Vigila · Stress-test

Find the rare adverse event before a patient does

Vigila oversamples the subgroups where safety signals hide, by genotype, comorbidity, age or ancestry, and maps where predicted risk rises with exposure.

Example safety mapExample

SZ-0412 · hepatic adverse events

Patients simulated
250,000
Overall grade 3+ rate
0.4% (0.3–0.5%)
At-risk cluster
CYP2C9 poor metaboliser + CKD
Cluster rate
3.1% (2.2–4.2%)
Exposure threshold
AUC above 2,100 ng·h/mL
Flagged for safety reviewAdverse event
Example. Values are illustrative.

Capabilities

What Vigila does

Rare subgroups

Oversampled at scale

Simulate hundreds of thousands of patients so a one-in-a-thousand event has enough cases to study.

Clusters

At-risk combinations

Find genotype, comorbidity and exposure combinations where predicted risk concentrates.

Thresholds

Exposure and dose limits

Map predicted risk against exposure to support dose caps and monitoring.

Constraints

Safety into design

Send safety limits to Protova so unsafe designs are ruled out early.

Monitoring

Continuous pharmacovigilance

Re-run as real-world outcomes arrive. Planned for marketed products.

Evidence

Signals on the record

Each signal and its later outcome is logged in Evidra.

How it works

Inside Vigila

  1. Amplify

    Oversample rare subgroups in Cohorta.

  2. Simulate

    Run exposure and safety models in Insilon.

  3. Cluster

    Find where predicted risk concentrates.

  4. Report

    Write a signal map for safety review.

Specification

Specification

Items marked planned are in design with pilot partners.

ItemDetail
Scale (target)105 to 107 patient scenarios per study
OutputsAdverse-event distributions, at-risk clusters, exposure thresholds
StatisticsCalibrated tail-risk models with intervals
Label supportWarning and monitoring suggestions (planned)
Causal attributionMechanism attribution of signals (planned)
StatusIn development

Questions

About Vigila

Is a predicted signal a real signal?

No. It is a hypothesis to investigate. Vigila helps decide where to look and what to monitor; clinical data decides.

Which adverse events can it model?

Events with a mechanistic or exposure link in the models, starting with hepatic, renal and cardiac events in selected areas.

Does it replace pharmacovigilance systems?

No. It adds simulation to your existing safety process and systems.

See Vigila in a briefing

We walk your team through Vigila on a public example, then discuss where a pilot could test it against outcomes you already know.