For labs · clinics · telehealth
Test results online, with the reading beside them.
Vitrubo is the layer a lab, clinic or telehealth service adds to the results it already produces. Each lab test result is read against its range and the patient's history, a comment is drafted beside every flagged value for the professional to sign, and the patient opens the report online under your brand, with a link they can hand to their doctor.
- HIPAA compliant
- GDPR compliant
- Encrypted in transit and at rest
- HL7 · FHIR R4
Test results online should carry more than the number.
LOINC codes
Every lab test result is mapped to one reference standard, whichever laboratory produced it. A value from one lab sits on the same line as the same test from another.
One summary
Flagged results are grouped into needs attention, worth watching, back to normal and always normal, so the report reads as a few stories rather than a long table.
Native record
One FHIR R4 record per person, every result coded and dated, the source document kept. HIPAA business associate agreement for US deployments, GDPR Article 28 terms as standard. Results online, encrypted in transit and at rest.
Records, on premises
Roughly 100,000 anonymised hospital records read inside a clinical program. The results never left the hospital's perimeter.
Who delivers test results online with Vitrubo?
The lab or clinic runs the test. Vitrubo reads the result and delivers it. In every case the professional signs; the software drafts.
Lab test results online, with a comment beside each flag.
The drafted comment is written in the style the lab already uses and approved at the release step. The patient opens the result online under the lab's brand, and the right follow-up test is raised while the sample is still fresh.
The whole history behind one result.
Every test result, letter and discharge summary is read into one record before the consultation. Patients see their results online in plain language; the clinician sees the same analysis with its reasoning.
Results inside your product.
Embed the reading, bundle it or resell it under your brand. Each new lab test regenerates the report, which gives users a reason to return with every result.
What a test result online should show.
A lab test arrives as numbers, units and reference ranges. Deterministic code computes the flags; no model writes a number. Each result is then read with the others: which markers move together, what the medication list changes, what a borderline value means beside two more.
Results from different labs are normalised to one standard, so the history of a marker reads as one line rather than a folder of PDFs. A value drifting for years, normal in every single test, becomes visible.
The patient view says what stands out, why it is grouped that way and what to discuss with a doctor. The clinician view of the same lab test result carries the full reasoning, connected conditions and medications, and tests to consider.
Each report opens from a link the patient can hand to a doctor or a family member. Previous versions stay as history, so the reading given with each result can still be seen later.
A test result is not read once and forgotten. The report regenerates with every new lab test, and the earlier results become the baseline the new one is read against.
White-label PDFs and a role-based portal for staff and patients, or JSON through the API into the portal you already run. HL7 and FHIR R4 in, FHIR and JSON out.
What a person should see when they open a result.
Emily Carter's live report: a 34-year-old, five visits over nine months, no condition on file. Every value sits against its range, the flagged results are gathered into a few connected stories, each statement carries the guidance it rests on, and the page ends with what to discuss with a doctor. This is what test results online look like when the reading arrives with the number.
Delivers results through the systems you already run.
Full integration.
Results flow in from the LIS as HL7 or FHIR, the drafted reading flows back into the same system for release, and the patient's copy goes out through the portal or channel the lab already uses.
PlatformWhite label, no integration.
A portal for the laboratory, the clinician and the patient under your brand. Lab test results online without an engineering project.
API first.
Teams with their own portal take the API alone: structured results and the reading as JSON. Recognition, normalisation and interpretation, together or one at a time.
Interface and API, for every customer.
Results mapped to LOINC, units made comparable, the record kept in FHIR R4. Containers on your infrastructure, your keys.
Why not paste the result into a chatbot?
Because a test result is read against a history, not on its own.
A general-purpose model
- Not built or validated for laboratory results; it writes fluently about a number it may have misread.
- Reads one PDF at a time; last year's lab test from a different lab is not in the picture.
- Units and reference ranges differ from lab to lab, and a general model leaves them that way.
- Nothing behind a statement; no source a clinician can open and check.
- Identity goes into the prompt together with the values.
A test result read by Vitrubo
- Numbers, units, ranges and flags computed by deterministic code; the models never write a number.
- Every lab test result normalised to LOINC and UCUM, so results from any lab land on one scale and trends read across years.
