Heart & Cardiovascular Research Intelligence
Cardiovascular studies usually combine routine measurements — blood pressure, heart rate, ejection fraction, laboratory values — with medication and event history. That makes eligibility highly structured, and a good demonstration of how protocol text becomes checkable criteria.
Screening support only. ClinQSphereX provides research and recruitment workflow support. It does not independently determine clinical eligibility, diagnosis, treatment or enrolment. Candidates are shown as potentially eligible and require researcher review.
Conditions in scope
- Coronary artery disease
- Heart failure
- Atrial fibrillation
- Hypertension
- Cardiomyopathy
Research variables
Synthetic data- Age
- Systolic / diastolic blood pressure
- Heart rate
- BMI
- Ejection fraction (where recorded)
- Relevant laboratory values
- Cardiovascular history
- Medication history
Variables are only used when they exist in the underlying dataset. Demonstration records are synthetic and are not real patient data.
Why screening is hard here
Structured measurements make criteria checkable, but records are often incomplete.
Clinical trial discovery
Live dataRecords are retrieved from the public ClinicalTrials.gov registry when you search. Nothing on this panel is a determination about any individual.
Structured eligibility screening
Synthetic dataProtocol text becomes one row per criterion. Each row records the expected value and the observed value, and resolves to PASS, FAIL or UNKNOWN. Missing information stays UNKNOWN — it is never converted into a pass.
| Criterion | Expected | Illustrative outcome |
|---|---|---|
| Age | 18–85 years | PASS |
| Documented heart failure diagnosis | Present | FAIL |
| Ejection fraction | ≤ 40% | UNKNOWN |
| Systolic blood pressure | ≥ 90 mmHg | PASS |
| Recent acute coronary event | Absent in last 90 days | FAIL |
Illustrative synthetic research profile. Outcomes shown here demonstrate the display format only; live outcomes are computed inside the workspace from your own data.
The decision stays with a researcher
- 01
Model prediction
Ranked shortlist with a confidence level.
- 02
Evidence
Observed value, source and timestamp per criterion.
- 03
Explanation
Feature contributions behind the prediction.
- 04
Researcher review
Pending review · Requires more evidence · Not relevant · Potentially relevant.
- 05
Research action
Outreach, screening visit or exclusion — recorded with the reviewer.
Limitations for this area
- Structured measurements make criteria checkable, but records are often incomplete.
- Demonstration records are synthetic; no real patient data is used on this site.
- Registry records are shown as published by ClinicalTrials.gov and are not verified against any individual.
- Model output is a prediction, not a diagnosis, and never changes a participant's status on its own.