For clinical trial sponsors and CROs

QIS

Your trial measures the visit.Patients leave between them.

Caregiver strain, oxygen non-adherence, social withdrawal, functional decline — the signals that precede a withdrawal are spoken aloud for weeks before anyone acts on them. QIS captures that stretch, reads it through three models at once, and flags what matters to a clinician while the participant is still enrolled.

Qualitative signal between scheduled visitsThree frontier models, disagreements keptNo record changes without a clinician

What a trial cannot see

Attrition is not a surprise. It is a signal nobody read.

A participant who withdraws has usually been telling someone for weeks — a caregiver, a family member, a nurse in passing. None of it is a scheduled endpoint, so none of it reaches the sponsor until the patient is already gone.

~30%

of trial participants drop out before the study ends

Published industry benchmark

$19,533

the benchmarked cost of replacing a single withdrawn participant

mdgroup, widely cited

$75k–$150k+

all-in cost per enrolled patient in a Phase 3 study

Published industry estimate

Figures are published industry benchmarks, cited for scale rather than as QIS results. At a 30% withdrawal rate, a 300-participant study carries roughly $1.7M in replacement cost alone, before any delay to readout. QIS has not yet been measured against live trial data — what it offers today is the mechanism, not a proven effect size.

How it works

Capture the month. Read it three ways. Flag it to a person.

Four steps, each one already running in the product.

  1. 01

    Capture what happens between visits

    Caregiver conversations, patient interviews and site notes are ingested as first-class qualitative records — not free-text fields nobody reads. Trials already measure the visits; this is the rest of the month.

  2. 02

    Read it through three models at once

    Every question runs against three frontier models under distinct analytical lenses. Where they agree is reported. Where they disagree is kept, because a split between models on a risk question is a signal, not noise to average away.

  3. 03

    Flag the signals that precede withdrawal

    Defined criteria — caregiver strain, oxygen non-adherence, social withdrawal, functional decline — route a record to a clinician instead of into a dashboard. The flag names which criterion fired and why.

  4. 04

    Nothing moves without a person

    Every finding and every suggested action arrives as a proposal. A clinician accepts, edits or dismisses it. This is the property that makes clinical AI deployable, and it is enforced in code rather than in policy.

Why this is deployable

The model can propose. It cannot act.

Every clinical AI connector shipping today is read-only, because nobody has a safe way to let a model change a patient record. QIS does not have to choose: a suggestion enters a clinician's review queue, and takes effect only when a person accepts it.

ProductSurfaceCan it change the record?
ChatGPT × EpicHealth-system EHRRead-only — states it does not write back to the patient record
athenahealth for ClaudePatient recordsRead-only
Third-party FHIR connectorsPatient recordsRestricted to read operations so the model cannot modify data
QISClinical digital twinCan propose. A clinician approves, or it never takes effect.

Each row above reflects that vendor's own published documentation as of November 2026. The difference is not that QIS trusts models more — it is that a care action has always been born as a proposal here, waiting for a clinician. Connecting an assistant changed nothing about that boundary; it only gave the proposal a new way in.

See it in practice

What a reviewer sees today, beside what QIS surfaces.

The same question, run two ways on synthetic trial data: once against the quantitative endpoints alone — the view a reviewer has now — and once across the full qualitative record. The difference between the columns is the thing a visit schedule cannot capture.

Margaret Chen · digital twin47 chunks · 3 meetings

Clinician asks

Is she trending toward diabetic complications, and what am I missing?

Retrieving twin context · three lenses running in parallel

FrameClaude

A1C 7.8% and rising albuminuria across the last two panels. Trend is the signal, not the single value.

SoulGPT

She stopped mentioning her walks in the March transcript. Adherence may be slipping before the labs show it.

SteelGemini

ADA guidance puts this profile in intensified management. Comorbid hypertension raises the CVD tier.

Convergence · 2 of 3 agree, 1 adds context

Risk is trending up on labs and on language. Intensify monitoring and probe adherence at the next visit.

Review the evidence and flagged risks before making care decisions.

What is already built

A working product, not a prototype deck.

Ingestion, meeting capture with consent gating, the review queue, the care calendar and the connector surface are all running today. This is what a pilot would actually be run on.

Who uses it day to day

The signal is only worth capturing if someone acts on it.

A sponsor buys the retention signal; a care team is who produces and acts on it. QIS is built for the people on the ward and at the kitchen table, because that is where the qualitative record actually comes from.

Make sense of your own records.

Keep your documents together and ask questions about your history. Return to your dashboard to see suggested actions and upcoming care.

Create your account
  1. 01Add a document to your Library
  2. 02Ask Chat to explain a record
  3. 03Check your upcoming care in Calendar

Learn QIS

Three walkthroughs, start to finish.

The same guided tours the product ships with, readable here before you sign in. Every step is written out; open any one to be walked through it.

