For the latest publications of this PI visit https://pure.amsterdamumc.nl/en/persons/jaap-oosterlaan/
Oosterlaan, J. (Jaap) j.oosterlaan@amsterdamumc.nl
| Research line | Neuroscientic outcome measurement |
|---|---|
| Department | General pediatrics |
| Research Institute(s) | AR&D |
| Description | This research line aims to determine the impact of disease and treatment on the brain of children and young adults. The work focuses on the development and application of neuroscientific outcome measurements in typically developing and clinical groups, assessing neurocognitive functioning in children and adults (e.g. the in-house developed ‘Emma Toolbox for Neurocognitive Functioning’), advanced analysis of neurocognitive test performance (e.g. neurocognitive networks), structural and functional brain networks (e.g. DTI resting-state fMRI), and early neurocognitive functioning in babies and infants (e.g. eye-tracking). |
| Seniors | • Jaap Oosterlaan, PI • Cece Kooper, Postdoc |
| Projects | • The HEADLINE Study (Marloes Hoppen) investigates the acute impact of heading in amateur football using blood biomarkers. • The PEPR Study (Cece Kooper) determines neurodevelopmental outcome of traumatic brain injury in a research network of hospitals using neurocognitive testing, EEG and advanced multimodal MRI. • The ONSET Study (Noa Ijdo ) tracks early neurocognitive development in infants using with sickle cell disease using eyetracking (Noa Ijdo) • The MATURE Study (Dook Koch) investigates the long term outcome of meningitis among young adults infected in childhood using neurocognitive testing and advanced multimodal MRI. • The INPACT Study (Sophie Lijdsman) investigates the impact of chronic kidney disease and associated treatments on the brain of children and young adults using neurocognitive testing, EEG and diffusion tensor imaging. |
| Research line | Clinical outcome prediction for precision medicine |
|---|---|
| Department | General pediatrics |
| Research Institute(s) | AR&D |
| Description | This research line is aimed at better prediction of patient outcome, contributing to the transition towards precision medicine by improving clinical outcome prediction. Together with prof. dr. Mark Hoogendoorn & dr. Frank Bennis, we investigate the added value of machine learning models for clinical outcome prediction. We are also developing a machine learning pipeline optimized for high-dimensional data. |
| Seniors | • Jaap Oosterlaan, PI • Frank Bennis, UD |
| Projects | • The BPD prediction study (Frank Bennis) developed a model that predicts the development of BPD (at 36 weeks) using routinely collected clinical data and continuous vital signs collected in the first 7 days after birth. The prediction model consists of an auto-encoder with long short-term memory model, embedded in a neural network. The model is currently implemented in EPIC for automatic outcome prediction and real-world model performance monitoring. • The Extubation Success Prediction study (Frank Bennis) develops a machine learning model using routine clinical data and device data that provides online predictions of extubation success for children on mechanical ventilation at the Pediatric Intensive Care Unit. • The PEPR Study (Cece Kooper) determines the added value of machine learning models to predict outcome based premorbid data, hospital data and multimodal MRI data assessing structural and functional brain connectivity. • The ONSET Study (Noa Ijdo) determines predictors of early adverse neurocognitive development in infants using with sickle cell disease (Noa Ijdo) • The MATURE Study (Dook Koch) determines predictors of very long-term term outcome of childhood meningitis in young adulthood. |
Last edited: 05-03-2026