Exploring ADHD Neuroanatomy: Machine Learning Analysis of Cortical Morphology
Poster No:
273
Submission Type:
Abstract Submission
Authors:
Chung-Yuan Cheng1,2, Yen-Chin Wang1,2, Jung-Chi Chang1,2, Susan Shur-Fen Gau1,2
Institutions:
1National Taiwan University Hospital and College of Medicine, Department of Psychiatry, Taipei City, Taiwan, 2Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University, Taipei City, Taiwan
First Author:
Chung-Yuan Cheng
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
Co-Author(s):
Yen-Chin Wang
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
Jung-Chi Chang
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
Susan Shur-Fen Gau
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
National Taiwan University Hospital and College of Medicine, Department of Psychiatry|Graduate Institute of Clinical Medicine, College of Medicine, National Taiwan University
Taipei City, Taiwan|Taipei City, Taiwan
Introduction:
Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder manifesting with inattention, hyperactivity, and impulsivity, impairing daily functions (Wolraich et al., 2019). Advances in neuroimaging, particularly structural magnetic resonance imaging (MRI), have uncovered brain structure irregularities in ADHD individuals, such as alterations in cortical thickness, surface area, gray matter volume, and gyrification patterns (Seidman et al., 2005). Notably, Shaw et al. (2007) reported delayed cortical maturation in the prefrontal and parietal regions. This study employs machine learning to analyze neuroimaging data, aiming to identify reliable neuroimage biomarkers and enhance diagnostic precision in the ADHD populations (Cao et al., 2023).
Methods:
The sample consisted of 600 typically developing controls (TDC) and 568 individuals with ADHD. The TDC group comprised 229 females (38.2%) with an average age of 17.75 years (standard deviation, SD = 8.41; range: 4-53), while the ADHD group included 140 females (24.6%) with an average of 15.48 years (SD = 9.10; range: 5-50). All participants underwent T1-weighted magnetic resonance imaging (MRI) scans. Cortical parcellation was performed using the Destrieux Atlas within FreeSurfer software (Destrieux et al., 2010; Fischl, 2012). From each parcellation, six cortical features were extracted: curvature index, mean curvature, folding index, gray volume, surface area, and cortical thickness. For the analyses, five machine learning models were employed: CatBoost, LightGBM, XGBoost, Random Forest, and Support Vector Machine. Each model was trained and evaluated, and those achieving an area under the receiver operating characteristic curve (AUC) greater than 0.7 were selected for feature importance analysis. This analysis using SHapley Additive exPlanations (SHAP)(Lundberg, 2017) to determine the most predictive features.
Results:
Four of the machine learning models achieved AUC ranging from 0.73 to 0.76 and were subsequently included in the SHAP feature importance analysis. Our analyses revealed several brain regions where structural differences that appear to be important for distinguishing between individuals with TDC and those with ADHD (Figure 1). These critical regions, as illustrated in Figure 1, include the left inferior temporal gyrus, left paracentral lobule and sulcus, right supramarginal gyrus, left middle frontal sulcus, right posterior transverse collateral sulcus, left cuneus, right paracentral lobule and sulcus, right precuneus, left inferior part of the precentral sulcus, right anterior occipital sulcus and preoccipital notch, and right subparietal sulcus. These results suggest that these specific cortical features significantly contribute to distinguishing between the two groups.
Conclusions:
This study identified multiple cortical features and brain regions that could serve as potential biomarkers for ADHD. These findings indicate a promising path toward a more objective and reliable diagnostic process for ADHD, potentially enhancing current assessment methodologies. Further research is needed to validate these potential biomarkers and to explore their clinical relevance and utility of these biomarkers in diagnosing and managing ADHD.
Disorders of the Nervous System:
Neurodevelopmental/ Early Life (eg. ADHD, autism) 1
Modeling and Analysis Methods:
Classification and Predictive Modeling 2
Neuroanatomy, Physiology, Metabolism and Neurotransmission:
Cortical Anatomy and Brain Mapping
Keywords:
Attention Deficit Disorder
Data analysis
Machine Learning
STRUCTURAL MRI
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
Destrieux, C., Fischl, B., Dale, A., & Halgren, E. (2010). Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclature. NeuroImage, 53(1), 1-15.
Fischl, B. (2012). FreeSurfer. NeuroImage, 62(2), 774-781.
Lundberg, S. (2017). A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874.
Seidman, L. J., Valera, E. M., & Makris, N. (2005). Structural brain imaging of attention-deficit/hyperactivity disorder. Biological Psychiatry, 57(11), 1263-1272.
Shaw, P., Eckstrand, K., Sharp, W., Blumenthal, J., Lerch, J., Greenstein, D., Clasen, L., Evans, A., Giedd, J., & Rapoport, J. (2007). Attention-deficit/hyperactivity disorder is characterized by a delay in cortical maturation. Proceedings of the National Academy of Sciences, 104(49), 19649-19654.
Wolraich, M. L., Hagan, J. F., Allan, C., Chan, E., Davison, D., Earls, M., Evans, S. W., Flinn, S. K., Froehlich, T., & Frost, J. (2019). Clinical practice guideline for the diagnosis, evaluation, and treatment of attention-deficit/hyperactivity disorder in children and adolescents. Pediatrics, 144(4).