Before you evaluate it
What this software is not, and what it refuses to do.
The limits
In the same size type as the features.
It is not a medical device and it is not approved for diagnostic use.
This build is a clinical-systems demonstration. It has not been validated against a clinical dataset, it holds no regulatory clearance anywhere, and its output must not be used to make a diagnosis or to decide treatment.
It does not diagnose, and it does not replace clinical assessment.
It analyses a recording, states what the signal supports, and hands that to a qualified person to review. The conclusion is the clinician’s, and the record shows which clinician.
No accuracy figure is published, because none has been established.
You will not find a sensitivity, specificity or agreement percentage on this site. Any figure of that kind for this build would be invented, and a performance claim about a clinical system is the last place to invent anything.
Evaluation figures shown in the product are illustrative and synthetic.
The demonstration data is generated from a cardiac dipole model by the system’s own synthetic ECG generator, and every screen that can show it labels it as such. It is not a patient record and it says so wherever it appears.
Some capabilities are genuinely absent.
Purchased periods do not renew automatically, and invoices and refunds are not generated. Nothing about a patient is ever emailed, texted or paged: no alert about a finding leaves the system. The single exception is an operational notice about the equipment itself — that a machine is failing or has stopped sending — which can be emailed or texted where the deployment has a transport configured, and which the software reports as unsent rather than sent where it does not. Each of these is reported as not configured or not implemented by the product itself.
Built to refuse
The guards are the safety argument.
A poor recording is not interpreted
A finding without evidence is a defect
A signature is bound to what it covers
Nothing clinical is fetched from outside
Who sees what inside your organisation
- Each organisation is one workspace with its own users, recordings, devices, thresholds and audit trail. Scoping is applied where queries are built, so a query that would reach another organisation’s data is one the application cannot express.
- Administrative authority and clinical authority are separate. A hospital administrator configures the service and cannot sign an interpretation; a cardiologist signs one and cannot rewrite the audit trail.
- Access, review, override, signature and every administrative act are written to an append-only, hash-chained trail enforced by database triggers rather than by the application behaving well.
- The platform operator administers organisations and holds no permission to open a patient record, so a support session is not a disclosure waiting to happen.
Where the AI sits, exactly
The deployment declares an AI posture — no external AI at all, minimised data, approved external AI, or an on-premise model — and it is enforced where a payload would be assembled: identifiers are refused when the policy forbids them. The health probe reports which posture is active rather than which one was intended.
- The engine that produces numbers is deterministic, versioned and in-process. It is not a language model.
- Where narrative reporting is enabled, the language model receives validated findings and nothing else. It is never asked what the ECG shows.
- Where it is not enabled, the structured findings are the report, and the deployment says so rather than leaving you to find out.
Answered without hedging
The four questions a clinical buyer asks first.
What happens when the recording is poor quality?
The interpretation is withheld. You get the explicit statement that the recording was inadequate for automated interpretation, which tells you to repeat the acquisition or read it manually. You do not get a low-confidence measurement to mentally discount — that failure mode is exactly what the quality gate exists to prevent.
Can a clinician disagree with the automated reading?
Yes, and disagreements are recorded rather than overwritten. Review, override and sign-off are three separate acts with three separate permissions. An override preserves the automated finding alongside the clinician’s, with the reason and the author, and it stays in the record.
Is it a medical device?
No. It is decision support for a trained clinician. This build has not been validated against a clinical dataset, it holds no regulatory clearance anywhere, and no diagnostic accuracy figure exists for it. It must not be used to diagnose a patient or to decide their treatment, and the software says so on its own screens rather than only on this page.
Does it renew, invoice or email us?
A paid period is a single purchase for a fixed term and does not renew by itself, and invoices and refunds are not generated. No receipt or reminder is ever sent, and nothing about a patient is emailed, texted or paged to anybody — no alert about a finding leaves the system by any channel. There is one exception, and it concerns equipment rather than people: where this deployment has a mail relay or an SMS gateway configured, it can send an operational notice that an ECG machine has failed, is misconfigured, or has stopped sending, because that fault produces no symptom on any worklist and someone has to be told. On a host with no transport configured, that notice goes to the deployment’s own log, and the software reports it as delivered to nobody rather than leaving you to discover it.
Per role
Each audience page states what that role cannot do.
Regulatory position
What this is not
This is a demonstration-grade clinical system. It is not a medical device, it holds no regulatory clearance anywhere, and it has not been validated against a clinical dataset.
It does not diagnose and it does not replace clinical assessment. Every interpretation is decision support for a qualified professional, who reviews, overrides and signs it — and the record shows which professional.
No sensitivity, specificity, agreement or accuracy figure appears on this site, because none has been established for this build. Any such figure would be invented. Read the full position.
See it on your own recordings.
Send a request, and a person reviews it. If it is approved you get a link that creates your own organisation, with the first 2 analysed studies included and no card details — and you are its administrator from the moment you set your password.