Flatiron Health AI
Flatiron Health (Roche) / flatiron.com
AI-powered oncology data and software platform that curates real-world evidence from cancer patient records to accelerate clinical research, drug development, and quality improvement in cancer care.
Pricing
Free
Free plan
No
Category
Developer Tools
Platforms
2
Free plan
No
API access
No
Open source
No
Platforms
2
Advertisement
What is Flatiron Health AI?
Flatiron Health is an oncology-focused health technology company (subsidiary of Roche) that curates real-world evidence from electronic health records of cancer patients to support pharmaceutical research, regulatory submissions, and cancer centre quality improvement.
The core asset is Flatiron's longitudinal oncology database — structured data from cancer patient records at over 280 cancer clinics representing more than 9 million US cancer patients, curated by abstractors and AI to extract structured clinical data from unstructured notes, pathology reports, and treatment records.
Natural language processing extracts structured clinical data — tumour characteristics, treatment regimens, response assessments, adverse events — from free-text clinical notes where data critical for research is buried in narrative form. This curation transforms unusable unstructured clinical notes into structured datasets for research.
Real-world evidence (RWE) generated from Flatiron's curated data supports regulatory submissions to FDA for drug approvals, health technology assessments, and post-market surveillance studies — with FDA having accepted Flatiron real-world evidence in multiple regulatory submissions.
For cancer centres, Flatiron's OncoEMR electronic health record system captures structured oncology data at the point of care, feeding the network database and enabling quality improvement analytics for participating centres.
Acquired by Roche in 2018, Flatiron's oncology data has become a critical asset for Roche's pharmaceutical pipeline and for independent pharmaceutical companies conducting oncology research.
How Flatiron Health AI works
Flatiron Health AI runs as document analysis llm software built around text and document workflows. Users typically start with a prompt, upload, or connected data source, and the underlying model handles the heavy lifting before returning a result you can refine or export. It's available on web and api.
What makes it worth shortlisting
The capabilities that matter most for teams evaluating Flatiron Health AI.
Oncology RWE database
Structured real-world evidence from 9 million+ US cancer patients curated from EHR records at 280+ cancer clinics, one of the largest regulatory-grade oncology datasets.
NLP clinical note curation
Extracts structured clinical data (tumour characteristics, treatments, outcomes) from unstructured clinical notes making this data accessible for research at scale.
FDA-accepted evidence
Multiple regulatory submissions have used Flatiron real-world evidence, establishing the data quality standards and methodology accepted by FDA for drug development purposes.
Best use cases
Who should use it
Pros
- 9 million+ patient oncology database is one of the most comprehensive real-world oncology datasets available for pharmaceutical research
- FDA-accepted real-world evidence from multiple regulatory submissions provides unmatched regulatory validation
- NLP curation of clinical notes extracts structured data inaccessible through structured EHR data alone
- Roche ownership provides stability and pharmaceutical partnership pipeline
Cons
- Roche ownership creates potential conflict of interest concerns for pharmaceutical competitors as data partners
- Real-world evidence database access requires partnership agreements limiting accessibility
- Clinical note NLP accuracy requires ongoing validation — structured EHR data remains more reliable for some variables
Advertisement
Is it worth the price?
Enterprise licensing to pharmaceutical companies and cancer centres. No public pricing. Subsidiary of Roche.
Model
Enterprise
Starting price
Free
Free trial
No
Tools like Flatiron Health AI
IQVIA Oncology provides competing real-world oncology data. Foundation Medicine (also Roche) provides genomic data complementary to Flatiron's clinical data. Tempus AI (covered, rank 275) provides competing oncology AI with genomics. ConcertAI provides oncology RWE.
Flatiron Health AI vs Hugging Face
A side-by-side look at the closest alternative in this category.
Flatiron Health AI
Flatiron Health (Roche)
Hugging Face
Hugging Face
Enterprise licensing to pharmaceutical companies and cancer centres. No public pricing. Subsidiary of Roche.
Free for most models and Spaces. Pro $9/month for private models, priority inference, and ZeroGPU. Enterprise Hub from $20/user/month for team collaboration and security.
HIPAA compliant with BAA. SOC 2 Type II. GDPR compliant for EU deployments. IRB approval for research datasets. FDA-accepted data quality standards.
Enterprise Hub includes SSO, access controls, audit logs, and private infrastructure. SOC 2 compliant.
Patient health data processed under strict HIPAA BAA and applicable research ethics frameworks. De-identification and IRB protocols govern research dataset access.
Public models and datasets are openly accessible. Enterprise Hub provides private model storage with data handling agreements. Review individual model licences before commercial deployment.
- 9 million+ patient oncology database is one of the most comprehensive real-world oncology datasets available for pharmaceutical research
- FDA-accepted real-world evidence from multiple regulatory submissions provides unmatched regulatory validation
- NLP curation of clinical notes extracts structured data inaccessible through structured EHR data alone
- Roche ownership provides stability and pharmaceutical partnership pipeline
- De facto standard hub for open source AI models with 500,000+ available
- Transformers library provides consistent API for diverse model families
- Spaces enable easy demo deployment without web infrastructure
- Free for public models and strong community support
- Roche ownership creates potential conflict of interest concerns for pharmaceutical competitors as data partners
- Real-world evidence database access requires partnership agreements limiting accessibility
- Clinical note NLP accuracy requires ongoing validation — structured EHR data remains more reliable for some variables
- Technical platform primarily for developers and researchers
- Inference API quality varies for very large or complex models
- Navigation complexity increases with scale of the platform
Technical & deployment info
Key facts about model providers, platforms, and team support.
Model Provider
Flatiron Health
Platforms
Web, API
Deployment
Enterprise, SaaS
Integrations
EHR systems, Clinical data systems, Regulatory submission tools, API
Team Collaboration
No
Launch Year
2021
Security & privacy
Compliance signals and data-handling notes as reported by the vendor.
HIPAA compliant with BAA. SOC 2 Type II. GDPR compliant for EU deployments. IRB approval for research datasets. FDA-accepted data quality standards.
Patient health data processed under strict HIPAA BAA and applicable research ethics frameworks. De-identification and IRB protocols govern research dataset access.
What users are saying
Verified reviews from signed-in users, stored in the backend and averaged into this tool's rating.
Sign in to rate Flatiron Health AI and leave a review.
No other reviews yet — be the first to share how this tool performs in practice.
Common questions about Flatiron Health AI
Editorial Verdict
Should you use Flatiron Health AI?
Flatiron Health is the leading oncology real-world evidence platform for pharmaceutical companies conducting oncology drug development, offering the most FDA-validated US cancer patient real-world database.
Last verified July 24, 2026.