LEWES, Del., Jan. 21, 2026 (GLOBE NEWSWIRE) — John Snow Labs, a healthcare AI company, today announced that its Patient Journey Intelligence (PJI) platform is the first secondary-use data platform designed specifically to meet the requirements of the U.S. Food and Drug Administration’s (FDA) newly finalized guidance on the use of real-world evidence (RWE) to support regulatory decision-making for medical devices.
The December 2025 final FDA guidance represents a shift in how real-world data must be generated, analyzed, and governed for regulatory use. It requires that clinical facts be sufficiently complete and accurate, meaning that structured EHR data alone is no longer sufficient, recognizing the necessity of unstructured clinical narratives, multimodal data, and longitudinal patient experiences. Second, it requires rigorous documentation of data provenance, quality, and reliability.
“Regulatory-grade real-world evidence must go beyond the ‘what’ — what data was used, what decisions were made — to also include the ‘how,’ meaning full provenance and governance of how it was generated,” said David Talby, CEO, John Snow Labs. “The Patient Journey Intelligence Platform makes the ‘how’ transparent by design, built to make every clinical fact traceable, reproducible, and auditable — exactly what the FDA now requires.”
A Secondary Use Data Platform
The PJI platform is purpose-built for the secondary use of healthcare data, transforming raw, fragmented clinical information into longitudinal patient journeys that span the full life of the patient. Rather than relying on static snapshots or administrative summaries, PJI continuously integrates multimodal data over time, including structured EHR fields, clinician notes, pathology and imaging reports, labs, imaging, and claims data.
Using specialized medical large language models (LLMs) and vision-language models (VLMs), the platform extracts clinically meaningful facts from unstructured sources that are routinely missed, delayed, or distorted in structured-only datasets. This approach directly aligns with the FDA’s guidance, which acknowledges that much of the clinically relevant information needed exists only in unstructured formats.
Most organizations today waste multiple years of data engineering effort on separate projects: Fast Healthcare Interoperability Resources (FHIR) to Observational Medical Outcomes Partnership (OMOP) conversion, de-identification, NLP/LLM pipelines, medical terminology normalization, cohort builders, and patient registries. PJI unifies these efforts, saving time and money, enabling organizations to focus on value-add projects like building AI agents or advancing novel research.
A Stronger Emphasis on Governance
The new FDA guidance places equal emphasis on data relevance and data reliability, requiring organizations to demonstrate clear data lineage, integrity, and auditability. Since inception, John Snow Labs has embedded governance directly into the core architecture of PJI. Not as a response to these guidelines, but as a foundation of the technology. Every derived clinical fact produced by PJI includes:
- End-to-end data lineage, tracing each data point back to its original source document and exact location
- Full model and transformation lineage, including versioned models, prompts, and rules used during extraction
- Human-in-the-loop validation workflows for high-stakes clinical endpoints
- Deterministic reproducibility, includes confidence levels and provenance
- Airgap privacy & data residency, with no external calls to LLM APIs since the platform includes John Snow Labs’ healthcare-specific LLM and SLM models
- Versioning and audit trails, for all data, metadata, and models
This ensures organizations meet FDA expectations for a complete data audit trail, turning regulatory scrutiny into a repeatable, defensible process. Additionally, PJI is deployed entirely within an organization’s own infrastructure, ensuring sensitive clinical data never leaves the organization’s security perimeter.
By automating de-identification, harmonizing with the OMOP Common Data Model, and AI-ready dataset generation, PJI dramatically reduces the time and operational burden required to produce regulatory-grade RWE without compromising privacy, compliance, or control.
Regulatory-grade evidence must reflect the true patient experience across care settings over time, supported by transparent, reproducible, and well-governed processes. John Snow Labs’ PJI platform establishes a new standard for RWE, enabling healthcare organizations to generate evidence that regulators, clinicians, and patients can trust.
To learn more about John Snow Labs’ PJI platform, join us for an upcoming webinar, “From Raw Data to OMOP Gold: Architecting the Secondary Use Data Platform for Clinical AI Agents,” taking place at 2pm ET on Wednesday, January 28, or visit johnsnowlabs.com.
About John Snow Labs
John Snow Labs, the AI for healthcare company, provides state-of-the-art software, models, and data to help healthcare and life science organizations put AI to good use. Developer of Medical LLMs, Healthcare NLP, Spark NLP, the Generative AI Lab, and the Patient Journeys Platform, John Snow Labs’ award-winning medical AI software powers the world’s leading academic medical centers, pharmaceuticals, and health technology companies. Creator and host of the Applied AI Summit (formerly the NLP Summit), the company is committed to further educating and advancing the global AI community.
Contact
Gina Devine
Head of Communications
John Snow Labs
gina@johnsnowlabs.com
