Skip to main content
Rare diseases

New EU project: Quicker Diagnosis for Rare Disease Patients

Genetic Newborn Screening and Artificial Intelligence are important tools in new 25 million Euro project. Associate Professor Richard Röttger from SDU is part of the project.

By Birgitte Svennevig, , 10/20/2021

A new international consortium aims to tackle the major hurdle for rare disease patients – the lengthy and convoluted diagnosis journey – via an innovative research approach based on two central pillars: genetic newborn screening and artificial intelligence (AI)-based tools such as machine learning.

The project will run for a period of five years with a total budget of EUR 25 million provided by the Innovative Medicines Initiative, a joint undertaking of the European Union and the European Federation of Pharmaceutical Industries and Associations (EFPIA).

There are more than 7,000 known rare diseases, conditions that affect one, or less than one, person in 2,000. These conditions, which collectively impact an estimated 27-36 million people across the EU and will affect one in 17 people during their lifetime, are often severe, multisystemic chronic diseases that put patients at risk of permanent organ damage and degeneration.

Lengthy diagnosis journeys

Patients typically face an arduous journey to proper diagnosis, enduring on average eight years of countless doctor’s consultations, misdiagnoses and ineffective treatments.

Lengthy diagnosis journeys place a heavy burden on patients, their families and society. They also hinder swift intervention – such as appropriate treatments or enrolment in clinical trials – and patient empowerment, realized through strategies such as lifestyle adjustments, family planning, genetic counselling and coping with the psychosocial and/or financial consequences of the condition.

The project tools

Screen4Care will use a multi-pronged strategy to shorten the time to diagnosis and treatment for patients with rare diseases:

1) Genetic newborn screening: The project will drive newborn screening (using genetic testing and related advanced genomic technologies), which is anticipated to be an effective tool for early diagnosis given that approximately 72% of rare diseases have a genetic cause and 70% of rare disease patients are children.

2) AI-based tools: The project will design and develop new AI algorithms to identify patients at early disease onset via electronic health records and develop a repository of AI ‘symptom checkers’ to help patients who are in the midst of their diagnosis journeys – both supporting symptom-based diagnosis later in life.

Establishing an ecosystem

In addition to its goal of developing the core early-diagnosis system, Screen4Care aims to establish a digital infrastructure and ecosystem to engage patients, parents of newborns and caregivers as equal decision-makers in the diagnosis process.

The ecosystem will provide an open innovation platform, which allows for continuous data collection and information exchange, aiding the development of next-generation diagnostics and enabling physicians, patients and relatives to make informed decisions at an earlier stage. Screen4Care proposes that this will contribute to minimised disease progression, improved patient health and quality of life and an optimised use of healthcare resources.

21 partners across Europe

The Screen4Care team comprises 21 academic partners led by the University of Ferrara, nine industrial project partners led by Pfizer, and four small and medium-sized enterprises. It brings together experts in genetics, bioinformatics, data management and standards, imaging for phenotyping, ethics and health preference research, decision-analytic modelling, and cybersecurity.

University of Southern Denmark partner is Associate Professor, Richard Röttger, Dept. of Mathematics and Computer Science. Dr. Röttger is an expert in applying computer science to health research.

Meet the researcher

Richard Röttiger is an associate professor at the Department of Mathematics and Computer Science. He focuses on various aspects of machine learning and data mining of biomedical data.


Editing was completed: 20.10.2021