IN-SILICO DEVICE VALIDATION · STEALTH

Find the failure before the first animal.

Ditto builds the computational human twin — and validates it against a physical twin it also controls. Run your device across realistic human anatomy, find where it breaks, and leave with evidence a reviewer will read.

0virtual patients per study
0verification cases, 5 solvers
0animals required to explore a design
within spec fails acceptance criterion
SCROLL
ACADEMIC, CLINICAL & RESEARCH HERITAGE
01 / THE BOTTLENECK

You spend the money first.
You learn last.

Cumulative programme spend against what you actually know. The blind zone is where device programmes die.
01

Bench phantoms

Static and acoustically unlike a person. They prove the device functions — not that it functions in a body.

02

Animal models

Expensive, slow, ethically costly, and anatomically wrong in ways that matter.

03

Human trials

Correct — and far too late to be a design tool. By then you have committed.

Crossing that gap costs years and tens of millions, and today it is crossed largely blind.

02 / THE PLATFORM

From imaging to failure envelope,
in days.

STEP 01

Anatomy

Imaging becomes a simulation-ready mesh through an automated pipeline with hard quality gates. A mesh that fails its gate stops the pipeline rather than proceeding with a caveat.

STEP 02

Physiology

A 12-lead ECG and an echo become a personalised heart. Bayesian inference returns a posterior, not a point fit — and names the parameters your data cannot determine.

STEP 03

Your device

Place it. Sweep it across a cohort. Get the failure envelope — which anatomies break it, and how much of the variance each parameter explains.

03 / A COHORT STUDY, LIVE

Two hundred patients.
Seconds, not weeks.

This runs in your browser. Every dot is a synthetic patient with its own anatomy and physiology; every evaluation places a point on the envelope. In the product these are real solver runs on real meshes — the shape of the answer is the same.

VIRTUAL COHORT · N=200 · INFRARENAL AAA
0evaluated
0breaches
—breach rate
—worst case
04 / THE MOAT

The bottleneck is not physics.
It is plumbing.

Excellent open-source physics already exists — openCARP, Chaste, SimVascular, FEniCSx, k-Wave, Pulse. None of it shares a patient-state object, enforces units across a boundary, or records whether a number was measured, inferred, or guessed from a 1994 paper on canine myocardium. Ditto builds the substrate.

core/twin — value admission

Rules a validator enforces,
not a policy document.

A value that cannot say where it came from does not enter the twin. Not by convention — by construction. The stream on the left is the actual admission logic: units, uncertainty, provenance class, and a source population for anything claiming to be literature.

  • No bare floats. A unit mismatch is a test failure.
  • No point estimate for a parameter your data cannot determine.
  • A solver that fails verification cannot be scheduled.
  • A solver refuses questions outside its declared scope.
  • Simulated is never presented as measured.

This is the argument of our peer-reviewed work on data stewardship barriers in precision-medicine digital twins.

And every number stays traceable.

Click any value to walk its provenance back to the root.

AAA-014 · CONFIDENCE LEDGER RESEARCH USE ONLY
PROVENANCE CHAIN
Select a value to trace its origin.
measured from this subject inferred by fitting published literature assumed by us — and flagged
05 / CREDIBILITY

Not a simulator.
An instrument.

A simulator’s only currency is credibility, and credibility comes from validation against ground truth. The weakness of computational physiology is that ground truth is unobservable — you cannot measure the conduction velocity field in a living human heart.

So we manufacture it. A programmable phantom with known geometry, known material properties and a known flow waveform, imaged with real hardware. The difference between what we predict and what it measures is a direct, quantitative error bound.

This corpus cannot be scraped, cannot be downloaded, and is expensive for anyone else to reproduce. It is why a device engineer believes the simulator.

