AI-assisted ECG analysis · Hospitals, clinics and diagnostics centres
Every ECG measured.
The urgent one read first.
Each recording is graded, measured and interpreted as it arrives, and the worklist puts the traces that need a clinician at the top. Your team reads, decides and signs — it does not count squares by hand, and it does not wait to find out where a report has got to.
Every request is reviewed by a person. Approved requests get a link to set up your organisation and your first analyses.
- Measured before anyone opens the study
- Worklist ordered by severity
- Reviewed and signed by a named clinician
The product
This is the software, not a description of it.
ECG work queue
1 469 studies · page 1 of 37- Critical findingFixture Patient 04MRN-…4417 · Emergency Department2026-02-01 09:05Ventricular tachycardia · 178 bpmCritical — immediate attention
- Critical findingFixture Patient 11MRN-…1180 · Coronary Care Unit2026-02-01 08:58ST-segment elevation, anterior leads · 121 bpmCritical — immediate attention
- UrgentFixture Patient 07MRN-…9032 · Cardiology Outpatients2026-02-01 08:12Prolonged QTc interval · 44 bpmUrgent review recommended
- Not assessedFixture Patient 19MRN-…2264 · Pre-operative Assessment2026-02-01 09:06Interpretation withheld — quality below the validated thresholdInterpretation withheld
- RoutineFixture Patient 02MRN-…6673 · General Medicine2026-02-01 08:40No significant abnormality detected · 68 bpmNo significant abnormality detected
Sorted by urgency, then by signal quality, then oldest acquisition first. Studies awaiting analysis are shown first, because nothing has been assessed for them.
Automated interpretation
VOMEDIQ Deterministic ECG Analysis vomediq-analysis-1.6.1 · rules 1.0.0Potentially critical finding — immediate clinical attention required
Overall confidence 0.58 · 5 findings reported; the most significant is listed first.
Rhythm
Ventricular tachycardia
Rhythm confidence
0.62
Processing time
142 ms
Reporting model
none
Measurements
| Measure | Value | Reference | Confidence | Derived from |
|---|---|---|---|---|
| Heart rate | 178 bpm | 60–100 | 1.00 | II |
| PR interval | not measurable | 120–200 | — | II |
| QRS duration | 144 ms | 80–120 | 0.94 | II, V1 |
| QT interval | 312 ms | 350–440 | 0.81 | II |
| QTc (Bazett) | 412 ms | 350–450 | 0.81 | II |
| QRS axis | leftward | −30° to +90° | 0.88 | I, II, III |
| R-wave progression | poor | progression by V4 | 0.86 | V1–V6 |
A measurement the recording does not support is reported as not measurable rather than estimated. Nothing on this screen is produced by a language model: the reporting model is recorded as none, and the narrative layer, where a deployment enables it, is given validated findings as its only input.
Every waveform shown anywhere on this site is produced by the system's own synthetic ECG generator, from the profiles the demonstration deployment serves. The full tour covers seven screens, including the alert worklist and the audit chain.
What it changes
Six things a department notices in the first week.
The measuring is already done
The dangerous trace is at the top
Repeats are caught at the machine
A reading you can hand to anyone
Nothing critical waits to be noticed
It fits the department you already have
Ordered by risk, not by arrival
The list knows which trace matters.
- Severity decides the order. Findings are graded against clinical rules with an explicit confidence floor, and the escalated traces sit at the top with their acknowledgement state.
- Escalation thresholds are yours. The point at which a finding interrupts somebody is a decision your service makes and owns, not a number buried in the engine — and changing it is a recorded act.
- A finding with no name against it is visible. The worklist shows what has been acknowledged, reviewed and signed rather than leaving it to be asked around.
- Critical
ST elevation, inferior leads — evidence: leads II, III, aVF at 2 mm or more
Acknowledged · Dr A. Osei · 09:21
- Urgent
QTc prolonged against the configured escalation threshold
Awaiting review · escalation target 30 min
- Normal
Sinus rhythm, intervals within reference limits
Reviewed · Nurse K. Adeyemi · 09:26
The same day, rearranged
What moves, and what does not.
Interval and axis measurement done by hand, for every trace, again and again.
Measurement computed from the samples, once per recording, with the engine version recorded against it.
A stack read in the order it was acquired, with the risk sorted out in the reader’s head.
A worklist ordered by severity, with escalation targets and acknowledgement state on the row.
A poor recording discovered when somebody finally comes to read it.
Quality graded at acquisition, so the trace is repeated while the patient is still there.
A conclusion in a report and no way to reconstruct the reasoning months later.
Every finding stored with its supporting measurement and the rule that produced it.
“Has anyone looked at this?” answered by asking around.
Acknowledged, reviewed and signed are states on the study, with a name and a timestamp against each.
How it works
From recording to signed report, in four steps.
