2024/11/19 by Trevor Wei Kiat Tan, Kim‐Ngan Nguyen, Chen Zhang +13 · 1 voice · 3 citations
Environmental Science · Neuroscience · Psychology · #Functional Brain Connectivity Studies #Health, Environment, Cognitive Aging #Neuroscience #Psychology
paper · pdf · doi:10.1101/2024.11.16.623903
published in bioRxiv (Cold Spring Harbor Laboratory) (Cold Spring Harbor Laboratory)
openalex publication_date 2024/11/19 · openalex created_date 2024/11/20 · openalex updated_date 2026/08/06
health outcomes, much like the success of finetuning large language models for specific applications. However, it is also well-accepted that machine learning models trained to directly predict specific outcomes (i.e., direct models) often outperform those trained on surrogate objectives. Therefore, despite their much larger training data, it is unclear whether brain age models outperform direct models in predicting specific brain health outcomes. Here, we compare large-scale brain age models (pretrained on 53,542 participants) and direct models for predicting specific health outcomes related to Alzheimer's Disease (AD) dementia. Using anatomical T1 scans from three continents (N = 1,848), we find that summarizing brain age with a single scalar (i.e., brain age gap) led to poor prediction performance. Using higher-dimensional intermediate representations of brain age models led to better prediction, but was still worse than direct models without finetuning. Using intermediate representations of finetuned brain age models was necessary to achieve similar performance as direct models. Overall, our results do not discount brain age as a useful marker of general brain health, but suggest that using chronological age as a pretraining target might be suboptimal for predicting specific health outcomes.