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 Bacterial Genome Analysis for Outbreak Detection

What it is for

Healthcare
  • Used by the NYC Public Health Laboratory to support foodborne disease surveillance — identifying bacterial strains, confirming outbreak clusters, and informing epidemiological investigations that may lead to restaurant inspections, closures, and food recalls.

NYC AI Use Cases — PulseNet 2.0

Research & Development
  • Supports multi-jurisdictional outbreak detection and public health surveillance coordination by generating nationally comparable genomic relatedness and clustering results shared with the CDC and partner laboratories.

NYC AI Use Cases — PulseNet 2.0

Run by
Department of Health and Mental Hygiene (DOHMH)
Where
No fixed location
Kept
Not stated by the NYC Office of Technology and Innovation.
Shared with
Accountable organization, Vendor
Your copy
You cannot see the data it holds about you. What you can do

What it is for

HealthcareResearch & Development

PulseNet 2.0 is a suite of bioinformatics tools used by the NYC Department of Health and Mental Hygiene to sequence, classify, and cluster bacterial genomes from foodborne illness cases. It helps public health laboratories identify whether cases of foodborne disease are genetically related, potentially indicating a common outbreak source. Results are shared with epidemiologists who may initiate restaurant inspections, closures, or food recalls. No personally identifying information about patients is collected or disclosed by the system.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Standardized bacterial DNA sequencing data (genomic reads) submitted by public health laboratories. This represents fragmented and amplified bacterial genome data, not personally identifiable information about patients.

NYC AI Use Cases — PulseNet 2.0

Processing

Clustering & Segmentation
  • Performs core and whole genome multi-locus sequence typing (cgMLST/wgMLST) and cluster analysis to identify genetically related bacterial isolates. Clusters cases using CDC-recommended case definitions to detect potential outbreak groups across jurisdictions.

NYC AI Use Cases — PulseNet 2.0

Classification & Prediction
  • Identifies the genus, species, and serotype of bacterial isolates from sequencing data, and performs quality control checks to ensure sequence data meets required standards before downstream analysis.

NYC AI Use Cases — PulseNet 2.0

What it does

Deciding (Analytical AI)
Human decides
  • Performs genome assembly, species identification, quality control, multi-locus sequence typing, and cluster analysis. Outputs are reviewed by foodborne epidemiologists who decide on investigative and regulatory actions.

NYC AI Use Cases — PulseNet 2.0

Outputs

About a measurement
Anonymized data
  • Nationally comparable genomic relatedness scores, cluster assignments, species and serotype classifications, and quality metrics for each bacterial isolate. Results are shared with foodborne epidemiologists and public health partners for outbreak surveillance coordination.

NYC AI Use Cases — PulseNet 2.0

A recommendation or prediction
Anonymized data
  • Cluster analysis results inform epidemiological partners about cases likely related to a common source, potentially triggering restaurant inspections, closures, or food recalls — though those consequential actions remain human decisions.

NYC AI Use Cases — PulseNet 2.0

Run by

Department of Health and Mental Hygiene (DOHMH)
  • The NYC Department of Health and Mental Hygiene, Disease Control – Public Health Laboratory, deploys PulseNet 2.0 to analyze bacterial genomes and coordinate outbreak surveillance.

NYC AI Use Cases — PulseNet 2.0

Built by

Centers for Disease Control and Prevention (CDC) and Booz Allen Hamilton
  • The CDC and Booz Allen Hamilton developed and maintain PulseNet 2.0. The tool is procured via a paid pilot arrangement.

NYC AI Use Cases — PulseNet 2.0

Kept for

Not stated by the NYC Office of Technology and Innovation.

Shared with

Available to the accountable organization
  • Clustering and relatedness results are available to the NYC Department of Health and Mental Hygiene's Disease Control bureau and its foodborne epidemiology partners for outbreak investigation.

NYC AI Use Cases — PulseNet 2.0

Available to vendor
  • As the national coordinator of PulseNet, the CDC has access to submitted sequencing results and cluster data as part of the national surveillance network for multi-jurisdictional outbreak detection.

NYC AI Use Cases — PulseNet 2.0

Not available to me
  • No identifying information about individual patients is collected or disclosed. Members of the public do not have access to individual-level genomic or cluster data from this system.

NYC AI Use Cases — PulseNet 2.0

Stored

Not stated by the NYC Office of Technology and Innovation.

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 Algorithmic TransparencyMembers of the public can learn about how PulseNet 2.0 works through the CDC's published documentation on the PulseNet national surveillance network. The system uses scientifically established methods (genome assembly, MLST, cluster analysis) with criteria defined by the CDC. For more information, contact the NYC Department of Health and Mental Hygiene, Disease Control division.

Risks and safeguards

  • Civil liberties harmCluster results communicated to partners could indirectly implicate individuals if linkage to identifying case data occurred outside the system.Safeguard: The system explicitly collects no identifying information; sequencing data is submitted as standardized biological measurements. Outputs are cluster-level relatedness scores, not individual records. Human epidemiologists exercise judgment before any regulatory action such as inspections or closures.