01Profile02CV03Projects04News05Agenda06Reviews07Contact
← All projects
Product / Software · Cleveland Clinic Funding

Dializy

Role Algorithm design & developmentPeriod June 2024
Quote
At the height of the Covid pandemic, we had around a hundred patients in intensive care at our hospital in Lyon, whereas normally this number does not exceed 10 people hospitalized in this department.
Dr Viet NguyenCritical care surgeon, Polyclinique Montréal (La Dépêche, November 2023)
Context
Problem

In acute dialysis, treatment parameters are calculated from the patient's biometric data and the machine's technology, with each device having its own rates and approach. The practitioner calculates them manually over 30 to 60 minutes, with a risk of error at the very moment when there is the least room for it. An initial version of the application existed, without an algorithm or automation: the parameters still had to be calculated manually.

Objective

Prove within ten days that a single formula could reliably and instantaneously produce these parameters on the target devices, for a presentation to investors in Paris.

Role

Analysis of clinical cases, design of the formula and algorithms, development of the application and AI assistant. Service provided under contract through Isalyx.

Market study

L'enjeu clinique

Figures provided by Dr Viet Nguyen in La Dépêche (November 2023). Acute dialysis artificially performs the blood purification functions normally carried out by the kidneys.

1/3Patients on acute dialysis are admitted to intensive care
50%Mortality within one month
Intensive care at the peak of the pandemic100 patients
Intensive care under normal conditions10 patients
Approach

Dix jours, 170 heures

J1J3J5J8J10
Clinical case analysis & formula
Algorithms & tests
.NET MAUI application & tests
Progress update with the practitioner
AI assistant
Features
One formula for three devices

Mathematical formula derived from the analysis of clinical cases, parameterized by the patient's sex and biometric data.

Prescription

Fresenius Multifiltrate Pro (CVVHD Citrate, CVVHD) and Baxter Prismax and Prismaflex (citrate CVVH, CVVHDF, CVVH).

Monitoring

Dedicated monitoring algorithms for each device, powered by the same calculation engine.

Conversational assistant

Obtain a prescription or monitoring plan by conversing with the assistant instead of filling out the form.

No more calculation errors

The decision is automated: manual calculation is removed from the practitioner's workflow.

Subscription and credits

“Dializy Plus” subscription journey and credit system integrated into the demonstration.

Architecture
Mobile application.NET MAUI, Android build
Calculation enginePrescription and monitoring algorithms, by device
AI assistantFunction calling to the engine, document grounding through RAG
LLMHosted on a European server
  • The calculation remains deterministic: the assistant does not calculate; it calls the engine via function calling and presents the result.
  • Assistant grounded in a medical corpus through RAG: outside this corpus, it has no basis for answering, keeping it focused on the dialysis domain.
  • LLM hosted in Europe for the governance and sovereignty of health data.
Security
  • Patient data anonymization
  • No patient data stored
  • LLM hosted on a European server · Governance and sovereignty of health data.
Results
30 to 60 min → 2 min
practitioner decision time
170 h
of development, in ten days
3
dialysis machines covered
Funding obtained
Cleveland Clinic, Abu Dhabi
Team

Équipe

  • Yohan DebusscherAlgorithm design, development & AI assistant
  • Dr Viet NguyenMedical expertise & clinical validation