Bland–Altman agreement, predicted against phantom-measured flow. Bias and limits of agreement — not a correlation coefficient, which hides bias.
VALIDATION HIERARCHY · WE STATE WHERE WE ARE
Analyticclosed-form referencesreached
Literaturepublished values
Retrospectiveclinical cohorts
Prospectivepre-registered

We are at tier 1. Every credibility report we generate says so, names the goals it does not meet, and cannot suppress that section. A reviewer who finds an unstated gap discounts the whole submission.

06 / WHY THIS IS A PLATFORM

The heart is the first organ.
Not the last.

Every architectural decision in H1 is chosen to be an H3 building block. The substrate does not care which organ it is describing — which is what turns a device-validation tool into a platform.

H1 · NOW → 2027

Ditto Cardio

Cardiovascular device validation. Revenue, no FDA clearance required for the tool itself, and a buyer with an existing budget line.

Shipping
H2 · 2027 → 2029

Ditto Body

Whole-body homeostasis and drug distribution. The cardiac twin becomes one organ inside a coupled system — lung, kidney, PBPK.

Gated on H1 revenue
H3 · 2029 →

Ditto Discover

Mechanisms medicine does not understand. Pyrazinamide has been first-line TB therapy since the 1950s and its mechanism is still contested, because the answer spans scales no single model can hold.

Gated on H2 validation

H2 is not funded until H1 has revenue. H3 is not funded until H2 validates a cross-organ prediction. We would rather state the gate than sell the vision.

07 / FOR YOUR TEAM

Three people buy this.
For three reasons.

Device R&D

Explore the design space in days. Find the failure modes three hand-segmented anatomies were never going to show you.

Regulatory affairs

Computational evidence is accepted in principle and brutal in practice. We generate the credibility argument automatically, from the runs.

CROs

Add computational validation to your services without building a simulation group. You own the client; Ditto is the engine.

08 / RESEARCH OUTPUT

Peer-reviewed.

MANUSCRIPTJournal article · 2026-07-27

Data Stewardship Barriers to Building Digital Twin Technology for Precision Medicine

AI in Medicine · ISSN 3042-6707

Patrick J. Silva · Jian Tao · Sara L. Rogers · Qiang He · Joshua D. Robert · Lance Black · Scott A. Bruce · Paula K. Shireman · Kenneth S. Ramos

DOI 10.3390/aimed1030020 ↗
CONFERENCE2026 AIHC · Poster #154

SonoSim (now Ditto): An AI-Driven Digital Twin and Validation Platform for Ultrasound Technologies

2026 AI in Health Conference · Rice Ken Kennedy Institute

Eric Gallagher · Joshua Robert · Joshua Norton · Maham Rahimi · Rick Silva

Poster #154 ↗

VentureWell Grant Recipient

Prototyping and clinical translation inside the Texas Medical Center with TMC Innovation and the EnMed Engineering Innovation Center.

We aren’t just building a model.
We are building the industry reference.
09 / THE ARCHITECTS
Joshua Robert
Lead / Physics

Joshua Robert

BS Computer Science, Texas A&M University

MD/MEng Candidate, TAMU School of Engineering Medicine

Joshua Norton
Lead / Platform

Joshua Norton

BS Aeronautical & Astronautical Engineering, Purdue University

MD/MEng Candidate, TAMU School of Engineering Medicine

Eric Gallagher
Lead / Biofluidics

Eric Gallagher

BS Electrical Engineering, University of Notre Dame

MD/MEng Candidate, TAMU School of Engineering Medicine

10 / ADVISORS
Rick Silva
Advisor

Rick Silva, PhD

Executive Director

Center for Genomic and Precision Medicine

Ramez Barsoom
Advisor

Ramez Barsoom, MD, MEng

Internal Medicine, Mayo Clinic

Cardiology, Cleveland Clinic

Maham Rahimi
Advisor

Maham Rahimi, MD, PhD, RPVI

Houston Methodist DeBakey Heart & Vascular Center

Weill Cornell Medical College

Bring your device CAD.
We’ll show you where it fails.

Cohort studies, platform access, and V&V40 credibility packages for cardiovascular device programmes. Investors: the deck is passphrase-protected — ask and we'll send it.