Intheris Health AG | Nodae ecosystem

Data stays,
knowledge moves

Intheris Health helps healthcare institutions convert clinical data into measurable operational and research value, without moving patient-level records.

Explore Nodae
Federated Research Network

Launch studies faster.
Keep control local.

Run multi-site evidence programs through one governed network, while each institution keeps local control.

View Architecture
Trust-by-design for data owners

Trust First.
No raw data transfer

Each site approves what runs, what is shared, and when. Cross-site outputs remain privacy-protected, traceable, and audit-ready.

Our Compliance
Nodae Platform Icon
The Technical Platform

Nodae

A clear operating model for hospitals and life-science partners: data stays inside each institution, studies are coordinated centrally, and only approved aggregated outputs are shared.

Module 01

Root: Local Ecosystem

For hospitals and data owners

Root enables data curation and deterministic reconstruction of patient journeys. It supports real-time analysis of clinical and financial data, and allows institutions to participate in studies while keeping local control. The platform is deployed in hardware tiers S, M, or L depending on message volume and site size.

Data Ingestion
Curation
Benchmarking
S / M / L Tiers
Module 02

Hub: Global Orchestration

For sponsors, pharma, and research networks

Hub orchestrates multi-site studies from a single sponsor-facing workspace. It distributes approved study logic to each participating hospital, supervises execution, and combines only the aggregated outputs each institution allows to share. Patient-level records never leave the local site.

Federated Learning
Decentralized Stats
Multicentric Studies
Study Templates
Module 03

Signals: Real-time Manager

For operations, quality, and pathway monitoring

Signals is the real-time monitoring layer of Nodae. It highlights operational and financial signals, pathway deviations, and live monitoring indicators so hospitals can detect friction early and review network-level patterns. It is intended for research and operations support only and is not a medical device.

Real-time Insight
Operational Signals
Live Cohort Tracking
Research Insights
Module 04

MimesIS·lab: Synthetic Stream

For validation, testing, and pre-production hardening

MimesIS·lab is the validation and simulation environment around Nodae. It generates realistic synthetic hospital activity across clinical, administrative, and financial workflows, and emits FHIR, HL7, DICOM, and file-based signals. Teams use it to stress-test algorithms, validate integrations, and rehearse deployments without touching real patient records.

Synthetic RWD
Stress Testing
Interop Testing
Bias Injection
Why Intheris Health

A local-first platform that compounds into a research network.

Hospitals do not install Root only to join studies. Root gives them a local cockpit for data quality, patient journeys, coding support, finance and operations, source monitoring, audit, and readiness. Adoption creates value before a single research program is launched.

Once Roots are installed, Hub turns them into a governed research network. Sponsors can design studies, invite sites, execute statistics or models locally, and receive aggregate outputs without centralizing patient records.

Intheris Health is an infrastructure partner, not a hospital information system vendor and not a data owner. This neutral position helps align hospitals, sponsors, and public-sector stakeholders around shared rules, transparent execution, and auditable outputs.

The same work that improves local operations also prepares a site for governed studies: cleaned data, terminology verification, source-health monitoring, eligibility coverage, provenance, and audit trails. Root makes research participation a by-product of better local infrastructure.

The platform supports country-level deployment, local governance, and provider-controlled permissions. Swiss and European institutions can collaborate across sites while keeping data control, compliance, and execution anchored locally.

Each new Root increases local institutional value and expands the addressable research network. This creates a practical adoption path: hospitals gain operational tools, sponsors gain governed access, and the platform compounds as the network grows.

Nodae is packaged for lightweight, reproducible deployment with containerized services, local keys, auditability, and provider-controlled trust. The operating model is reinforced by a documented IP portfolio: nine patent families prepared across Nodae and MimesIS·lab, currently in filing and counsel-review workflows.

