Clinerion Ltd Contact Details:
Main address: Margarethenstrasse 47 4053 Basel, Switzerland ,
Tel:+41 61 865 60 60 , E-mail: info(at) Website:

Clinerion Patient Network Explorer

Clinerion Patient Network Explorer

Optimized study design, precise site selection and faster patient search and identification for clinical research - in real time.

Clinerion Cookie Policy

Welcome to the Clinerion website. This website uses cookies. These cookies are used on your browser to understand how you are using our website. Using this website means you agree to our use of cookies. If you prefer not to have these cookies on your device, we advise you to disable them in your web browser settings. You accept the use of cookies by accepting this notice. You can read more details via our Privacy Policy page.

Privacy Policy page >

Federated Machine Learning Platform


Clinerion has built a Federated Machine Learning Platform on its Patient Network Explorer infrastructure, incorporating real-world data (RWD) from its global network of partner hospitals. The new platform will train machine learning (ML) algorithms and enable sophisticated analytics and pattern recognition use cases, ultimately offering better diagnosis of patients.

  • Development of advanced statistics and ML algorithms on Clinerion’s global network of de-identified electronic health records (EHRs), covering >435 M patients in 24 countries.
  • Facilitation of federated learning, learning across site-nodes and model deployment to sites, enabling direct, anonymized data metrics and per site / per country patient population insights.
  • Training of models on local data to identify patterns in local patient cohorts, and further optimization of models by using data from multiple sites.

This platform is now available for Machine Learning projects.

Potential Use Cases:

  • Development of detailed models based upon all possible disease presentations and predictive biomarkers, enabling the detection of high risk patients before they reach critical state, as well as the generation of disease phenotype sets for the identification of undiagnosed diseases, e.g., to find rare disease patients.
  • Generation of actionable insights into the patient journey.
  • Access to diverse population data to increase the diversity and inclusion of racial and ethnic minorities in clinical trials.

How It Works

Federated machine learning is the architectural framework based upon a single global server with decentralised data across many differential client servers. The goal of Federated Learning is to apply discrete models on multiple client servers and allow them to iterate and learn across the disparate data centers and learn collectively through the central global server. The advantage of this methodology is that data are not aggregated or pooled but stay locally in the original host server and all that is transacted is the model outputs or learning from the federated framework. At the same time, models can adapt across disparate data centers and iteratively learn across the aggregate without data pooling.

Our Technology Partners


Find Out More

Article: AI/ML to Generate Medical Insights ... While Maintaining Patient Data Security and Privacy

We wrote an article for the Journal for Clinical Studies on how the use of AI/ML techniques on patient EHR data can clarify the patient journey, while still preserving patient data privacy and security.

Read the article >

White Paper: Diagnosing Rare Diseases with Electronic Health Records

Our recent white paper explores the use case of identifying undiagnosed rare disease patients by modelling disease-specific phenotypes through use of Patient Network Explorer, our global patient Electronic Health Record network and Artificial Intelligence/ Machine Learning technologies.

Read the White Paper >

White Paper: The Clinerion Technology Vision for RWD Insights 

This white paper outlines Clinerion's vision of the future of RWD technologies and capabilities. Strong among them is the application of AI/ML learning.

Read the White Paper >



Webinar Recording: Rare Disease Patient Cohort Identification Using AI/ML Models and Federated EHR-based Real-world Data Infrastructure

In this webinar, along with speakers from Volv Global, Sanofi, and the Svabhegy Paediatric Hospital, Hungary, we assessed the issues facing patients of rare and orphan diseases. We looked at current developments in large hospital patient data networks, which enable automated patient search while keeping the identifiable patient data within the hospital systems, as well as the growing sophistication of artificial intelligence/machine learning models which can learn to identify sets of phenotypes for hard-to-diagnose diseases.

View the webinar >

Poster: Strategies Toward Identifying Undiagnosed Rare Disease Patients

In this poster, produced together with Volv Global, we explore how EHR-based real world data enables the ability to find potential patients that have been diagnosed as well as those that have not been correctly diagnosed.

The poster explains how EHR systems can be used to identify existing diagnosed patients, to identify undiagnosed patients through related symptoms, and to model more heterogenous disease response using an AI/ ML approach to find patients yet undiagnosed.

View the poster >