Predicting trail-making test performance using 7-Tesla structural cerebral MRI.
9 affiliations
- 1Department of Psychiatry, Psychotherapy and Psychosomatics, RWTH Aachen University, Aachen, Germany.
- 2Institute of Neuroscience and Medicine 4, INM-4, Forschungszentrum Jülich, Jülich, Germany.
- 3Department of Psychiatry II, Ulm University and BKH Günzburg, Günzburg, Germany.
- 4Department of Psychiatry and Psychotherapy II, LVR-Klinik Köln, Köln, Germany.
- 5Department of Neurology, RWTH Aachen University, Aachen, Germany.
- 6Department of Psychiatry, Psychotherapy and Psychosomatics, RWTH Aachen University, Aachen, Germany. [email protected].
- 7Institute of Neuroscience and Medicine 4, INM-4, Forschungszentrum Jülich, Jülich, Germany. [email protected].
- 8Department of Psychiatry, University of Southern Denmark, Odense University Hospital, Odense C, Denmark. [email protected].
- 9Department of Psychiatry II, Ulm University and BKH Günzburg, Günzburg, Germany. [email protected].
Abstract
Psychopharmaceutical therapy has seen a lack of improvement in efficacy, highlighting the need for a more individualized treatment approach that optimally leverages pharmaceutical effects. To achieve this, it is necessary to identify factors that can predict psychological attributes and treatment outcomes. We hypothesize that brain morphology may serve as a predictor of performance in psychological tests. A 7-Tesla-MRI system was used to measure 74 transdiagnostic patients and 41 healthy controls. Values for grey matter volume (GMV), cortical thickness and gyrification based on the Schaefer 100 Atlas for parcellation were determined. Using this morphological data, performance in a Trail-Making Test (TMT) - A and B was predicted with the help of a deep learning model. A SHAP analysis was conducted to identify the key variables important for the model. The accuracy in predicting TMT performance was very good at 0.795. The most decisive feature influencing predictions was gyrification. Areas indicating inter-group differences were focused in the frontal cortex, as well as in temporal and parietal regions. Morphological characteristics can predict test performance with high accuracy. These results support the implementation of a transdiagnostic approach in clinical practice to better address the underlying pathophysiology. Symptom prediction based on neuroimaging data appears to be an achievable goal.
Related
- Age-Related Cognitive Slowing and Wrong-Target Errors on the Trail Making Test in Virtual Reality Across the Adult Lifespan
- Validity, Diagnostic Accuracy, and Feasibility of Trail Making Test in Virtual Reality for Mild Cognitive Impairment
- Hemodynamic-Structural Multi-Fidelity Assessment of Endovascular Flow Diversion Strategies for Cerebral Aneurysm Treatment: An Integrated Computational and Experimental Framework
- Predicting Cerebral Pericyte Contractility Across Experimental and Physiological Conditions: an in-silico framework
- Voxelwise degree centrality alterations and cognitive performance in severe unilateral M1-segment middle cerebral artery stenosis with ipsilateral watershed infarction.
BibTeX
@article{schnellbacher2026predicting,
title = {{Predicting trail-making test performance using 7-Tesla structural cerebral MRI.}},
author = {Gereon J Schnellbächer and Ravichandran Rajkumar and Tanja Veselinović and Shukti Ramkiran and Jana Hagen and Maria Collee and N Jon Shah and Irene Neuner and Jürgen Dammers},
journal = {Translational psychiatry},
year = {2026},
month = oct,
doi = {10.1038/s41398-026-04402-x},
url = {https://europepmc.org/article/MED/42897153},
note = {CC BY},
}
RIS
TY - JOUR
TI - Predicting trail-making test performance using 7-Tesla structural cerebral MRI.
AU - Gereon J Schnellbächer
AU - Ravichandran Rajkumar
AU - Tanja Veselinović
AU - Shukti Ramkiran
AU - Jana Hagen
AU - Maria Collee
AU - N Jon Shah
AU - Irene Neuner
AU - Jürgen Dammers
PY - 2026
DA - 2026/10/19
JO - Translational psychiatry
DO - 10.1038/s41398-026-04402-x
UR - https://europepmc.org/article/MED/42897153
AB - Psychopharmaceutical therapy has seen a lack of improvement in efficacy, highlighting the need for a more individualized treatment approach that optimally leverages pharmaceutical effects. To achieve this, it is necessary to identify factors that can predict psychological attributes and treatment outcomes. We hypothesize that brain morphology may serve as a predictor of performance in psychological tests. A 7-Tesla-MRI system was used to measure 74 transdiagnostic patients and 41 healthy controls. Values for grey matter volume (GMV), cortical thickness and gyrification based on the Schaefer 100 Atlas for parcellation were determined. Using this morphological data, performance in a Trail-Making Test (TMT) - A and B was predicted with the help of a deep learning model. A SHAP analysis was conducted to identify the key variables important for the model. The accuracy in predicting TMT performance was very good at 0.795. The most decisive feature influencing predictions was gyrification. Areas indicating inter-group differences were focused in the frontal cortex, as well as in temporal and parietal regions. Morphological characteristics can predict test performance with high accuracy. These results support the implementation of a transdiagnostic approach in clinical practice to better address the underlying pathophysiology. Symptom prediction based on neuroimaging data appears to be an achievable goal.
SN - 2158-3188
ER -