Record intelligence

See what the record isn't telling you.

Patients slip through the gaps between events. Vivantal reads the whole record and surfaces what no single chart shows — open loops, contradictions, and silent declines, before they become harm.

12M
US adults affected by diagnostic error each year
$0
to run — no model, no server
4
analysis lenses, one record
RECORD · P-2847 READING
Jan 2023Creatinine 1.1 mg/dLacknowledged
Apr 2023Creatinine 1.4 mg/dL ↑not acked
Jun 2023Lisinopril startedactive
Sep 2023Potassium 6.4 mmol/Lcritical
Nov 2023Cardiology referralopen 8mo
Jan 2024Creatinine 1.8 mg/dL ↑↑not acked
3 open loops detected
Lisinopril continued despite critical potassium · referral never closed · renal function declining across three visits
The problem

A chart shows what happened. It can't show what didn't.

The most dangerous thing in a record is often the thing that's missing — the follow-up that never came. No standard view flags an absence. Vivantal does.

Open loops

The gap between an event and its follow-up is where patients get hurt.

An abnormal potassium nobody acknowledged. A suspicious mammogram with no biopsy. A referral placed and forgotten. Each looks fine alone. Together, they're a pattern of preventable harm.

Diagnostic errors contribute to an estimated 10% of patient deaths.
Inequity

The same gap isn't distributed evenly across patients.

Equal findings, unequal action. Follow-up happens less often for some patients than others — by race, insurance, or language — and it usually goes entirely unmeasured.

Hospitals are increasingly required to audit care equity, with almost no free tooling to do it.
One record, four readings

Four lenses on the same patient.

Every lens reads the same longitudinal record and surfaces a different category of risk.

01

Open-loop detection

Walks the timeline and finds follow-ups that were never closed — unacknowledged abnormal results, incomplete referrals, imaging recommendations that went nowhere, and medications started without their required monitoring.

Example finding
"Potassium critical (6.4) resulted 817 days ago — never acknowledged."
02

Equity audit

Measures how often an actionable finding actually gets closed for each patient subgroup — race, insurance, language, sex, age — and uses a significance test to separate a real disparity from noise.

Example finding
"Medicaid patients close 51% of findings vs 74% for the reference group — p < 0.001."
03

Reconciliation

Reads each record for internal contradictions fragmented care produces — dangerous drug interactions, a medication continued against a contraindicating lab, duplicated work-ups.

Example finding
"ACE inhibitor active through a critical-high potassium result."
04

Deterioration

Trends each repeatedly-measured value over time and flags patients whose trajectory is sliding toward a dangerous bound — the slow decline invisible in any single result.

Example finding
"Creatinine drifting upward across three visits — renal function declining."
0 AI
Deterministic — every finding traces to a named rule
$0
No model, no inference, no server cost
None
Data sent to us — everything runs in your browser
4
Lenses on one shared patient record

Load a cohort. Look for yourself.

80 synthetic patients, realistic gaps, every lens live. No install, no account.

Use cases

Who it's for, and what they'd do with it.

Vivantal speaks to two teams that rarely share a tool — patient safety and health equity — because both questions live in the same record.

Quality & safety

Catch the follow-ups that slipped

Run a unit's or panel's records through Vivantal to find every open loop, ranked by severity and how long it's been open — so the riskiest patients surface first for outreach.

Example finding
"Potassium critical (6.4) resulted 817 days ago — never acknowledged."
Health equity

Measure whether follow-up is fair

Audit closure rates across race, insurance, language, sex, and age. See, with a significance test, whether a subgroup's findings are acted on less often than the best-served group's.

Example finding
"Medicaid patients close 49% of findings vs 90% for the reference group — p = 0.0008."
Care managers

Build a worklist, or study the pattern

Use the ranked roster as an actionable outreach list, or use the cohort-level statistics to study where and for whom care processes break down — all from de-identified data, in the browser.

Example use
"Pull the 23 patients with unaddressed critical results into this week's safety huddle."
A worked example

One patient, one record, the gaps made visible.

Take a real-looking record: years of visits, labs, imaging, and referrals. Most of it is fine. Vivantal pulls out only the loops left open — and links each to the exact event so a clinician can confirm it in seconds.

What it flags in a single record

unacknowledged_resultA high calcium of 12.9 was resulted and never acknowledged — possible hypercalcemia left unworked.
imaging_followup_openA mammogram read "BIRADS 4 — biopsy recommended." No biopsy is on file.
missing_med_monitoringAmiodarone was started; it requires TSH monitoring, and no TSH has been drawn since.
referral_incompleteA cardiology referral was placed 596 days ago and is still open — the patient may never have been seen.
How it works

Deterministic. Auditable. Yours to verify.

