Research launched to develop explainable AI

Amsterdam University Medical Centre (UMC), Centrum Wiskunde & Informatica (CWI) and Leiden UMC have received almost €900,000 to develop new forms of explainable AI.

The aim is to tackle misunderstanding of AI information, especially in the medical field.

Artificial Intelligence has many applications for improving healthcare, for example to predict which treatment is most appropriate for each patient based on data, but not all doctors understand how to interpret these predictions properly, which limits the use of this technology in hospitals.

Peter Bosman, senior researcher in CWI’s Life Sciences and Health group, said:: “AI is changing the world, but the possibilities and impact could be even greater if we could better understand and explain to medical experts how a learned model comes to certain conclusions.”

Tanja Alderliesten, project leader on behalf of LUMC, said the technology is being considered a ‘black box’ for many. “Doctors don’t fully understand how it works. Consequently, they find it hard to blindly trust its predictions”. By developing new AI forms that are more accessible for medical professionals, researchers hope to boost its use in clinical settings.

This project, funded by the Gieskes-Strijbis Fund, also focuses on building models that factor in different types of data at the same time - a major innovation compared to existing techniques.

Alderliesten explained: “AI in healthcare is very suitable for image analysis, such as CT scans. These models can provide insights concerning whether any abnormalities are found on the scan. However, there is much more data available to us that should also be considered, such as DNA profile, gender, weight, medical history. Better predictions can be made by including the whole spectrum of information.”

Amsterdam embraces AI

The research ties into Amsterdam’s vision for AI - that, used responsibly, it truly improves citizen’s lives. As one of the world’s most AI-ready cities, the Dutch capital is home to countless innovations, and public-private initiatives such as AI Technology for People ensures AI applications are designed and deployed in the city in responsible and useful ways.

One recent application of AI in healthcare helped determine the best treatment for severely ill patients. By sharing data from ICU units in hospitals across the Netherlands, doctors could decide the best course of action for patients with COVID-19, for example. 

Read more business news from around Amsterdam.