ECG confirmation on HeartSciences' MyoVista Insights platform ran 5x faster than before with the delivered workflow, and the final sign-off still stays with the clinician. ML LABS engineered the platform's backend, a platform that has reached clinical production in two countries and keeps expanding. The architecture and technical decisions across infrastructure, AI inference, EHR integration and security were ML LABS' to make and own.
The speed came from the platform as a whole. Every ECG arrives with an AI analysis already generated, every input format is preprocessed into one normalized reading, and clinicians review, annotate and confirm in one interactive view. Underneath, the backend runs AI inference across multiple model providers, takes part in hospital workflows over HL7 and FHIR, and meets medical-device requirements in two jurisdictions.
Confirmation Runs 5x Faster
- ECG confirmation ran 5x faster with the delivered workflow.
- Each ECG arrives with its AI analysis already generated.
- Inputs in many formats become one normalized reading.
- Clinicians review, annotate and sign in one interactive view.
MyoVista Insights runs today as HeartSciences' core product across multiple healthcare organizations in US and UK production, giving clinicians one view of ECGs, AI results, and prior studies inside their own EHR, plus natural-language search over the clinical worklist.
Every ECG Arrives Already Analyzed
A clinician no longer starts from a blank tracing. As each ECG is submitted, the platform generates its AI analysis automatically, so the findings are waiting when the study opens and the clinician's time goes to confirming them rather than producing them.
ML LABS built an async inference architecture that decouples ECG submission from AI result delivery, runs studies through multiple model providers, and absorbs provider unavailability without dropping any submitted work. Per-organization model enablement lets a new algorithm roll out to one organization before all the rest, and adding a new AI model provider is a short configuration task rather than a new engineering project.
Each inference request carries an idempotency key, so a retry after a provider timeout can never produce a second billable result for the same ECG. Every record reaches a definite terminal state that a query can name, so reconciliation is a query, not a heroic act. HeartSciences' study volumes, inference latencies, and production availability are the client's own data, and ML LABS will not publish them to make a case study look better.
Every Input Format Reads As One ECG
ECGs reach the platform from many devices and systems, and each encodes the same heartbeat its own way. Nothing in that difference raises an error. Miss it and the platform hands a cardiologist a value that is wrong and yet looks entirely right.
The preprocessing and normalization layer that ML LABS built turns every input format into one unified representation of the waveform and its clinical measurements, then checks the result against expected physiological ranges before any AI analysis is allowed to run. Duplicate submissions are recognized by waveform fingerprint, so a clinic that uploads the same study through two pathways does not pay twice or read two answers.
Every source encodes clinical data differently. Getting this wrong does not produce an error message. It produces a clinically incorrect value that looks right. The platform that handles this correctly becomes the one clinicians trust.
Clinicians Review And Annotate In One View
The review itself is interactive. Clinicians see the ECG, its AI findings and prior studies in one place, annotate what they see, and confirm or correct the interpretation without moving between systems. Easy review is what turns an AI finding into a confirmed result quickly.
Clinical reports are signed, confirmed, and locked through a lifecycle carrying legal and regulatory weight, so the report workflow enforces accountability at each stage and tracks every post-signature modification with a full audit trail. Security was remediated inside the delivery cadence rather than deferred to a hardening phase at the end.
Results Land In The Clinician's EHR
EHR integration means participating in the clinical order workflow, not merely reading patient demographics out of it. The platform receives an order message when a physician requests an ECG interpretation, processes the study through inference, and returns a result message carrying clinical measurements and the billing codes downstream hospital systems depend on for reimbursement. A malformed result message is not a logging problem; it is an unpaid claim and a clinician who never learns that the answer came back.
New Hospitals Join Without New Code
The most consequential decision on this platform was made before it had a second customer: onboarding a new organization is configuration, never code. A new organization is defined by its HL7 field mappings, its enabled AI models, its invoice pricing, and its storage provisioning, and each is a configuration surface rather than a branch in the codebase.
HeartSciences adds hospitals, device vendors, and AI model providers by configuring them, not by commissioning engineering projects, and the same codebase serves test, US production, and UK production with data residency separation built into the infrastructure.
Omar did outstanding work designing and building the backend for our cloud-native AI-ECG platform. I recommend him to any organization needing a skilled and reliable engineering partner.
— Jason Domask, Director of Software Engineering, HeartSciences
HeartSciences remains an ML LABS engineering retainer client. The retainer's work so far includes a custom billing system, a validation and verification system, a management platform for admins and an EHR simulator to facilitate hospital integrations.
Flexibility Paid For Only Where Needed
Configuration-first multi-tenancy is front-loaded, and front-loaded cost is real cost. In a domain with one device vendor, one model, one jurisdiction, and one billing scheme, it is a tax on variability that will never arrive, and the honest recommendation is to skip it. The test is not ambition, it is the count of open axes: each dimension that can plausibly gain a second value is a configuration surface you will otherwise discover as a migration.
Two Steps That Prevent A Migration
- Enumerate the open axes before the schema. List every dimension that can plausibly take a second value (device vendor, model provider, jurisdiction, billing scheme) and decide, on paper, which become configuration surfaces and which stay hard-coded.
- Write the terminal-state list before the happy path. Name every end state a record may reach, and make each one queryable. If an engineer cannot answer "where is study X and why" with one query, an operator is already paying the reconciliation burden.
Speed Comes From The Whole Platform
No single model made confirmation faster. The analysis was already there, every format read as one ECG, and the review was built for the clinician who signs. Those platform decisions cost little to design early and are expensive to retrofit. When that kind of system is what you are building, that is the build, and the person who built it keeps it running.
