Predicting sex from brain rhythms with deep learning

Michel J A M Van Putten,Sebastian Olbrich,Martijn Arns

doi:10.1038/s41598-018-21495-7

Michel J A M Van Putten, Sebastian Olbrich + Show 1 more

Open Access

https://doi.org/10.1038/s41598-018-21495-7

Copy DOI

Abstract

We have excellent skills to extract sex from visual assessment of human faces, but assessing sex from human brain rhythms seems impossible. Using deep convolutional neural networks, with unique potential to find subtle differences in apparent similar patterns, we explore if brain rhythms from either sex contain sex specific information. Here we show, in a ground truth scenario, that a deep neural net can predict sex from scalp electroencephalograms with an accuracy of >80% (p < 10−5), revealing that brain rhythms are sex specific. Further, we extracted sex-specific features from the deep net filter layers, showing that fast beta activity (20–25 Hz) and its spatial distribution is a main distinctive attribute. This demonstrates the ability of deep nets to detect features in spatiotemporal data unnoticed by visual assessment, and to assist in knowledge discovery. We anticipate that this approach may also be successfully applied to other specialties where spatiotemporal data is abundant, including neurology, cardiology and neuropsychology.

Highlights

We have excellent skills to extract sex from visual assessment of human faces, but assessing sex from human brain rhythms seems impossible
Brain rhythms are the electrophysiological signatures of brain function[8,9,10], and scalp electroencephalogram (EEG) recordings in pathologies like postanoxic coma or seizures are very distinct from physiology[11,12,13]
We show that human scalp EEG recordings contain sex specific information that can be extracted with a deep convolutional network, reaching prediction accuracies better than 80%

Summary

Introduction

We have excellent skills to extract sex from visual assessment of human faces, but assessing sex from human brain rhythms seems impossible. We extracted sex-specific features from the deep net filter layers, showing that fast beta activity (20–25 Hz) and its spatial distribution is a main distinctive attribute. This demonstrates the ability of deep nets to detect features in spatiotemporal data unnoticed by visual assessment, and to assist in knowledge discovery. Deep nets do not need prior extraction of such hand-made features, can learn from raw data[28,29,30], and have potential to detect subtle differences in otherwise similar patterns[25,28]. We report on sex prediction from human scalp EEG recordings using a deep convolutional neural network

Objectives

Methods

Results

Conclusion