StrokeIQ

AI-powered stroke risk intelligence, from risk factors to early insight.

A machine-learning prototype that estimates stroke risk from clinical, demographic, behavioral, and socioeconomic variables. Score an individual, simulate lifestyle changes, and explore risk across a population, right in your browser.

Launch the App Request a Pilot

Prototype only. Not clinically validated and not for medical diagnosis. Results are for research and demonstration purposes.

Try It Now

Run StrokeIQ in your browser

If the app has been idle, the first load can take up to a minute while it wakes up.

Loading live prototype…

Inside the App

Four tools, one screening workflow

Each tool sits in the app's sidebar. Start with an individual score, then see what would change it, where risk concentrates, and where to set the screening cut-off.

  1. 01

    Risk Assessment Calculator

    An interactive clinical calculator that returns an instant stroke risk score from an individual's risk profile.

  2. 02

    What-If Scenario Simulator

    Simulates how changing modifiable factors such as blood pressure, smoking and activity would reduce an individual's risk score.

  3. 03

    Population Analytics

    Real-time interactive exploration of risk patterns across a population of 1,000,000 records.

  4. 04

    Model Performance & Thresholds

    Visual tools for choosing a screening cut-off that fits your programme's goals.

Why It Matters

Stroke risk is often recognised too late

Stroke is a leading cause of death and long-term disability, yet many of its drivers, such as hypertension, diabetes, smoking and inactivity, are modifiable. Because risk signals are scattered across clinical, lifestyle, and socioeconomic data, high-risk individuals are frequently identified only after a first event.

  • Risk factors spread across clinical, behavioral, and socioeconomic records
  • Few tools that show patients how lifestyle changes would lower their risk
  • Little population-level visibility into where stroke risk concentrates
  • Screening cut-offs chosen without a clear view of the trade-offs
How the Model Works

Transparent by design

  1. 1

    Interpretable model

    Each risk factor's contribution stays visible, so clinicians can see why a score is high.

  2. 2

    Adjustable screening thresholds

    The screening cut-off can be adjusted to fit each programme's goals rather than fixed in advance.

  3. 3

    Validation & safety checks

    Built-in validation views and clear disclaimers. Results support research and demonstration, not diagnosis.

Prototype Collaboration

Bring StrokeIQ to your health programme

Discuss a tailored demonstration or a focused proof-of-concept on your own population data.

Request a StrokeIQ Pilot All Frimps IQ Engines