Get your health data ready for research and AI, without it leaving your control.

FIELDLABELED

member_dob●●/●●/19●●

WHAT IT ISDate of birth PHI · quasi-identifier

RULESHIPAASTATE LAW

MAY BE USEDRESEARCH: YESMODEL TRAINING: NO

STATUSMasked · Expert Determination mode

Researchers and AI developers are asking for clinical data faster than privacy teams can review it by hand.

Labels are machine-readable, so your query layer and pipelines can enforce them.

The problem

The most valuable part of the record is the hardest to use safely.

Clinical notes, case notes, faxed letters and scanned documents hold the detail that decides a study, a data license or a coverage decision, and the identifiers with it. So organizations either lock that data away and lose its value, or release it and carry risk nobody has measured.

{{ p.who }} {{ p.stat }}–{{ p.stat2 }}

{{ p.text }} ({{ p.credit }}).

Using that data safely starts with knowing exactly what is in it.

See the engine →

Markets

One engine. Four markets.

Each market loses something different when its notes and documents go unused. One engine finds what they hold and keeps it governed in your environment.

{{ p.eyebrow }}

{{ p.title }}

{{ p.body }}

{{ p.link }} →

Use cases

What teams do once they know what their data holds.

Discovery comes first. These are the outcomes the Tidegate engine supports from there, each one running in a cloud account you control, so identifiers and record-level data stay in your environment.

01

Safe AI on clinical data

Find and handle PHI, PII and payment card data before clinical notes, documents or transcripts reach LLMs, copilots or retrieval systems, so teams can adopt AI without exposing sensitive data.

FORAI, data and security teams at health systems, health plans and digital health companies

See it on a real clinical note →

Builds on: Discovery and Protection Request an evaluation →

02

AI-ready data for model development

Prepare clinical and claims data for training, fine-tuning and evaluating internal or partner models. Synthetic data for development and testing, released only after memorization tests, with a synthetic data report.

FORData science and ML teams, and life sciences R&D groups building or evaluating models

Builds on: Protection and synthetic data Request an evaluation →

03

Data commercialization and research

Prepare EHR data and clinical notes for AI developers and research partners. The Tidegate engine transforms them in your environment, deployed with Tidegate Forward Deployed Engineers under a BAA whenever they access PHI, and an independent, qualified expert you engage reviews the release.

FORHealth systems, health plans and data holders with the rights to license: labs, pharmacy and PBM data, clearinghouses, specialty networks, digital health, health data networks

Data commercialization and research Request an evaluation →

04

Sensitive data discovery and governance

Inventory and classify sensitive attributes across structured and unstructured data, grounded in Tidegate’s data attribute ontology, for compliance, audit and risk reduction.

FORPrivacy, compliance and data governance teams, including state Medicaid agencies and other public payers

Builds on: Ontology and Discovery Request an evaluation →

05

Linkage and interoperability readiness

The next step once data is clean and classified: connect each person’s records within your data, with match quality reported, and export them to OMOP, CSV or Parquet with their labels attached. From v1.1: FHIR with Provenance.

FORTeams joining claims, EHR, lab and note data, or preparing it for exchange with partners

Builds on: Entity linking and Interoperability Request an evaluation →

Fits your stack

Works inside the systems you already use.

Data networks, eligibility systems and data platforms run the engine where the records already are.

{{ s.title }} {{ s.ref }} {{ s.where }} · ILLUSTRATIVE

{{ s.railLabel }}

{{ r.label }} {{ r.flag }}

{{ s.docHead }}

{{ sg.t }}

{{ lg.t }}

VERDICTS

{{ v.label }} {{ v.chip }}

{{ s.toast }}

All formats →

Run a network, token service, eligibility system or data platform? Build Tidegate into it.

Become a partner →

Evaluation

Start with an evaluation

We run the Tidegate engine on a sample you choose, scoped in writing, in a cloud account you control, for a fixed period agreed in writing.

Evaluations are booking now for spring 2027.