Stefan Haufe

Dec 29, 2023 | cell.com | Humboldt-Universität zu Berlin |Stefan Haufe

Highlights•Full predictive information in brain images not utilized even at 1 M samples•Multiple imaging modalities improve accuracy akin to doubling sample size•Most informative modality varies with larger sample sizes•Achieving practical utility may require prohibitively large samplesSummaryThis study examines the impact of sample size on predicting cognitive and mental health phenotypes from brain imaging via machine learning.

May 4, 2023 | frontiersin.org | Stefan Haufe |Ji Chen |German Castellanos-Dominguez |Luis Gomez |Luis Gómez

1. Introduction Electroencephalography (EEG) is a widely used tool for the assessment of neural activity in the human brain (Brette and Destexhe, 2012). To estimate the area of the brain responsible for the measured data, one has to simulate the electric potential as induced by hypothetical current sources in the brain, i.e., the EEG forward problem has to be solved.