Peer-reviewed science for high-validity evidence.
Verantos scientists and collaborators publish the methods, validations, and applied studies that underpin the platform, across data reliability, AI-based phenotyping, and disease-area applications in asthma, migraine, and cardiovascular medicine.
10
peer-reviewed publications and abstracts4
therapeutic areas7
journals and conferencesFDA
sponsored work (TRUST / VERIFY)Ten entries. Every figure on this site traces to one.
10 of 10 shown
INSIGHTS Asthma Pragmatic Registry — a pragmatic approach to high-validity real-world evidence for asthma
Describes the design of a retrospective, adult and adolescent asthma cohort that pairs longitudinal EHR data with rigorous data reliability standards, supporting clinical, payer, and regulatory decision-making at registry scale.
Healthcare resource utilization by severity of disease among adult patients with asthma in the United States
Characterizes HCRU across the full asthma severity spectrum, including mild-to-moderate populations under-represented in prior literature, using longitudinal real-world data.
Implementing accuracy, completeness, and traceability for data reliability
Early learnings from the FDA-funded TRUST demonstration project. Operationalizes the FDA Real-World Evidence Program's reliability dimensions of accuracy, completeness, and traceability in 120,616 patient records and contrasts traditional vs. advanced data and technologies.
Advanced approaches to generating high-validity real-world evidence in asthma
Head-to-head comparison of traditional structured-data RWE against AI-enabled extraction from unstructured EHR. Across 18 protocol-defined asthma features in 3,481 patients, F1 rose from 52.2% (traditional) to 94.7% (advanced), an 81.4% relative improvement. Supported in part by FDA Award U01FD007172.
Ways to minimize data quality headaches in migraine research
Demonstrates that AI applied to unstructured EHR data recovers migraine subtypes and symptoms, variables routinely missed by structured-data-only approaches, with the granularity and accuracy needed for credible RWE.
Machine learning approaches to predict asthma exacerbations: a narrative review
Narrative review of AI/ML methods for predicting asthma exacerbations, synthesizing the role of biomarkers, pulmonary function, comorbidities, and environmental factors, and the data infrastructure required to deploy these models in practice.
Retrospective comparison of traditional and artificial intelligence-based heart failure phenotyping in a US health system to enable real-world evidence
Compares ICD/structured-data heart failure phenotyping against an AI-based approach using unstructured EHR. Shows the accuracy gap that determines whether downstream RWE meets regulatory-grade criteria in cardiology.
Using artificial intelligence to identify patients with migraine and associated symptoms and conditions within electronic health records
Validates AI extraction of migraine cases, symptoms, and comorbidities from EHR data, addressing the well-known variability of structured fields and the limits of code-based phenotyping in migraine.
Development and validation of a novel model for characterizing migraine outcomes within real-world data
Defines and validates a 10-point migraine outcomes model, severity plus associated features, extracted from unstructured EHR with AI. Provides a reproducible framework for measuring soft outcomes that historically resist structured capture.
Real-world evidence in cardiovascular medicine: ensuring data validity in electronic health record-based studies
Foundational study establishing the gap between structured-EHR and AI-augmented unstructured-EHR accuracy for cardiovascular concepts. Structured queries fell short of regulatory-grade thresholds; AI on unstructured notes met or exceeded them across most concepts.
Ready to advance your evidence program?
Speak with our team about how the Verantos pharmacoepidemiology stack can accelerate your timeline.