André Marquand appointed professor of computational psychiatry

André Marquand has been appointed Professor of Computational Psychiatry at Radboudumc / Radboud University. It applies artificial intelligence techniques to large datasets with different types of data. This allows him to predict how psychiatric disorders will develop in individual patients. It also contributes to the development of better treatments.

Psychiatric disorders such as ADHD, autism, schizophrenia and depression have many forms and causes. But we do not yet know enough how they are born and how they develop. Principal investigator André Marquand of the Donders Institute for Brain, Cognition and Behavior uses artificial intelligence (AI) to recognize patterns in large datasets containing different types of data, such as brain scans, genetics, behavior and environmental factors. For example, it maps the differences between individuals, predicts the course of each patient’s disease and discovers the starting points for personalized therapy.

ocean of data

Last year, Marquand published a study in which he and his colleagues analyzed the brain scans of 60,000 people. They used it to make an atlas of the brain. Brain scans of psychiatric patients can now be compared to this atlas to show abnormalities. It recently started using smartphone data as well. With colleagues from the psychiatry department, he collected this type of data from around 100 patients suffering from depression for a year. Marquand explains, “How many text messages do you send per day, how often do you move around, how bright is your screen; this data says a lot about your behavior. We really swim in an ocean of data, it is difficult to recognize patterns. A computer can do it much better. That’s why we use AI methods to make chocolate from it.

Black Box

AI is a “black box” that is difficult for many people to understand. This is why Marquand uses relatively simple techniques. “We have to be able to understand it and explain it to others,” he says. “It increases confidence in the results we get and gives others the opportunity to verify them. But of course we want to be able to make a good prediction, and sometimes more complex methods are better for that. This remains an important consideration in our work. Ultimately, this should lead to better treatments for psychiatric illnesses. “By getting a better picture of the differences between patients, we can offer them personalized treatment in the future,” says Marquand. “In oncology, they’ve come a long way with this ‘precision medicine’ approach, and we need to move towards that in psychiatry as well.

Career

Marquand (Vevey, Switzerland, 1977) studied computer science and psychology at the University of Canterbury in New Zealand. He obtained his PhD at King’s College London on machine learning techniques for MRI image analysis (thesis title: ‘Probabilistic Machine Learning Methods for Multivariate Prediction of Magnetic Resonance Images’). Subsequently, he was a post-doctoral fellow and university lecturer at this institute. He has been working at Radboudumc since 2014, first as an assistant professor and from 2019 as an associate professor. He has received several grants, including a VIDI grant (2015), a Wellcome Trust ‘Digital Innovator’ grant (2020), a Horizon Europe grant (2020) and NIH R01 grants from the US government (2021, 2022).

Marquand has been appointed Professor of Computational Psychiatry for a period of five years, starting December 1, 2022. His chair is 50% funded by a Consolidator Grant from the European Research Council (awarded in 2020).