Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

Abstract

Machine learning (ML) has transformed neuroimaging research by enabling accurate predictions and feature extraction from large datasets. In this study, we investigate the application of six ML algorithms (Lasso, relevance vector regression, support vector regression, extreme gradient boosting, category boost, and multilayer perceptron) to predict brain age for middle-aged and older adults, which is a crucial area of research in neuroimaging. Despite the plethora of proposed ML models, there is no clear consensus on how to achieve better performance in brain age prediction for this population. Our study stands out by evaluating the impact of both ML algorithms and image modalities on brain age prediction performance using a large cohort of cognitively normal adults aged 44.6 to 82.3 years old (N = 27,842) with six image modalities. We found that the predictive performance of brain age is more reliant on the image modalities used than the ML algorithms employed. Specifically, our study highlights the superior performance of T1-weighted MRI and diffusion-weighted imaging and demonstrates that multi-modality-based brain age prediction significantly enhances performance compared to unimodality. Moreover, we identified Lasso as the most accurate ML algorithm for predicting brain age, achieving the lowest mean absolute error in both single-modality and multi-modality predictions. Additionally, Lasso also ranked highest in a comprehensive evaluation of the relationship between BrainAGE and the five frequently mentioned BrainAGE-related factors. Notably, our study also shows that ensemble learning outperforms Lasso when computational efficiency is not a concern. Overall, our study provides valuable insights into the development of accurate and reliable brain age prediction models for middle-aged and older adults, with significant implications for clinical practice and neuroimaging research. Our findings highlight the importance of image modality selection and emphasize Lasso as a promising ML algorithm for brain age prediction.

Elucidating Multimodal Imaging Patterns in Accelerated Brain Aging: Heterogeneity through a Discriminant Analysis Approach Using the UK Biobank Dataset

“…Lasso is widely employed in predictive modeling, particularly when dealing with high-dimensional datasets. Prior investigations into brain-age prediction [35,36] have consistently demonstrated the superior performance of the Lasso model when compared to other machine-learning models. Given these compelling findings, we have chosen the Lasso model as the method of choice for brain-age prediction in our study.…”

Understanding the Temporal Dynamics of Accelerated Brain Aging and Resilient Brain Aging: Insights from Discriminative Event-Based Analysis of UK Biobank Data

“…The Lasso (least absolute shrinkage and selection operator) is a regression technique that enhances linear models by penalizing coefficients to prevent overfitting, aiding generalization and variable selection. Its superiority in brain age prediction is welldocumented [34,35]. Hence, we employed the Lasso in our research, with the regularization parameter (alpha) crucial for controlling the penalty magnitude.…”

Quantifying Brain and Cognitive Maintenance as Key Indicators for Sustainable Cognitive Aging: Insights from the UK Biobank

“…Dinsdale et al [38] applied a deep 3D convolutional neural network architecture based on the T1 MRI images of 19,687 subjects (age range 44.6 to 80.6 years), achieving MAEs of 2.86 years in females and 3.09 years in males, respectively. In a recent study [39], we conducted a comprehensive comparative analysis of six commonly used machine learning models. Our results revealed that the Lasso model demonstrated significantly superior performance compared to the other five models.…”