AI-Assisted Immunization Evaluation and Vaccine Forecasting

What it is for

Healthcare

ICE evaluates a patient's immunization history and generates recommendations on whether the patient has completed a vaccine series or is due for additional vaccines, supporting clinical immunization decision-making for childhood, adolescent, and adult populations.

NYC ADS Register — ICE

Run by: Department of Health and Mental Hygiene (DOHMH)
Where: No fixed location
Kept: Retained Not specified; data is held in the Citywide Immunization Registry per its own retention policy
Shared with: Accountable organization

What it is for

Healthcare

The Immunization Calculation Engine (ICE) reviews a patient's vaccination history and recommends which vaccines they still need, based on official public health guidelines. It is used daily by the NYC Bureau of Immunization and draws on records from the Citywide Immunization Registry. The system's recommendations are monitored by health professionals before any action is taken.

What it collects and what happens to it

Data taken in

Sensitive personal information

Identifiable data

ICE uses patient demographic data, specifically date of birth, drawn from the Citywide Immunization Registry. This data is identifiable at intake as it is linked to individual patient records.

NYC ADS Register — ICE

About behaviour

Identifiable data

ICE ingests vaccination records — immunization date, vaccine group, and vaccine type — stored in the Citywide Immunization Registry. These records describe prior clinical actions taken on behalf of a specific patient.

NYC ADS Register — ICE

Processing

Classification & Prediction

ICE applies rule-based forecasting logic derived from the Advisory Committee on Immunization Practices schedule to classify a patient's immunization status (complete or due) and predict upcoming vaccine needs. Updated annually with new vaccine recommendations.

NYC ADS Register — ICE

What it does

Deciding (Analytical AI)

Human decides

ICE forecasts vaccine due dates and evaluates series completion by applying the Advisory Committee on Immunization Practices schedule rules to patient demographic and vaccination history data. The system's autonomy is described as 'Monitored' — health professionals review recommendations before action is taken.

NYC ADS Register — ICE

Outputs

A recommendation or prediction

Identifiable data

ICE returns a recommendation per patient on whether a vaccine series has been completed or whether vaccines are due. These are advisory outputs reviewed by Bureau of Immunization health professionals — they are not automatically acted upon.

NYC ADS Register — ICE

Run by

Department of Health and Mental Hygiene (DOHMH)

The Bureau of Immunization within the NYC Department of Health and Mental Hygiene deploys and operates ICE to evaluate patient immunization histories and generate vaccine recommendations based on national guidelines.

NYC ADS Register — ICE

Built by

HLN Consulting

HLN Consulting is the professional services vendor that developed ICE and continues to be involved in program enhancements. It maintains the DOHMH implementation of the open-source system.

NYC ADS Register — ICE

Kept for

Retained Not specified; data is held in the Citywide Immunization Registry per its own retention policy

Patient vaccination and demographic data used by ICE are stored in the Citywide Immunization Registry. The register entry does not specify an output-data retention period; retention is governed by the Registry's own policies.
Duration: Not specified; data is held in the Citywide Immunization Registry per its own retention policy

NYC ADS Register — ICE

Shared with

Available to the accountable organization

Output recommendations and patient immunization evaluation data are available to the NYC Bureau of Immunization staff who use the system operationally. Input data is drawn from and stored in the Citywide Immunization Registry.

NYC ADS Register — ICE

Stored

Stored locally

Input data (demographic and vaccination records) are stored in the NYC Citywide Immunization Registry, a local government data system within the jurisdiction where the data is collected.
Duration: Not specified; governed by the Citywide Immunization Registry policy

NYC ADS Register — ICE

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 TransparencyICE is a free and open-source system. Its immunization schedule logic, based on the Advisory Committee on Immunization Practices recommendations, is publicly documented. Members of the public can review the system's rules and methodology at the project's public wiki (https://cdsframework.atlassian.net/wiki/spaces/ICE/overview).
Right to a Human ReviewICE operates under a 'Monitored' autonomy model, meaning health professionals from the Bureau of Immunization review its output before any immunization recommendation is acted upon. Patients whose care involves ICE outputs will have those recommendations reviewed by a qualified clinician.

Risks and safeguards

Reputational harmAn incorrect evaluation of a patient's immunization history could cause a patient to be incorrectly flagged as under-vaccinated or over-vaccinated, potentially affecting their care or public health reporting.Safeguard: The 'Monitored' autonomy model requires health professional review before recommendations are acted upon. Vaccine schedule rules are updated annually (most recently CY2025) to reflect current ACIP guidance. ICE is open-source, enabling external review of its logic.