4 steps
Getting Started with QIS

Learn the basics of the Qualitative Intelligence Systems

  1. 01Welcome to QISThe Qualitative Intelligence Systems is your digital companion for clinical intelligence. It helps you triangulate multiple data sources to get comprehensive patient insights.
  2. 02Chat ModeStart with Chat Mode for quick conversational queries. Ask questions about your patient in natural language and get fast, focused responses based on ingested data.
  3. 03QIS ReviewUse QIS Review for deep clinical analysis. It runs your question through three analytical lenses simultaneously to identify convergence and divergence.
  4. 04Patient PickerUse the patient selector to switch between different patients. Your chat history is maintained per patient, so you can jump between patients without losing context.
4 steps
Uploading Patient Data

Learn how to ingest documents and files into the system

  1. 01Supported File TypesQIS accepts multiple file formats: CSV for structured data, PDF and DOCX for documents, TXT and MD for notes.
  2. 02How to UploadNavigate to Library, select a patient, and drag-and-drop or click New to upload. You can also attach a file from the chat composer. Files are processed asynchronously in the background.
  3. 03Record TypesYou can categorize documents as quantitative (measurements), qualitative (notes), caregiver input, surveys, or let the system auto-detect.
  4. 04Async ProcessingFiles are chunked, embedded, and stored in the background. You'll see a processing status and can check when they're ready for analysis.
4 steps
Understanding Triangulation

Deep dive into the three analytical lenses

  1. 01Verity Frame (Structural)Analyzes the objective, factual structure of the case. Timeline, diagnoses, procedures, medications, and measurable health metrics.
  2. 02Verity Soul (Contextual)Considers the human context: patient goals, values, social factors, emotional state, and lived experience. The 'why' behind the facts.
  3. 03Verity Steel (Risk)Identifies risks, gaps, contradictions, and things that don't fit. Red flags, medication interactions, care coordination gaps.
  4. 04Reading the Convergence MapAfter a query, you'll see how the three lenses agree (convergence) or disagree (divergence). High convergence = high confidence. Divergence signals gaps to investigate.
4 steps
Recording and Transcribing Meetings

Capture and ingest meeting recordings

  1. 01Recording a MeetingUse the in-app recorder to capture patient conversations. The recording is transcribed by Fireflies.ai and stored for review.
  2. 02Recording ConsentRecording consent varies by US state. Set your state in Settings before recording. Some states require all-party consent.
  3. 03Reviewing the TranscriptAfter transcription completes, review and edit the draft transcript. The review UI lets you amend text and see an edit history.
  4. 04Approval & IngestionOnce approved, the transcript is added to the patient's digital twin, integrity-hashed, and locked. You can't edit it after approval.
4 steps
Managing Care Actions

Extract and track patient action items

  1. 01What Are Care Actions?Care actions (action items) are extracted patient-directed instructions: medications to start, follow-ups to schedule, labs to order, lifestyle changes, or monitoring tasks.
  2. 02Auto-ExtractionQIS automatically extracts care actions from ingested documents and meeting transcripts. You can also manually re-extract from specific sources.
  3. 03Action LifecycleActions flow: proposed → confirmed (by clinician) → completed. You can also decline actions or edit their details (priority, due date, etc.).
  4. 04Cross-Patient InboxThe Actions Inbox shows all pending proposed items across patients you have access to. Use it to batch-review and confirm care actions.
4 steps
Patient Registry & Profiles

Manage patient records and summaries

  1. 01Registry OverviewThe Patient Registry is your master list of all patients in the system. It shows key info and links to detailed profiles.
  2. 02Patient ProfileEach patient has a profile with their clinical summary, portrait (AI-stylized avatar), documents, and meetings. The summary is auto-generated from ingested data.
  3. 03Clinical SummaryThe AI-generated summary captures the patient's conditions, history, current status, and identified risks. It's continuously updated as new data arrives.
  4. 04Patient Portrait (Avatar)Upload a photo and QIS AI will create a stylized cartoon portrait. This personal touch makes the patient feel more connected in the digital twin.
3 steps
Digital Twin Voice

Clone and use a patient's voice in the system

  1. 01Voice CloningRecord a short voice sample from the patient (or caregiver). QIS clones it using ElevenLabs IVC to create a personal voice for the digital twin.
  2. 02Synthesizing ResponsesOnce a voice is cloned, chat responses can be converted to audio and spoken in the patient's own voice. Great for accessibility and personalization.
  3. 03Use CasesVoice synthesis is useful for bedside communication, accessibility (screen readers), and creating engaging touchpoints with patients or caregivers.
3 steps
Team Collaboration

Working with caregivers and other clinicians

  1. 01Roles and AccessQIS has four roles: Patient (self-record), Caregiver (linked to patients), Doctor (clinician), and Admin. Each role has specific permissions.
  2. 02Linking PatientsWhen registering as a caregiver or doctor, specify which patients you manage. You'll see only those patients in your list and registry.
  3. 03Sharing FeedbackAll users can submit feedback about the system: questions, bugs, feature requests, or general comments. Admins review all feedback.

