Machine Learning for Precision Neuropsychiatry ML4PNP

Projects

Our projects focus on developing and applying machine learning methods in neuroimaging and healthcare, with a strong emphasis on real-world relevance and societal impact. They combine methodological innovation with large-scale data analysis, clinical collaboration, and human-centered design to address challenges in mental health, brain aging, and healthcare operations. Across projects, we aim to translate computational research into robust, interpretable, and actionable tools that support personalized care, informed decision-making, and sustainable healthcare systems.

Charting Brain Dynamics using Normative Modeling
Charting Brain Dynamics using Normative Modeling MEGaNorm

MEGaNorm develops normative models of brain function from large-scale MEG and EEG data across the human lifespan. These models enable individualized assessment of brain dynamics and support research toward precision neuropsychiatry. The project is funded through a starter grant awarded to the principal investigator.

Normative Range of P600 Morphology as a Diagnostic and Prognostic Tool in Neuropsychiatric Disorders
Normative Range of P600 Morphology as a Diagnostic and Prognostic Tool in Neuropsychiatric Disorders P600Norm

This project uses brain signals and machine learning to support diagnosis and outcome prediction in mental disorders. By modeling individual variability in neural responses during language comprehension, it contributes to more personalized and effective mental health care. The project is funded by the NWO within NWA within the Routes scheme (NeuroLab).

More

Charting the Normative Electroencephalography in Healthy Aging Population
Charting the Normative Electroencephalography in Healthy Aging Population

This project develops normative models of functional brain activity using large-scale EEG data from healthy aging populations. It is funded by the Growth Projects programme of Digital Sciences for Society at Tilburg University.

Predicting the Nurse Perceived Adequacy of Staffing Scale NPASS Score Using Machine Learning
Predicting the Nurse Perceived Adequacy of Staffing Scale (NPASS) Score Using Machine Learning NPASS

This project develops a machine learning–based system to predict nurse-perceived staffing adequacy using routinely collected hospital operational data. It is funded by the Growth Projects programme of Digital Sciences for Society at Tilburg University.

A patient-centric lifestyle recommender system for optimizing treatment response in psychosis
A patient-centric lifestyle recommender system for optimizing treatment response in psychosis U-Heal

U-Heal develops a human-centered and explainable AI framework for smart psychiatric care in patients with psychosis. This project shifts the focus from clinician-facing tools to patient-centered decision support. The project is funded by the EWUU alliance.