No model, no black box. Every finding comes from a named rule or an explicit statistic you can check by hand.

Step 01

Load a record

Use the synthetic demo cohort, build a patient by hand, or load your own already-de-identified records. Everything stays in your browser.

Step 02

Read the timeline

Vivantal assembles each patient's events into one longitudinal record — labs, imaging, referrals, medications, vitals.

Step 03

Run the lenses

Four deterministic engines scan the record for open loops, contradictions, subgroup disparities, and deterioration trends.

Step 04

Confirm & act

Each finding links to the exact event behind it, so a clinician can verify it in seconds and export a worklist.

The open-loop rules

unacknowledged_resultAn abnormal or critical lab result with no documented acknowledgement in the record.
imaging_followup_openAn imaging study whose report recommends follow-up that never occurred.
referral_incompleteA referral placed but never completed, ranked by how long it's been open.
missing_med_monitoringA medication started without the lab monitoring it requires (e.g. warfarin without INR).

The equity method

closure rateFor each subgroup, the share of actionable findings that actually got closed.
two-proportion z-testCompares each group to the best-performing one; surfaces gaps unlikely to be chance.
four-fifths ruleFlags any group closing at under 80% of the reference rate — a standard disparity threshold.
min-N guardCohorts too small for a reliable signal are reported honestly as "not enough data," never as false headlines.
Live demo. Running on 80 synthetic patients with realistic gaps and disparities built in. Not convinced it's not cherry-picked? Hit Generate random cohort for a brand-new random set — the engine finds the gaps every time. Everything is computed in your browser; load your own de-identified records anytime.

What is this cohort’s record not telling you?

Open loops surfaced from each record — abnormal results never acknowledged, referrals never completed, medications started without their required monitoring. Sorted so the patients most likely to have fallen through the cracks rise to the top.

No cohort loaded
No cohort loaded yet
Load the demo cohort, or upload your own de-identified records, to begin.

Does follow-up depend on who the patient is?

Equal findings should get equal action. This audit measures, for each subgroup, how often an actionable finding gets closed — then compares each group to the best-performing one. A gap that survives a significance test is a disparity worth investigating, not noise.

Load a cohort first
Switch to the Cohort tab and load data; the equity audit runs on the same records.

Where does this record contradict itself?

Fragmented care produces conflicts no single clinician sees: interacting medications, a drug continued against a lab that contraindicates it, duplicated work-ups. This lens reads each record and surfaces those contradictions for a pharmacist or clinician to resolve.

Who is sliding, one normal-looking result at a time?

A value that moves from normal toward danger across several visits is invisible in any single result. This lens trends each repeated measurement and flags the patients whose trajectory is heading the wrong way — before it becomes a crisis.

Research & quality-improvement tool — not a diagnostic device. Vivantal analyzes record completeness and follow-up patterns and surfaces process gaps for human review. It does not diagnose, and every finding is a transparent, rule-based flag a clinician should verify. Demo data is fully synthetic; no real patient information is used. Disparity figures are illustrative of the method, not claims about any real population.
Build a patient

Turn a few clinical facts into an analyzable record.

Add events one at a time — a lab, a referral, an imaging study, a medication. Each becomes a row. When the record is built, analyze it directly or export it to load into the cohort tools.

🔒 No identifying information. This builder never asks for names, dates of birth, or medical record numbers. Each record gets a de-identified code, and you only enter demographic categories and clinical events. Everything stays in your browser — nothing is sent anywhere.

Add an event

Pick a type, fill the fields, add it to the record.

Patient (categories only)
When the event occurred.
Leave blank if no monitoring is required.
Working recordRL-0001
No events yet
Add a lab, referral, imaging study, or medication from the left to start building this record.
Trust & safety

Vivantal never compromises patient privacy.

Protecting patient data isn't a policy we promise — it's an architecture we can't violate. Here's exactly how, in plain terms, and the rules we hold ourselves to.

The one rule we never break

Protected health information is never compromised. Vivantal does not receive, store, or transmit identifiable patient data — ever. There is no server in our analysis pipeline to send data to. Everything runs in your browser, on your machine. You can't leak what you never receive, and we never receive it.

How privacy is guaranteed

Protection by architecture, not by promise.

No server, no transmission

The entire engine is JavaScript running inside your browser tab. Records you load are processed locally and never sent anywhere. Disconnect from the internet entirely and Vivantal still works.

De-identified data only

Vivantal is designed for data that's already de-identified. A separate, open converter — which runs on your machine, never ours — removes the 18 HIPAA Safe Harbor identifiers before any record reaches the app.

No tracking, no telemetry

No analytics, no trackers, no third-party scripts, and nothing stored about you or your data between sessions. Close the tab and nothing persists.