Two priorities
Scalable RWE architecture and practical access to real-world data

Intheris Health provides the local infrastructure hospitals can use immediately and the federated architecture sponsors need to run governed RWE programs at scale. For research and operational support only, not a medical device.

Get it done with us
Who we serve

Why healthcare leaders choose Intheris Health.

Hospitals & Labs

Strengthen local operations and participate in sponsored research — whatever your institution's size — while keeping legal and technical control of patient data.

  • Sovereign Control Patient-level data stays on your infrastructure, under your governance.
  • Audit-Ready by Default Built-in traceability and role-based access help simplify compliance and reviews.
  • Research Revenue Channels Participate in sponsored studies and evidence programs without exposing raw patient records.
  • Integration Acceleration Healthcare-native interoperability reduces friction across systems and teams.

Pharma & MedTech

Run federated evidence programs across a governed group of institutions — from large academic centers to smaller regional hospitals — and work with verifiable results produced at the source, without moving identifiable patient data between sites.

  • Fast Study Setup Move from protocol to multi-site execution with lower operational overhead.
  • Verifiable Evidence Work with verifiable outputs produced directly at source institutions.
  • Reach Sites of Any Size Connect large and smaller hospitals alike through one governed model — each site keeps full technical and legal control of its data.
  • Regulatory Posture Governance, auditability, and privacy controls are integrated from day one.

Public Health & Researchers

Run cross-institution analyses with privacy-preserving methods for policy, epidemiology, and translational research.

  • Faster Access Standardized workflows reduce coordination delays across institutions.
  • Legal Clarity No raw data exchange simplifies legal pathways for many collaboration scenarios.
  • Near Real-Time Signals Track trends across diverse populations with timely, comparable metrics.
  • Reproducible Analytics Use privacy-preserving methods that keep analyses robust, transparent, and repeatable.
"Keep patient data sealed. Unlock evidence at network scale."

Enable · Federate · Discover

TRUST & GOVERNANCE

Intheris Health AG is a neutral infrastructure partner and does not claim ownership of patient data. Patient records stay inside each institution. The platform is built for clear governance, full traceability, and compliance with Swiss nFADP and GDPR. The network service can run in member countries to support sovereign operations.

  • ✓ No direct access to patient records: only model parameters and aggregated indicators leave the hospital
  • ✓ Local control: data processing runs in the hospital's own infrastructure, under hospital authority
  • ✓ Proof after the fact: tamper-evident audit trails show that no unauthorized processing took place
  • ✓ Country-level sovereignty: the network service can be deployed in host countries
  • ✓ Local user management: staff credentials never leave the hospital's infrastructure
Sovereign cloud hosting

Built on proven science,

Inter
connectivity
thera
healthcare
IS
Information Systems

Our platform builds on established research in federated learning and privacy-preserving analytics:

Rieke, N. et al. (2020). "The Future of Digital Health with Federated Learning."

npj Digital Medicine

McMahan, B. et al. (2017). "Communication-Efficient Learning of Deep Networks from Decentralized Data."

Proceedings of AISTATS 2017

Bonawitz, K. et al. (2017). "Practical Secure Aggregation for Privacy-Preserving Machine Learning."

Proceedings of ACM CCS 2017

Li, T. et al. (2020). "Federated Learning: Challenges, Methods, and Future Directions."

IEEE Signal Processing Magazine

Dwork, C. & Roth, A. (2014). "The Algorithmic Foundations of Differential Privacy."

Foundations and Trends in Theoretical Computer Science

Hersh, W. (2018). "Secondary Use of Electronic Health Records for Clinical Research."

Yearbook of Medical Informatics

The Team

Dr. Frédéric Schoenahl, PhD

Dr. Frédéric Schoenahl, PhD

Founder & CEO

Dr. Olivier Rager, MD

Dr. Olivier Rager, MD

Advisory Board Member, Physician

Dr. Lars Leidolt, MD

Dr. Lars Leidolt, MD

Advisory Board Member, Physician