The recording arrives
From your own ECG machines by REST or CSV upload, with its sampling rate, lead set, calibration and duration stored alongside the samples.
Quality is settled first
Per-lead integrity, baseline stability, interference and duration are graded immediately. A trace that cannot be interpreted reliably says so while the patient is still there.
The measurement is done
Intervals, axis, amplitudes and the findings the rule set supports are computed from the samples, each with the evidence behind it and the engine version that produced it.
A clinician decides
Findings are graded, escalated against your thresholds, reviewed, overridden where the clinician disagrees, and signed — and the report goes where your records live.
Behind those four steps is a ten-stage pipeline, described stage by stage with the guard each one applies.
Who it is for
One system, eight kinds of working day.
More ECGs read, by the same team.
For the people accountable for the ECG service: its turnaround, its staffing and its budget.
What changes here CardiologistsSpend your hour on the ECGs that need you.
For the clinician who owns the interpretation, and who wants to spend the hour on the traces that need a cardiologist.
What changes here RadiologistsECG reporting that fits between the other lists.
For the reporting clinician who reads ECGs alongside everything else on the list.
What changes here DoctorsAn answer attached to the trace, at the point of care.
For the physician who ordered the ECG and needs the answer at the point of care, not the next morning.
What changes here NursesYou will know when something needs a person.
For the team at the bedside, who need to know whether the trace has been looked at and whether anyone needs to be called.
What changes here ECG TechniciansRecord it once, properly, with the judgement written down.
For the people who record the trace, who would rather repeat it now than be asked tomorrow.
What changes here Pathology & diagnosticsAn ECG report before the patient leaves the building.
For pathologists and diagnostics centres running ECGs alongside laboratory work.
What changes here Audit & qualityInterrogate the record without being able to alter it.
For internal audit, quality and assurance, who have to measure the service without being able to change it.
What changes hereGetting access
Access is granted by a person, not by a form.
Request access
Name, work address, organisation and how you would use it. Nothing is created: no workspace, no account, no password.
A person reviews it
Every request is read before anything is issued. This is a clinical system, so it does not hand out workspaces to whoever fills in a form.
Set up your workspace
Approval issues a single-use link. Through it you name your organisation, choose your own password, and become its administrator — with the first analyses included.
What we will not do
Four commitments, each stated as a claim.
The engine decides. The model describes.
No finding in this system originates from a language model.
Measurements, findings and severity are produced by a versioned deterministic rule engine reading the stored samples. A language model is used only to turn validated findings into readable prose — it is never asked what the ECG shows, and a statement it produces that is not traceable to a validated finding is a defect.
Quality is a gate, not a footnote.
An uninterpretable recording produces no interpretation, not a cautious one.
Automated interpretation is published only when the recording passes quality validation. Where it does not, the result is the explicit statement that interpretation was withheld — which is a different thing from a normal ECG, and is presented as such.
A person is in the loop, by permission rather than by habit.
Review, override and sign-off are separately permissioned acts, and disagreement is recorded.
A signature is bound by digest to the exact interpretation it covers and to the person who gave it. An override is stored as an override for ever: the automated finding, the clinician’s finding and the reason, all attributable.
Nothing is asserted without the evidence for it.
Every claim on this site about a capability maps to something the software does.
The limits stated on these pages are not modesty. Automatic renewal, email delivery, invoices and refunds are genuinely absent, and the product reports them as absent in its own health probe rather than leaving them to be discovered.
Pricing
Pay for published interpretations. Nothing else.
Free trial
2 analysed studies
2 analysed studies at no cost, with no payment details and no expiry.
- No card details, and no stored payment method anywhere.
- No expiry. The included allowance is there when you come back to it.
- Your own workspace: its users, recordings, thresholds and audit trail.
Clinic
₹2,999.00
200 analysed studies for 30 days. One payment, not a recurring mandate.
- 200 analysed studies, valid for 30 days.
- Bought as a single payment. It does not renew, and it cannot surprise you.
- Review, override, sign, export and transmit are never metered.
Questions
Asked first, answered plainly.
Where does the time actually come back?
Three places, and none of them is a number we invented. Measurement is computed rather than performed by hand, so the repetitive arithmetic is gone from every single reading. Work is ordered by severity rather than by arrival, so the traces that need attention are the ones a reader opens first. And the state of a study — pooled, acknowledged, reviewed, signed — is visible on the study rather than in somebody’s memory, which is what removes the chasing. We publish no minutes-saved figure because this build has not been evaluated in a service, and a performance claim about a clinical system is the last place to invent anything.
What exactly does the AI do, and what does it not do?
The deterministic engine does the measuring: intervals, axis, amplitudes and the findings its rule set supports, computed from the stored samples under a stated algorithm version. A language model is used afterwards, and only to describe findings the engine has already established, in prose a person can read quickly. It is never asked what an ECG shows. If you see a number in a report, it came from the engine, and the interpretation records which version of it.
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.
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.