Trial Enrichment Agent · NACC + OASIS-3 Validated
Reduce Costly Screen-Failures
Before Confirmatory Testing
Clinovia’s Trial Enrichment Agent stratifies your candidate pool by progression and biomarker risk — using models validated on independent cohorts — before you spend on PET or CSF confirmation.
For Research Use Only. Not a diagnostic device.
The CRO Problem
Expensive confirmation happens too early
Patient burden
Site burden
Lost recruitment time
Unnecessary cost
What if risk stratification happened upstream?
Clinovia Trial Enrichment Agent
Move risk stratification upstream
Give the agent your protocol and candidate cohort. It applies the validated models that match your available data, ranks candidates by likely biomarker and progression status, and hands off a prioritized shortlist — before you spend on confirmatory testing.
Connects to your existing workflow — CSV, API, CTMS, or EDC.
CSF / Amyloid Prescreening
The first layer of enrichment
Predicts amyloid/tau (AT) status from age, sex, and MMSE alone — before any invasive or imaging-based confirmation.
Inputs
Age · Sex · MMSE
Predicted AT(N) Status
No PET.
No MRI.
No lumbar puncture for the initial assessment.
Sample output for illustration. For Research Use Only.
Clinovia Model Toolkit
Match the model to your protocol
The agent selects from validated models matched to whatever your protocol already collects — no new assessments required to get started.
Clinical
Age, sex, MMSE
Fastest to apply. No added assessments beyond routine intake.
Clinical + Cognitive
+ RAVLT and/or LIMM
Higher precision when cognitive testing is already in protocol.
Clinical + MRI
+ structural MRI
Highest precision for studies with imaging already scheduled.
Use the data your study already collects — the agent handles the rest.
External Validation
Frozen models. Independent cohorts.
Models are locked before validation and evaluated on independent cohorts that were not used for model development.
NACC
🔶 N =External validation cohort
🔶 0.00
AUC
🔶 0%
Sensitivity
🔶 0%
Specificity
OASIS-3
🔶 N =External validation cohort
🔶 0.00
AUC
🔶 0%
Sensitivity
🔶 0%
Specificity
Frozen models
Model parameters are locked before validation. No retraining, threshold tuning, or recalibration is performed on the validation cohort.
Independent cohorts
Validation cohorts are separate from the populations used for model development, with no overlap in the evaluated participants.
External validation
Performance is evaluated on data the model did not see during development, rather than relying solely on internal cross-validation.
Example Workflow
One protocol, one ranked cohort
The agent applies your eligibility criteria, scores every remaining candidate, and shows exactly how tightening the threshold concentrates your highest-likelihood candidates into a smaller group.
Executive Summary
Clinovia Score · A+T+ Probability
0.18
Min
0.49
Median
0.48
Mean
0.71
Max
Enrichment by Threshold
Sample output from a synthetic demo cohort. For Research Use Only.
Pilot Program