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 SARS-CoV-2 Variant Classification for Public Health

What it is for

Healthcare
  • Pangolin supports public health epidemiological surveillance by classifying SARS-CoV-2 viral variants from genomic sequences, enabling variant tracking for COVID-19 public health response.

NYC Automated Decision Systems — Pangolin (2025)

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

What it is for

Healthcare

Pangolin is a bioinformatics tool used by the NYC Department of Health and Mental Hygiene to assign lineage names to SARS-CoV-2 genomic sequences. It classifies viral samples into named variants (such as Omicron or Delta) to support epidemiological tracking and public health reporting. The system processes viral genome data — not personal health information — and its outputs are used to understand how COVID-19 variants are spreading across the city. Results inform variant surveillance decisions made by public health professionals.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • SARS-CoV-2 consensus genome sequences generated through public health sequencing workflows. No identifying information is collected or disclosed — sequences are biological measurements from viral samples, not linked to individual patient identities.

NYC Automated Decision Systems — Pangolin (2025)

Processing

Classification & Prediction
  • Pangolin uses a combination of random forest tree classification, additional classification methods, and maximum parsimony to assign Pango lineage names to SARS-CoV-2 genomic sequences, binning sequences that are more likely to be similar.

NYC Automated Decision Systems — Pangolin (2025)

Clustering & Segmentation
  • The tool bins SARS-CoV-2 sequences that are more likely to be similar into named lineage groups using a nomenclature system maintained by the Pango Network, supporting genomic epidemiology.

NYC Automated Decision Systems — Pangolin (2025)

What it does

Deciding (Analytical AI)
Human decides
  • Pangolin classifies and assigns lineage names to SARS-CoV-2 genomic sequences using random forest, classification methods, and maximum parsimony. The tool is supervised — results are reviewed by public health laboratory professionals before being used for epidemiological reporting.

NYC Automated Decision Systems — Pangolin (2025)

Outputs

About a measurement
Anonymized data
  • Viral lineage assignments indicating the genetic classification of SARS-CoV-2 sequences (e.g., BA.2, XBB.1.5), used for variant tracking and epidemiological reporting. Outputs are not linked to individual patient identifiers.

NYC Automated Decision Systems — Pangolin (2025)

Run by

Department of Health and Mental Hygiene (DOHMH)
  • The NYC Department of Health and Mental Hygiene's Public Health Laboratory deploys Pangolin to classify SARS-CoV-2 genomic sequences generated through public health sequencing workflows, supporting variant tracking and epidemiological reporting.

NYC Automated Decision Systems — Pangolin (2025)

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

Available to the accountable organization
  • Viral lineage assignment outputs are available to the NYC Department of Health and Mental Hygiene for variant surveillance and public health reporting. No identifying information is collected or disclosed.

NYC Automated Decision Systems — Pangolin (2025)

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 TransparencyPangolin is an open-source tool whose methodology — random forest classification, additional classification methods, and maximum parsimony — is publicly documented at https://github.com/cov-lineages/pangolin and in scientific literature. The Pango lineage nomenclature system used is maintained openly by the Pango Network.

Risks and safeguards

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