sanaitio

Building trust
in healthcare AI.

Trust by Design  ·  AI medical device consulting

sanaitio helps medtech companies develop, validate, and deploy AI-based medical devices that earn clinical adoption and regulatory approval.

Talk to us ⟶
01 / Problem
The adoption gap

Approved.
But not used.

The market for AI medical devices is large. Clinical adoption is not. Most cleared devices never reach routine use, and most lack the evidence to justify it.

950+
FDA-cleared AI medical devices
95%
cleared on regulatory equivalence, without new clinical evidence
<1%
of studies report real patient outcomes
3×
higher recall risk for devices without clinical validation
28 / 50 / 59%
cite trust as the top barrier (clinicians, hospitals, AI developers)

And the regulatory bar is rising. MDR now classifies most AI clinical decision support as Class IIa or higher. The AI Act demands full compliance by August 2027. Devices built on performance metrics alone cannot clear that bar.

Sources: European Commission (2025); Joshi et al. (2025); Muralidharan et al. (2024); Lee et al. (2025).

02 / Sanaitio
What we do

We close the gap between
approval and adoption.

sanaitio helps medtech companies develop, validate, and deploy AI-based medical devices that earn clinical adoption and regulatory approval.

We are a small consultancy combining biostatistics, causal inference, regulatory science, and clinical experience. We work with medtech teams from product definition through post-market monitoring, replacing fragmented compliance work with one coherent strategy: Trust by Design.

Talk to us
03 / Trust by Design
The framework

Build trust in.
Don't test it in.

Trust by Design adapts Quality by Design (ICH Q8/Q9/Q10), the framework that transformed pharmaceutical development, to AI-based medical devices.

Algorithmic performance is a prerequisite. Not the goal. The goal is a device used by physicians, funded by hospitals, and trusted by patients. Every data, modelling, and study decision is evaluated against that endpoint, from day one.

Four principles

Seven phases, one strategy

From product definition to post-market surveillance, every phase is informed by the same framework.

01

Objectives

  • Target Product Profile
  • Users, workflow, population
  • Risk class
02

Causal analysis

  • Causal DAG
  • Variables and confounders
  • Bayesian network
03

Data strategy

  • Quality
  • Optimal sampling
  • Representative cohorts
04

Model training & validation

  • Causal AI methods
  • Stress testing
  • Robustness
05

Clinical validation

  • Bayesian and adaptive protocols
  • Real-world evidence
06

Regulatory dossier

  • Justified strategy
  • Performance evidence
  • Interpretability
07

Deployment & monitoring

  • Local calibration
  • Drift detection
  • Quality control
04 / Methods
How it works

Causal and Bayesian
methods.

We are statisticians at the core. Our work is on the variables that decide whether a device performs, generalises, and earns approval: development variables, clinical endpoints, sources of bias, sample design, uncertainty.

Causal graphs make assumptions explicit and expose the confounders that classical performance metrics miss. Bayesian networks turn those graphs into quantitative tools, used to design data collection, validation protocols, and clinical studies under uncertainty.

Why Bayesian

EMA and FDA guidance increasingly endorses this approach in clinical development.

05 / Services
What we deliver

Four ways we engage.

Ordered by where they enter the lifecycle. Most engagements combine two or more.

01

Upstream development strategy

Build the map before you build the model.

The Bayesian network as a prospective simulation tool. Surfaces success factors, adoption risks, data needs, and regulatory constraints at the earliest design stage, when changes are cheapest.

02

Clinical validation

Validation designed from causal evidence, not guesswork.

Workflow mapping, Bayesian protocol design, sample-size justification under uncertainty, and adaptive strategies for evolving AI devices.

03

Regulatory navigation

The regulations, translated for your device.

The AI Act, MDR/IVDR, and GDPR turned into concrete technical and clinical actions. Implementation guidance, not generic checklists.

04

Deployment and monitoring

Trust does not end at certification.

The post-market plan: user training, local calibration, drift detection, quality control, and feedback loops that keep the device safe and effective in routine use.

06 / Why Sanaitio
What sets us apart

A foundation built for the work.

  1. 01

    Pharmaceutical
    heritage.

    The same rigor, now applied to AI.
    Three decades of qualifying drugs, processes, and measurement systems for the most heavily regulated industry there is.

  2. 02

    Causal and
    Bayesian methods.

    Uncertainty quantified, not hidden.
    The methodological foundation that makes Trust by Design operational, increasingly aligned with EMA and FDA guidance on Bayesian methods and real-world evidence.

  3. 03

    One offering,
    four disciplines.

    Not four contracts to four vendors.
    AI engineering, advanced statistics, causal inference, and regulatory science delivered as a single integrated service.

  4. 04

    Quality
    at the core.

    Compliance is not an afterthought.
    We follow ISO 9001 principles. Client data privacy and security are treated with the rigor healthcare demands, end to end.

  5. 05

    Concrete,
    tailored advice.

    For your device, not a template.
    Implementation guidance for your specific device, workflow, and risk class.

Talk to us
07 / Team
Founders & team

Behind sanaitio.

Bruno Boulanger

Bruno Boulanger

Co-founder & Scientific Advisor

30+ years in applied statistics for the pharmaceutical and medical device industries (Eli Lilly, UCB). Founder of Arlenda (2003). USP Committee on Statistics, 2010-2024. 130+ peer-reviewed publications.

LinkedIn
Nils Boulanger

Nils Boulanger

Co-founder & CTO

Data scientist and AI engineer. Designs and validates deep-learning systems for medical imaging deployed in real clinical workflows. Leads technical implementation at Sanaitio.

LinkedIn
Gaëlle Martin

Gaëlle Martin

Head of QA

20+ years in QA leadership across biotech, pharma, and consultancy. Designs QMS aligned with GMP, GCP, GAMP5, ISO 9001, and ISO 13485. Quality oversight for computerized system validation and GxP projects.

LinkedIn

Bruno and Nils also lead Trilenda, sister company specializing in CMC statistics and software for biopharma.

08 / Contact
Talk to us

From algorithm
to adoption.

A device in development, a validation path to plan, or just want to explore where Trust by Design fits your roadmap. Send a note.