Machine learning on subcortical brain features: A study of sample size efficiency for neurodegenerative disease classification

Subcortical brain alterations are a key feature of dementia disease progression. Machine learning (ML) has been applied widely to MRI-based brain features in dementia, where performance depends on the model choice, training data size, and input feature characteristics. Most studies compare ML models using a single training sample size. Here, we evaluate the sample-size efficiency of ML models based on subcortical gross volume and vertex-wise shape features for dementia stage classification using 2,511 samples in the Alzheimer's Disease Neuroimaging Initiative (ADNI). Learning curves were generated for dementia vs. cognitively normal controls (CN), dementia vs. mild cognitive impairment (MCI), and MCI vs. CN across increasing training sample sizes. Classification performance improved when increasing sample size for all models, with late- fusion models consistently achieving the highest performance, and Logit-TVL1 outperforming the other shape-based models. Learning curve analysis showed that classification performance was driven by the training sample size and the magnitude of anatomical group differences, and can be used to optimize future model selection tasks in dementia and other brain disorders.