Rigorous research.
Robust intelligence.

Our AI empowers patients to navigate their health and enables them to contribute to research

100%

U.S. EMR Coverage

40+

Diseases in 10+ therapeutic areas

75+

Publications

How it works

We unlock meaningful insights for participants.

Enroll

Participants choose to enroll in research

They sign an informed consent form to enroll in a study, enabling them to contribute their anonymized data to research of their choice.

Streamlined research participation

  • 100K+ patient journeys mapped
  • 79 Patient Net Promoter Score (NPS)
Geographic Reach

Patients' complete medical journeys, identified

Our AI technology identifies every site where the patient has received care.

Data Collected

  • Records from 100K+ ambulatory and inpatient sites in all 50 states
  • 80+ specialties and subspecialties
Retrieve

Full retrieval across all sites of care

AI-enabled retrieval systems collect documentation from all care touchpoints regardless of care setting, data type, and file format.

Rapid data collection across sites

  • 32M+ notes retrieved to date
  • Records spanning 50+ years of care
Structure

AI-driven structuring of clinical data

Our fine-tuned medical LLM is purpose-built to structure records and identify key data elements based on your research needs.

Heterogeneously trained model

  • 350M+ clinical endpoint labels
  • Diverse patient populations
  • 3X better performance than GPT-4 for clinical named entity recognition
  • 47% better performance than leading medical LLMs when abstracting over records
Explore Analysis
Abstract

Meaningful insights based on your research needs

By synthesizing information across your patient population's records, we transform raw data into structured, actionable insights.

Stronger insights

  • 75+ publications
  • FDA submission
  • Research in 40+ diseases and 10+ therapeutic areas
Explore Publications

Faster, more efficient, and stronger insights

Fast access and retrieval

We have built direct pipelines with every major care site to conduct retrieval from anywhere in the U.S.

High-integrity insights

Our team of epidemiologists, clinicians, and biostatisticians, combined with programmatic quality controls and our industry-leading LLM, ensure that insights are accurate, complete, and aligned to your research questions.

Flexible by design

Our AI model’s mapping, structuring, and abstraction capabilities support efficient updates as research questions evolve.

Sustained patient engagement

By returning a curated health history to every patient, we enable 98% patient retention year over year.

Resources

Publication
5
 min read
LLMD: A Large Language Model for Interpreting Longitudinal Medical Records
This preprint introduces LLMD, a large language model (LLM) that uses medical records to characterize patient health over time, and isdeployed today in applications that improve health outcomes andpower clinical research. Along with general medical knowledge,LLMD is trained on labeled longitudinal medical records, givingit unique advantages over LLMs trained on knowledge alone, onunlabeled records, or on records from a single health system. Weshow that LLMD learns to make nuanced connections in information covering years of patient care documented across facilities,and that these are critical to real-world accuracy
PicnicAI
3
 min read
Building a Personal Medical AI
An overview of structuring, abstraction and all the nuance that comes with building a personalized medical AI.
Article
4
 min read
The Role of AI in Observational Research | Q&A with PicnicHealth Chief Technology Officer and Co-founder, Troy Astorino
This week PicnicHealth unveiled PicnicAI, an AI-driven platform designed to rapidly unlock universal medical records and deliver accurate insights for patients and life science companies.