AI-Assisted Duplicate Health Record Matching

What it is for

Inform

ChoiceMaker supports data management by identifying duplicate immunization and lead records in public health registries, enabling accurate deduplication and record merging for individuals tracked by DOHMH.

NYC Automated Decision Systems — ChoiceMaker (CM)

Run by: Department of Health and Mental Hygiene (DOHMH)
Where: No fixed location
Kept: Retained not specified in the register
Shared with: Accountable organization, Vendor
Your copy: You cannot see the data it holds about you. What you can do

What it is for

Inform

ChoiceMaker is a record-matching tool used daily by the NYC Department of Health and Mental Hygiene to find duplicate immunization and lead-exposure records belonging to the same person. It compares demographic and health event data, then assigns a probability score to each candidate record pair so staff can merge duplicates. The system operates under human supervision — staff review and act on the matches it surfaces.

What it collects and what happens to it

Data taken in

Sensitive personal information

Identifiable data

Demographic data including names, date of birth, address, and identifiers drawn from the Citywide Immunization Registry and LeadQuest registry.

NYC Automated Decision Systems — ChoiceMaker (CM)

Sensitive personal information

Identifiable data

Health event data including date and type of immunization event and lead exposure records from the Citywide Immunization Registry and LeadQuest registry.

NYC Automated Decision Systems — ChoiceMaker (CM)

Processing

Classification & Prediction

ChoiceMaker uses probabilistic record-linkage techniques trained on DOHMH staff decisions to classify pairs of records as likely matches or non-matches, outputting a probability score for each pair.

NYC Automated Decision Systems — ChoiceMaker (CM)

What it does

Deciding (Analytical AI)

Human decides

ChoiceMaker computes a match probability score for each candidate record pair. Human staff review these scores and decide whether to merge records — the system is advisory, with supervised deduplication workflows.

NYC Automated Decision Systems — ChoiceMaker (CM)

Outputs

A recommendation or prediction

Anonymized data

The program outputs a series of record pairs and a match probability for each pair, used in ongoing manual and automated deduplication processes. The output advises staff on likely duplicates but does not itself merge records.

NYC Automated Decision Systems — ChoiceMaker (CM)

Run by

Department of Health and Mental Hygiene (DOHMH)

The Department of Health and Mental Hygiene deploys ChoiceMaker through its Bureau of Investigations and Healthy Homes units to deduplicate immunization and lead records in the Citywide Immunization Registry and LeadQuest registry.

NYC Automated Decision Systems — ChoiceMaker (CM)

Built by

HLN Consulting

HLN Consulting is the professional services vendor that maintains the DOHMH implementation of ChoiceMaker, which has been customized using DOHMH training data. ChoiceMaker itself is available as an open-source program.

NYC Automated Decision Systems — ChoiceMaker (CM)

Kept for

Retained not specified in the register

The register does not specify a retention period for the match outputs or probability scores produced by ChoiceMaker. The underlying immunization and lead registry records are maintained by DOHMH under applicable public health record retention rules.
Duration: not specified in the register

NYC Automated Decision Systems — ChoiceMaker (CM)

Shared with

Available to the accountable organization

Match outputs and probability scores are available to DOHMH's Bureau of Investigations and Healthy Homes units for use in deduplication workflows.

NYC Automated Decision Systems — ChoiceMaker (CM)

Not available to me

Individual members of the public cannot access the record pairs or match probability scores produced by ChoiceMaker. The system is an internal data management tool used by DOHMH staff.

NYC Automated Decision Systems — ChoiceMaker (CM)

Available to vendor

HLN Consulting maintains the DOHMH implementation of ChoiceMaker and is likely to have access to the system configuration and training data, though the register does not explicitly specify the extent of their access to operational output data.

NYC Automated Decision Systems — ChoiceMaker (CM)

Stored

Stored locally

The system operates on DOHMH registries (Citywide Immunization Registry and LeadQuest) which are expected to be stored locally within NYC jurisdiction. The register does not explicitly describe the storage infrastructure for ChoiceMaker outputs.
Duration: not specified in the register

NYC Automated Decision Systems — ChoiceMaker (CM)

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 UseIndividuals whose records appear in the Citywide Immunization Registry or LeadQuest may not be directly informed that their records are being processed by an automated matching tool. The register does not describe a public notification mechanism specific to ChoiceMaker's operation.
Right to a Human ReviewAll record pair outputs produced by ChoiceMaker are subject to manual review by DOHMH staff before any record merging takes place. The autonomy level is described as supervised, meaning human staff make the final deduplication decisions.

Risks and safeguards

Reputational harmIncorrect record matches could incorrectly merge health records belonging to different individuals, leading to erroneous health histories and potential misidentification.Safeguard: the system operates under human supervision — DOHMH staff review all match outputs before records are merged, and the training data incorporates expert staff judgement to improve match accuracy.