Fully auditable

Because Vivantal is deterministic and open, anyone can verify these claims: open your browser's network tab and watch zero data leave the page. Nothing hidden in a model or a server you can't inspect.

The rules we hold ourselves to

We only support use on data the user is already authorized to access, under their own approval such as an IRB protocol. Vivantal grants no access to data — it only analyzes what a user may already handle.
De-identification happens on the authorized user's machine, before any record reaches Vivantal — never on our side, because we have no side that touches data.
We treat an automated tool as an aid, not a certification. The converter produces a candidate de-identified file plus a review report, and states clearly that the user and their IRB must confirm it meets the legal standard.
×
We never ingest identified patient data into anything our team controls. No "upload your chart and we'll clean it" — that would mean PHI touching our systems, and we will not build it.
×
We never claim more than is true. Vivantal surfaces process gaps for human review. It does not diagnose, and we say so everywhere.

How real data is handled — and why it stays safe

01
Authorized access
A clinician with lawful access to their own data, under their IRB approval.
02
Local de-identification
They run the open converter on their machine; identifiers are stripped before anything leaves.
03
IRB review
They and their IRB confirm the de-identification meets the legal standard.
04
Local analysis
The clean file is loaded into Vivantal — which also runs locally.
At no point does identifiable patient data reach the Vivantal team. We contribute software; the authorized user keeps custody of their data the entire time. That's what makes the privacy commitment true by construction, not just asserted.
Research & quality-improvement tool — not a diagnostic device. Vivantal analyzes record completeness and follow-up patterns and surfaces process gaps for human review. It does not diagnose. Use on real patient data requires the user's own lawful access, de-identification on their machine, and institutional review.
Team

Built by two people who think medicine's blind spots are an engineering problem.

Vivantal started from a simple conviction: the most preventable harm in healthcare hides in the gaps between events, and you can make those gaps visible without a black box.

NM
Neeraj Movva
Lead
Leads Vivantal — the clinical reasoning model, the open-loop ruleset, and product direction. Background in computational medicine and clinical machine-learning research.
AR
Aditya Raut
Co-Lead
Co-leads Vivantal — engineering, the equity-audit methodology, and data architecture. Focused on making the analysis rigorous, reproducible, and genuinely deployable.
Where this is headed

From prototype to pilot.

Vivantal today is a working, validated prototype on synthetic data. The path forward is real: validating the open-loop rules with clinicians, testing the method on de-identified institutional data under review, and adding lenses onto the same spine. The goal is a tool quality and equity teams reach for, then trust.

Your workspace

Account

Signed in. Your settings and audit history live on this device.

Care-gap thresholds

Tune the engine to how your practice works. Changes apply immediately to the next analysis. These are preferences, not patient data — nothing here is PHI.

Referral open limitFlag a referral as high-severity after it's been open this many days.
days
Monitoring gap limitFlag a medication's missing monitoring lab as high-severity after this many days.
days
Critical escalationA value past its reference bound by more than this fraction of the normal range escalates to critical.
× range
Minimum subgroup sizeAn equity subgroup needs at least this many actionable findings before a disparity is reported.
findings

Per-lab cutoffs Custom

Override the high/low bound for a specific test — for example, flag HbA1c high at 7.0 instead of the lab's default.

Clear this device

Wipe your account, settings, and audit history from this browser. Use this on a shared or public computer when you're done. This can't be undone — you'll need your recovery phrase to get back in elsewhere.

Audit trail

A timestamped record of every audit you've run — counts only, never patient data. This is the evidence a clinic shows its insurer or regulator to prove gaps are being actively monitored.

No audits logged yet
Open the demo, load or generate a cohort, and your audit will be recorded here automatically.

Team workspace

Invite your staff so everyone processes records against the same clinical thresholds. Membership and shared settings are non-PHI; patient data still never leaves each person's own machine.

Seats on this plan: 5. In a hosted deployment, invites email a sign-up link; here they're added directly for demonstration.

Generate a compliance report

Produce a branded, timestamped PDF summarizing your audit activity — the document a clinic hands to HHS or its malpractice insurer. Built entirely in your browser from metadata only.

No patient data appears in the report — counts and dates only.
Vivantal never compromises patient privacy.
Runs in your browser · no data ever leaves your machine

Sign in

Your clinical thresholds and audit history, on every device you use.

New here?

Create your account

Free to start. Your patient data never touches our servers — only your settings sync.

Already have an account?

Save your recovery phrase

These 12 words are the only way to reset your password. Write them down and keep them safe — we can't recover them for you.

Reset your password

Enter your email and the 12-word recovery phrase you saved at sign-up.