FROM INFORMATION TO UNDERSTANDING

One record.
A world of clarity.

Take a guided look at a familiar care journey.
Choose a step to see what happens next.

01 / THE RECORD

A place for the whole story.

Start by choosing a patient and adding a document to the Library. QIS processes the text so you can read it, ask about it, and find suggested care actions.

You can add PDFs, Word documents, text files, spreadsheets in CSV format, or images of records. Wait until a file is ready before asking about it.

Start your own journey
Illustrative walkthrough · sample content
QIS / Collect
PATIENT LIBRARY

Follow-up visit notes.pdf

Ready to read

Your files stay connected to the selected patient.

Connected to the patient record
RecordsContextNext steps

The QIS perspective

Three lenses. One patient story.

For questions that need a closer look, QIS Review considers the clinical facts, the human context, and potential risks together.

Frame

Claude

Structural · factual

Maps clinical frameworks, timelines, diagnoses, procedures, medications, and measurable metrics. Frame is the objective backbone — what happened, when, and in what order.

Soul

GPT

Contextual · human

Reads interview transcripts, caregiver notes, and patient language for goals, values, burden, and emotional signals — the narrative behind the numbers.

Steel

Gemini

Risk · evidence

Stress-tests findings against contradictions, red flags, medication interactions, and care-coordination gaps — the early-warning lens for what does not fit.

You stay in control. Review the source evidence and flagged risks. Care actions require confirmation, and meeting transcripts are reviewed before approval.

A little guidance

Start with confidence.

The essentials, without the technical detour.

What problem does QIS solve for a trial sponsor?

Trials capture what happens at scheduled visits. Withdrawal is usually decided in between them — caregiver strain, medication or oxygen non-adherence, social withdrawal, functional decline. Those signals are spoken aloud to family and care staff for weeks before they reach a sponsor. QIS ingests that qualitative record, reads every question through three frontier models at once, and routes anything meeting defined clinical criteria to a clinician for review while the participant is still enrolled.

Has QIS been proven to reduce dropout?

No. QIS runs on synthetic and de-identified data today and has not been deployed against live trial data, so no retention effect has been measured. What exists is the mechanism and a working product: ingestion, triangulation across three models, convergence and divergence mapping, eight defined human-gate criteria, and the review and scheduling workflow. Any figures we cite about the cost of attrition are published industry benchmarks, not QIS results.

Can the AI change a patient's record?

No, and this is enforced in code rather than policy. Every finding and every care action is created in a 'proposed' state and waits for a clinician to accept, edit or dismiss it. That applies equally to a connected AI assistant: an assistant can propose a care action through our connector, and there is deliberately no tool by which it can approve one. Every clinical AI connector shipping today is read-only for this reason; the human gate is what lets QIS accept a proposal safely.

What happens when the three models disagree?

The disagreement is preserved and surfaced, not averaged away. Convergence is scored, findings reported by only one model are kept as divergent, and low convergence on a result containing risk signals is itself one of the criteria that routes a record to a human. A split between models on a risk question is treated as information about uncertainty rather than as noise.

Can we use QIS with real patient data?

Not in the demo environment. Production use with protected health information requires a signed business associate agreement and a dedicated deployment, and we will walk you through what that involves before you commit to anything. Everything you can see today runs on synthetic records.

Where should I start?

Create an account or sign in to your dashboard. If a patient record is already linked, open the Library and add a document. Otherwise, caregivers and clinicians can create a patient from Chat; patients without a linked record should contact their care team. Once a file finishes processing, you can ask questions about it in Chat.

What does QIS mean by a digital twin?

It is a connected collection of a patient’s records, approved meeting transcripts, and saved findings. QIS uses this shared context when answering questions, so you do not have to explain the history from scratch each time.

Should I use Chat or QIS Review?

Start with Chat for everyday questions and explanations based on your records. Choose QIS Review when you want a deeper comparison: three AI perspectives examine the facts, personal context, and risks, then show where they agree or differ.

What can I add to the Library?

Upload PDF, Word (DOCX), CSV, TXT, or Markdown files. Supported images and scans can also be processed when image recognition is available. Wait until the file is ready before asking about it. If processing fails, the Library shows the error so you can check the file and try again.

How do I turn a suggested action into a plan?

Open Care actions to review suggestions extracted from records or meetings, together with their source evidence. Confirm, edit, or dismiss them as appropriate. Confirmed actions can then be scheduled in Calendar.

Bring us a trial.

Tell us the indication, the phase, and where you are losing participants. We will walk you through what QIS would have surfaced, on synthetic data, and be straight with you about what it has and has not been proven to do.

Research stage

QIS runs on synthetic and de-identified data today. It has not been deployed against live trial data, and no retention outcome has been measured.

PHI requires a BAA

Protected health information needs a signed business associate agreement and a dedicated deployment. We will tell you what that involves before you ask.

Patent pending

The triangulation and human-gate architecture is the subject of US patent application 63/935,100.