Skip to content
This is NOT an official site of the City of New York. Click here for official AI reports.

NYC Office of Technology and Innovation

NYC - DTPR AI Register

Back to your search

AI-Assisted EMS Unit Dispatch Routing for NYC

What it is for

Safety & Security
  • The algorithm supports emergency medical services by optimizing the search order for dispatch zones, enabling faster selection of the nearest available EMS unit for any incident across New York City.
Mobility
  • The system models emergency vehicle travel times across the city's road network to rank geographic response atoms from closest to furthest, directly enabling efficient routing of EMS units.
Run by
Fire Department (FDNY)
Where
No fixed location
Kept
Retained not specified
Shared with
Accountable organization, Vendor
Your copy
You cannot see the data it holds about you. What you can do

What it is for

Safety & SecurityMobility

This algorithm determines the order in which geographic response zones are searched so that the emergency dispatch system can select the closest available EMS unit for any given incident. It relies on historical trip-time data and a calibrated travel-time network model to rank zones by proximity. The system does not collect personal information about individuals. Starting in September 2025, the model also accounts for time of day and day of week when generating recommended search orders.

What it collects and what happens to it

Data taken in

About a place
Anonymized data
  • Geographic locations of dispatch zones (atoms) across New York City, representing the spatial units the algorithm ranks for each potential incident location. Includes time of day as of September 2025.
About a measurement
Anonymized data
  • Historical EMSCAD emergency unit response trip-time data used to calibrate the network analysis model that derives atom-to-atom transport times. No personal or identifying information is included.

Processing

Optimization
  • A calibrated network analysis model computes atom-to-atom travel times and ranks geographic zones from closest to furthest for each possible dispatch origin. The updated September 2025 model accepts time of day as an input to vary recommendations by time period and day of week.

What it does

Deciding (Analytical AI)
Human executes
  • The algorithm ranks geographic zones (atoms) from closest to furthest in travel time, producing an ordered list that the EMSCAD dispatch system uses to select an EMS unit. The algorithm decides the search order; a dispatcher or the EMSCAD system executes the resulting unit assignment.

Outputs

A recommendation or prediction
Anonymized data
  • An ordered list of geographic atoms (response zones) ranked from closest to furthest in travel time, delivered as an Excel file converted to an EMSCAD-compatible format and loaded into the dispatch system for real-time unit selection. As of September 2025, separate orderings are produced for different times of day and days of week.

Run by

Fire Department (FDNY)
  • The NYC Fire Department's Management Analysis and Planning unit deploys and operates the EMS Unit Suggestion Algorithm to support real-time emergency dispatch decisions.

NYC Algorithmic Tools Compliance Report

Built by

Deccan International
  • Deccan International is the professional services vendor that provides the EMS Unit Suggestion Algorithm and produces the output file loaded into the EMSCAD dispatch system.

NYC Algorithmic Tools Compliance Report

Kept for

Retained not specified
  • The register does not specify a retention period. Historical EMSCAD trip-time data is retained to support ongoing model calibration; the output files are loaded into the dispatch system and replaced on a daily update cycle.
  • Duration: not specified

Shared with

Not available to me
  • No identifying information about individuals is collected or disclosed. The algorithm operates on geographic zones and aggregate travel-time data only; members of the public have no data subject access rights because no personal data is held.
Available to the accountable organization
  • The output file and algorithm parameters are available to the NYC Fire Department and loaded into the EMSCAD system for operational use by dispatch staff.
Available to vendor
  • Deccan International, as the professional services vendor that produces the algorithm and output file, has access to the historical trip-time data and model parameters used in the computation.

Stored

Stored locally
  • The output file is loaded into the EMSCAD system operated by the NYC Fire Department. Storage jurisdiction and infrastructure are not detailed in the register entry, but deployment is within NYC city government systems.
  • Duration: not specified
How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the NYC Office of Technology and Innovation, not the vendor.

Your rights

  • Right to Be Informed of AI UseMembers of the public are informed of this algorithm through NYC's Algorithmic Tools Compliance Report, publicly available at the NYC Open Data portal. Because no personal data is collected, individual notification mechanisms are not applicable.
  • Right to Algorithmic TransparencyInformation about how this algorithm works — including its purpose, inputs, outputs, and vendor — is disclosed in the NYC Algorithmic Tools Compliance Report, accessible through the NYC Open Data portal at https://data.cityofnewyork.us/City-Government/Algorithmic-Tools-Compliance-Report/jaw4-yuem.

Risks and safeguards

  • Civil liberties harmUnequal EMS response times across different geographic areas or demographic groups if the travel-time model has calibration gaps or historical data biases.Safeguard: The algorithm is described as informative rather than fully autonomous — the EMSCAD system and dispatchers retain the ability to override recommendations. The model is updated regularly (including a September 2025 update adding time-of-day inputs) to improve calibration. Disclosure through the NYC Algorithmic Tools Compliance Report provides public accountability.