A million dollar grant for medical visualizations

This can completely change the way healthcare providers and patients communicate about medical information

Thanks to AiNed’s grant of 3.5 million euros, doctors will be able to show the patient’s personal illness more easily in the future. Academic Alliance Radboudumc – Maastricht UMC+ develops artificial intelligence in cooperation with the business world, which enables, for example, the visualization of DNA, brain signals or hearing. This gives patients a better understanding of their own health.

This can completely change the way healthcare providers and patients communicate about medical information. Instead of having to explain black and white scans step by step, the doctor will get help from artificial intelligence in the future. This enables the use of insightful images of an individual patient’s anatomy. Trained computer models like ChatGPT can explain and even visualize medical data in an understandable way. This enables easy interpretation of complex data sources such as DNA analyses, brain signals and hearing tests.

PROSPER Innovation Lab, a consortium of 27 partners led by ENT doctor Marc van Hoof, will now receive 3.5 million euros to develop this type of artificial intelligence. The support comes from the Dutch growth fund AiNed, which is committed to developing artificial intelligence both economically and socially. Van Hoof: “I expect that our AI will lead to new insights, better diagnostics and a better understanding of patients’ health.”

Large scale
Privacy laws are currently still a barrier to AI development because AI requires a lot of data, but you can’t just use traceable patient data. A new consortium called PROSPER InnovationLabs uses an ingenious method to do this. “We are going to build very large synthetic data sets of real data, but made completely anonymous and therefore no longer traceable,” says researcher Joost Stultiens at UMC+ in Maastricht.

This approach enables the exchange of data between Dutch hospitals on a large scale, while still complying with data protection legislation. This data, which is no longer known from which patient it came from, allows them to quickly launch their AI project without years of approval processes and contract negotiations. This scale is only possible thanks to partnerships between Dutch hospitals. “We want to work together to enable real innovations that improve care,” says Professor Dr. Ronald Pennings of the Radboud University Medical Center.

Translation
In this system, patients can decide online what can be done with their data. This combination of anonymized health data and dynamic patient consent could be a breakthrough in obtaining the necessary data for AI training in healthcare. “This means that traceable data no longer needs to be shared with commercial parties, and patients decide for themselves who can use their data and for what purpose.” explains researcher Elke Dedamp from UMC+ in Maastricht.

Van Hoof and his team are starting with this approach in ear, nose, and throat medicine, but they expect a quick translation to other areas of medicine. – We demonstrate this by combining different fields of medicine, from neurosurgery to breast cancer diagnosis at home. This not only saves time and energy, but also reduces the need to collect large amounts of patient data for each application, strengthening both healthcare and the Netherlands’ commercial position in AI health technology.

Collaborators
The PROSPER InnovationLab consortium consists of the following partners: Radboudumc, Maastricht UMC+, UMCG, TNO, Superconnectors, Enatom, SURF, WSK Medical, IDS International BV, Quantitas Solutions, Earhelp, Zuyderland Medical Center, Catharina Hospital, Deventer Hospital, Elisaedenth Sairaala, Isala Clinics , Rijnstate, Bernhoven Hospital, Elkerliek Hospital, Treant Hospital Care, AI hub Oost NL, AI hub Brightlands, Brainport, Screenpoint medical, Dutch Head Neck Society (NWHHT) and Eyehelp.

Source: Maastricht UMC+