Clinical Datasets & Insights
Curated, AI-enriched clinical and real-world datasets that deliver deeper insights into patients, diseases and outcomes.




AI-Enriched Datasets. Clinically Unlocked.
OM1 integrates and links structured and unstructured real-world data—including EMR, clinical notes, claims, labs, patient-reported outcomes, and social determinants—into continuously updated, research-ready real-world datasets. Each dataset is curated by experts, enriched with AI, and built to answer critical questions about patient journeys, disease progression, and treatment outcomes.
patients
years median follow-up
linked to claims
providers represented
Deep, TA-Specific Data That Focus on Real-World Outcomes
OM1 processes longitudinal clinical data from networks of specialists and primary care. These data are further enriched for key outcomes from the unstructured clinical notes, labs, and biomarkers and linked to OM1’s extensive, multi-source real-world data. Disease-area (across immunology, neuroscience, cardiometabolic, respiratory, rare disease, etc.) and custom clinical data sets are available through multiple user-friendly and cost-effective models.
Examples from dozens of enriched datasets include Alzheimer’s Disease, Depression, Heart Failure, Hidradenitis, IBD, Lupus, Psoriasis, and Rheumatoid Arthritis.
Access these ready-to-use datasets or define a custom cohort tailored to your evidence goals.

AI-Driven Enrichment & Endpoint Amplification
Fill the Gaps in Real-World Data with AI-Estimated Endpoints
Traditional RWD often lacks key clinical measures captured only in trials. OM1’s validated AI models extract concepts, estimate outcomes and identify subtypes from structured and unstructured data to dramatically expand endpoint availability and improve data completeness.
OM1 is a leader in extracting concepts from clinical text with LLMs and NLP. OM1 extractions are state-of-the-art, validated and have been successfully used in regulatory submissions. OM1 regularly extracts thousands of variables.
OM1 pioneered the estimation of clinical and patient reported outcomes from clinical notes. These validated metrics fill in missing data and are available across disease areas including depression (ePHQ-9), rheumatoid arthritis (eCDAI), lupus (eSLEDAI), hidradenitis suppurativa (eHurley), heart failure (eNYHA), ankylosing spondylitis (eBASDAI), and more. Nine validation papers and counting have been published.
Interactive Dashboards and Reports
Visualize patient populations, treatment patterns, and outcomes through OM1’s analytic standard and custom dashboards.

Train AI with Confidence
OM1 delivers AI-ready, normalized real-world data that meet key requirements for model training and validation. Our HIPAA-compliant, de-identified datasets offer large-scale, diverse, and representative populations to enable faster development, and trustworthy results.

Evidence in Action
Life Sciences Case Studies from OM1
Case Study
Large-scale comparative study for cancer screening for label expansion
>600k patients submitted for new label indication
Case Study
AI Automation enables largest registry at remarkably lower costs
>1M patients enrolled and followed over 5 years using an agentic-first approach
Case Study
Powering long-term evidence generation in rare dermatologic disease
A 3 year prospective study with 30+ Centers of Excellence
Let’s Talk About Your Goals
From research and evidence to predictive insights and beyond.

