Brain Age Prediction: A Comparison between Machine Learning Models Using Brain Morphometric Data

Han, Juhyuk; Kim, Seo Yeong; Lee, Junhyeok; Lee, Won Hee

doi:10.3390/s22208077

Cited by 19 publications

(17 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the surface, our nding seems to contradict other, comparative analyses of machine learning models in predicting brainage using morphometric data who found RVR to systematically outperform GPR [41]. However, the one scenario in which GPR did outperform RVR in [41], was in the test case with the smallest number of participants, closer to that of the sample size used here. Therefore, machine learning model will be an important consideration for future use cases.…”

Section: Discussioncontrasting

confidence: 91%

“…These methods were selected as they have been shown to outperform other linear approaches [35], including in pediatrics [36]. On the surface, our nding seems to contradict other, comparative analyses of machine learning models in predicting brainage using morphometric data who found RVR to systematically outperform GPR [41]. However, the one scenario in which GPR did outperform RVR in [41], was in the test case with the smallest number of participants, closer to that of the sample size used here.…”

Section: Discussionmentioning

confidence: 73%

See 1 more Smart Citation

Predicting ‘Brainage’ in the Developmental Period using Structural MRI, Morphometric Similarity, and Machine Learning

Griffiths-King

Wood

Novák

2023

Preprint

View full text Add to dashboard Cite

Brain development is regularly studied using structural MRI. Recently, studies have used a combination of statistical learning and large-scale imaging databases of healthy-children to predict an individual’s age from structural MRI. This data-driven, ‘brainage’ typically differs from the subjects chronological age, with this difference a potential measure of individual difference. Few studies have leveraged higher-order or connectomic representations of structural MRI data for this brainage approach. We leveraged morphometric similarity as a network-level approach to structural MRI to generate predictive models of age. We benchmarked these novel brain-age approaches using morphometric similarity against more typical, single feature (i.e. cortical thickness) approaches. We showed that these novel methods did not outperform cortical thickness or cortical volume measures. All models were significantly biased by age, but robust to motion confounds. The main results show that, whilst morphometric similarity mapping may be a novel way to leverage additional information from a T1-weighted structural MRI beyond individual features, in the context of a brain-age framework, morphometric similarity does not explain more variance than individual structural features. Morphometric similarity as a network-level approach to structural MRI may be poorly positioned to study individual differences in brain development in healthy individuals.

show abstract

Section: Discussioncontrasting

confidence: 91%

Section: Discussionmentioning

confidence: 73%

Predicting ‘Brainage’ in the Developmental Period using Structural MRI, Morphometric Similarity, and Machine Learning

Griffiths-King

Wood

Novák

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…XG Boost by (De Lange et al, 2022), R= 0.889 and RMSE = 8.427 years in the CamCAN dataset). Similar to the work by (Han et al, 2022) comparing the performance of 27 different machine learning models (linear and nonlinear), we found the regularized linear regression algorithms achieved similar or better performance to nonlinear and ensemble algorithms.…”

Section: Methodssupporting

confidence: 82%

“…This is promising and suggests that for larger datasets as well as when trained experts for the visual motion rating are not available, this transformed Euler number can be used as a proxy measure. In line with previous studies in the literature (De Lange et al, 2022;Gao and Pang, 2022;Han et al, 2022;Monti et al, 2020), the brain age prediction model was trained based on a healthy aging population (CamCAN), and was then applied to the target MR-ART dataset, to provide an estimation of the range of effects sizes of delta brain age values that can be attributed to motion. As a complementary step we also used the MR-ART dataset for both training and test, where we trained the model on the data from no motion session and tested it on high motion session and vice versa.…”

Section: Discussionmentioning

confidence: 99%

Investigating the impact of motion in the scanner on brain age predictions

Moqadam

Dadar

Zeighami

2023

Preprint

View full text Add to dashboard Cite

Introduction: Brain Age Gap (BAG) is defined as the difference between the brain's predicted age and the chronological age of an individual. Magnetic resonance imaging (MRI)-based BAG can quantify acceleration of brain aging, and is used to measure brain health as aging and disease interact. Motion in the scanner is a common occurrence that can affect the acquired MRI data and act as a major confound in the derived models. As such, age related changes in head motion may impact the observed age-related differences. However, the relationship between head motion and BAG has not been directly examined. The aim of this study is to assess the impact of motion on voxel-based morphometry (VBM) based BAG. Methods: Data were obtained from two sources: i) T1-weighted (T1w) MRIs from the Cambridge Centre for Ageing and Neuroscience (CamCAN) were used to train the brain age prediction model, and ii) T1w MRIs from the Movement-related artifacts (MR-ART) dataset were used to assess the impact of motion on BAG. MR-ART includes one motion-free and two motion-affected (one low and one high) 3D T1w MRIs. We also visually rated the motion levels of the MR-ART MRIs from 0 to 5, with 0 meaning no motion and 5 high motion levels. All images were pre-processed through a standard VBM pipeline. GM density across cortical and subcortical regions were then used to train the brain age prediction model and assess the relationship between BAG and MRI motion. Principal component analysis was used to perform dimension reduction and extract the VBM-based features. BAG was estimated by regressing out the portion of delta age explained by chronological age. Linear mixed effects models were used to investigate the relationship between BAG and motion session as well as motion severity, including participant IDs as random effects. Results: In contrast with the session with no induced motion, predicted delta age was significantly higher for high motion sessions (t-value = 5.06, p < 0.0001), with marginal effect for low motion sessions (t-value = 1.95, p = 0.051). In addition, delta age was significantly associated with motion severity as evaluated by visual rating (t = 4.46, p < 0.0001). Conclusion: Motion in the scanner can significantly impact brain age estimates, and needs to be accounted for as a confound, particularly when studying populations that are known to have higher levels of motion in the scanner. These results have significant implications for brain age studies in aging and neurodegeneration. Based on these findings, we recommend assessment and inclusion of visual motion ratings in such studies.

show abstract

“…Han et al in their work “Brain Age Prediction: A Comparison Between Machine Learning Models Using Brain Morphometric Data” [ 13 ] presented machine-learning-based approaches for the purpose of abnormal aging process detection. The authors evaluated 27 machine learning models, which they applied to three independent datasets: the Human Connectome Project, the Cambridge Centre for Ageing and Neuroscience and the Information eXtraction from Images.…”

mentioning

confidence: 99%