- Several models review the same case; disagreements are resolved before a draft is shown.
- Every statement links named guidance: EHA, WHO, NICE, KDIGO, BSH. A chip opens the publication.
- Identity never enters the prompt; the models see values and an internal ID.
Every statement rests on named medical guidance. The chip opens the same guideline page a clinician would read.
From first call to production, on your own test results.
An evaluation runs on the results your lab or clinic already produces. Six steps, none of them a commitment until the last.
Talk to the team
A short call about your panels, the format your results come in, and where the reading should appear: LIS, portal or both.
Sandbox and API docs
Test access for your team, with the API contract and sample payloads.
Run your own lab tests
Send real result formats, anonymised. Blood, urine and allergy panels, PDF or HL7.
Validate the output
Your scientist or clinician reads the drafted comments against their own reading of the same results.
No commitment at this stage
Comment style, reference ranges and branding are configured here. Nothing is signed.
Production when ready
Inside your perimeter or a private cloud, connected to the LIS or EHR, or portal-first.
Questions about test results online.
No. Vitrubo does not perform or sell laboratory tests. The lab, clinic or telehealth provider produces the result; Vitrubo is the reading layer added to it, so the result reaches the patient online with an interpretation beside it. A person who already holds a lab test result can use the same layer to understand it.
Every value against its reference range, in plain language. Flagged results are gathered into a few connected stories in four zones: needs attention, worth watching, back to normal and always normal. Each statement carries the medical guidance it rests on, and the report ends with what to discuss with a doctor. The live reports show the format.
Every test result is mapped to LOINC, with units converted to UCUM, so a marker from one lab sits on the same line as the same marker from another. Trends then read across labs and across years, which is where a slow drift shows up.
Numbers, units, ranges and flags are computed by deterministic code. Several AI models cross-check the interpretation, and every statement links named guidance: EHA, WHO, NICE, KDIGO, BSH, with up to 30 sources behind one biomarker view. A clinician or lab scientist reviews and signs before the result is released.
No. Vitrubo does not diagnose, select treatment or replace a clinician or lab scientist. It drafts a reading of the test result, organises the history and names tests to consider. The decision and the signature stay with the professional. For a patient, the report is context to bring to an appointment, not medical advice.
Through white-label PDFs and a role-based portal carrying the lab's logo, headers and disclaimers, or through JSON into the portal the lab already runs. The drafted comment appears in the release step for approval; after sign-off the patient receives the result through the lab's usual channel, with a link to the full report.
Yes. Each report opens from a link that can be shared with a doctor or a family member. The clinician who opens it can switch to the clinical view of the same analysis, with the full reasoning, connected conditions and medications, and tests to consider.
The report regenerates. The new lab test is read against every earlier result on file, values that have returned to normal move into their own zone, and the previous version stays as history. The record is kept for the next result, not rebuilt from scratch.
PDF, photos and scans of a lab report, HL7, FHIR R4 and JSON through the API. Blood, urine and allergy panels arrive as values; hospital records, prescriptions and notes are read as context for the interpretation.
Inside your perimeter: containers on your infrastructure or a private cloud. You own the keys; Vitrubo ships versioned builds and has no access to the data. Identity never enters the prompt. A HIPAA business associate agreement for US deployments and a GDPR Article 28 processing agreement with Standard Contractual Clauses.
Yes. Embed the reading, bundle it with a consultation or resell it under your brand. Results arrive through the API and the report comes back as JSON or as a branded PDF; every new result regenerates it, so users return with each test.
With a call, then sandbox access and API documentation. Your team sends its own anonymised lab test results, your scientist or clinician validates the drafts against their own reading, and nothing is committed until production, when you are ready.
Demo cases
Invented people, real product. Every case is a synthetic record with a stock portrait: no real patient, no real result. The reports are live.
Robert Hensley
58A year of CKD follow-up with full context supplied.
Emily Carter
34Five visits over nine months with no diagnosis supplied.
Ryan Hayes
30Fifteen months of lifestyle change. The direction of travel is read.
See it on your own test results.
A walkthrough on the result formats your lab or clinic already produces, sandbox access for your team, and a drafted report online on your own panels.