient beds reflect hospital-wide bottlenecks — not just the front door.
One language for the shift
Normal through Disaster — repeatable in every huddle, every handoff, every escalation call.
Throughput you can see
Door-to-bed and census inputs surface flow problems early — before they snowball into diversion.
Three big additions to NEDOCS
A 2-hour forecast that sees around the corner, a locally calibrated companion score, and a consent-driven way to send your status to state and EMS agencies.
The 2-hour forecast
Projects where your NEDOCS score is heading — with an honest uncertainty band, the likely band, and the probability you escalate before the next handoff.
- Point estimate and an 80% range
- Probability of crossing into a higher band
- Plain-language drivers, including weather & respiratory pressure
- Backtested model — only serves when it beats the baseline
The ED Operations Index
A 0–100 composite that z-scores your boarding, reserve drain, workload, and waits against your facility's own trailing 90 days — and flags when local strain is racing ahead of NEDOCS.
- Five local bands: Steady, Elevated, Stressed, Critical, Saturated
- Show-your-work panel on every dashboard tile
- Tunable weights from
Settings → Operations Index - Sits next to NEDOCS — never replaces it
State HAvBED · EMResource · WebEOC · EMS
Push your live NEDOCS, boarding load, and operational flags to the agencies that need them — directly from your dashboard, in the format they already speak.
- Hospital-controlled, scoped, revocable grants
- Five formats: JSON v1, FHIR R4, EMResource JSON, CSV, HAvBED XML
- HMAC-signed webhooks with exponential backoff
- Seven-year audit log, dead-letter queue, rate limits
Five color-coded threat bands
Your hospital maps local actions to each level — like a difficulty setting for your shift. Read the playbook →
Normal
Within usual capacity — cruise control.Busy
Elevated activity — eyes on the board.Overcrowded
Material strain — call the huddle.Severe
High diversion risk — escalate.Disaster
Extreme overload — surge plan on. 🚨Built on 119 peer-reviewed studies
Every tile, score, and recommendation traces back to a citation we publish in source control.
Machine learning for high-acuity LWBS prediction
XGBoost and temporal fusion transformer models reached AUC 0.86 for predicting high-acuity LWBS — using the same NEDOCS inputs the app already collects.
Kappy, Bhakta, Lalonde et al. →A Machine Learning Strategy to Predict the Number of High-Acuity Children Who Leave Without Being Seen From the Emergency Department
Examines a Machine Learning Strategy to Predict the Number of High-Acuity Children Who Leave Without Being Seen From the Emergency Department.
Brandon Kappy MD MPP →An unsupervised machine learning approach for defining surge levels in emergency medical services
Examines an unsupervised machine learning approach for defining surge levels in emergency medical services.
Qixuan Zhao →Development and Implementation of the Modified Pediatric Emergency Department Overcrowding Scale in Two Large Academic Pediatric Centers
Examines development and Implementation of the Modified Pediatric Emergency Department Overcrowding Scale in Two Large Academic Pediatric Centers.
Nathan Timm MD →Ready to start your shift?
Launch the live console first — no sign-in. When it matches what your shift looks like, drop your email and we'll set up your hospital.
Psst — type "surge" for red alert, or the Konami code for a grid-warp. 🎉