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

AI-Assisted Bacterial Outbreak Detection via Genome Analysis

What it is for

Healthcare
  • Used by public health laboratory staff to investigate potential bacterial outbreaks by assessing genetic relatedness among isolates — supporting epidemiological decision-making about whether cases share a common source.
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
Your copy
You cannot see the data it holds about you. What you can do

What it is for

Healthcare

This system analyses bacterial genome sequences to build phylogenetic trees — visual maps of genetic relatedness among bacterial isolates — to help public health scientists determine whether cases share a common source and may constitute an outbreak. It is used by NYC Department of Health and Mental Hygiene laboratory staff 2–3 times per week. No identifying information about individual patients is collected or disclosed; inputs are laboratory sequencing data about bacteria, not people.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Assembled genome sequences generated from laboratory sequencing data of bacterial isolates. No identifying information about individuals is collected or linked to these sequences at the point of input.

Processing

Clustering & Segmentation
  • Applies multiple algorithms — maximum-likelihood, parsimony, and neighbor-joining — to cluster bacterial isolates by genetic similarity based on single-nucleotide polymorphisms (SNPs) derived from assembled genome sequences.

What it does

Deciding (Analytical AI)
Human decides
  • Produces phylogenetic trees and SNP-based relatedness scores from genome sequences. Human epidemiologists and laboratory scientists review the output to decide whether to rule in or out a bacterial outbreak — the system is supervised and advisory, not determinative.

Outputs

About a measurement
Anonymized data
  • Single-nucleotide polymorphism (SNP)-based relatedness results and phylogenetic trees summarizing genetic similarity among bacterial isolates. These outputs are used by epidemiologists to inform outbreak investigation decisions; they contain no identifying information about individuals.
A recommendation or prediction
Anonymized data
  • The phylogenetic trees and SNP relatedness results serve as advisory outputs that help investigators rule in or rule out bacterial outbreaks. The final outbreak determination is made by human public health scientists.

Run by

Department of Health and Mental Hygiene (DOHMH)
  • The Public Health Laboratory within the Disease Control division deploys kSNP4 to perform phylogenetic analysis of bacterial genomes for outbreak investigation purposes.

NYC AI Use Case Register (kSNP4)

Built by

Not stated by the NYC Office of Technology and Innovation.

Kept for

Not stated by the NYC Office of Technology and Innovation.

Shared with

Not available to me
  • No identifying information about individuals is collected or disclosed. Members of the public have no personal data in this system to access. The tool processes only de-identified laboratory sequencing data about bacterial isolates.
Available to the accountable organization
  • Phylogenetic trees and SNP relatedness results are available to NYC DOHMH Disease Control laboratory and epidemiology staff for outbreak investigation purposes.

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 TransparencykSNP4 is an open-source, published tool. Its algorithms — maximum-likelihood, parsimony, and neighbor-joining phylogenetic methods — are documented in peer-reviewed literature (PubMed PMID 37948764). Members of the public may review the methodology via the published reference.
  • Right to Be Informed of AI UseThis system operates on bacterial genome data, not on personally identifiable information. No individual patients are profiled or notified. The NYC AI Use Case Register provides public disclosure that this tool is in operational use by the Department of Health and Mental Hygiene.

Risks and safeguards

No risks or safeguards have been published for this system yet.