Publications
Read about scientific publications published by Brainify.AI, including peer-reviewed work.
Selected scientific publications
You can download each publication file.
Khayretdinova M, Shovkun A, Degtyarev V, Kiryasov A, Pshonkovskaya P and Zakharov I (2022) Predicting age from resting-state scalp EEG signals with deep convolutional neural networks on TD-brain dataset. Front. Aging Neurosci. 14:1019869. doi: 10.3389/fnagi.2022.1019869
The current study aimed to create a new deep learning solution for brain age prediction using raw resting-state scalp EEG. The architecture and training method of the proposed deep convolutional neural networks (DCNN) improve state-of-the-art metrics in the age prediction task using raw resting-state EEG data by 13%. Given that brain age prediction might be a potential biomarker of numerous brain diseases, inexpensive and precise EEG-based estimation of brain age will be in demand for clinical practice. Download
Khayretdinova M, Zakharov I, Pshonkovskaya P, Adamovich T, Kiryasov A, Zhdanov A, Shovkun A. Prediction of brain sex from EEG: using large-scale heterogeneous dataset for developing a highly accurate and interpretable ML model. Neuroimage. 2024 Jan;285:120495. doi: 10.1016/j.neuroimage.2023.120495. Epub 2023 Dec 12. PMID: 38092156.
This study presents a comprehensive examination of sex-related differences in resting-state electroencephalogram (EEG) data, leveraging two different types of machine learning models to predict an individual's sex. The best-performing model achieved an accuracy of 85% and a ROC AUC of 89%, surpassing all prior benchmarks set using EEG data and rivalling the top-tier results derived from fMRI studies. Download
A. Shovkun, A. Kiryasov, I. Zakharov and M. Khayretdinova, "Optimization of the Deep Neural Networks for Seizure Detection," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-2, doi: 10.1109/ICASSP49357.2023.10094645.
The goal of the present study was to optimize model selection and data preparation procedures for seizure detection in patients with epilepsy on wearable EEG data for the "ICASSP Signal Processing Grand Challenge’. We tested more than 100 deep convolutional neural networks (DCNN) architectures and hyperparameter combinations to achieve the most accurate, robust, and generalizable performance in seizure detection tasks. The best models included the spectral. Download transformation of raw EEG data for the DCNN model input, using correct cross-validation procedures, tuning data sampling for class imbalance problems, and data augmentation procedures. View, Download
Zakharov I., Kiryasov A., Shovkun A., Pshonkovskaya P., Khayretdinova M.
In the current study, we show that data leakage is an important problem in the existing large-scale EEG datasets. Using the DCNN model we demonstrate such non-physiological information of EEG as the recording location can be predicted with 99% accuracy. Our results show that crucial for advances in neuroscience large-scale EEG projects studies urgently require tools to harmonize data and eliminate the data leakage problem. Download
Ilya Zakharov¹, Alexey Shovkun¹, Andrey Kiryasov¹, Polina Pshonkovskaya¹, Timofey Adamovich¹, Andrey Zhdanov¹, Mariam
Khayretdinova¹
Current research on sex-related electrical signatures of the brain shows that some of these features are more common in females and others are more common in males. Overall, sex-related brain variance is better described as a continuous rather than a binary variable. Moreover, fMRI studies have found the mosaic “male” and “female” zones (Joel et al., 2015), and the distribution of such zones can be unique for a person. The “brain sex” phenotype may act as a biomarker to mark certain mental health disorders (Phillips et al., 2019). Download
Predicting age from resting-state scalp EEG signals with deep convolutional neural networks on TD-brain dataset
The current study aimed to create a new deep learning solution for brain age prediction using raw resting-state scalp EEG. The architecture and training method of the proposed deep convolutional neural networks (DCNN) improve state-of-the-art metrics in the age prediction task using raw resting-state EEG data by 13%. Given that brain age prediction might be a potential biomarker of numerous brain diseases, inexpensive and precise EEG-based estimation of brain age will be in demand for clinical practice.
Published in Frontiers on December 6th, 2022
Prediction of brain sex from EEG: using large-scale heterogeneous dataset for developing a highly accurate and interpretable ML model
This study presents a comprehensive examination of sex-related differences in resting-state electroencephalogram (EEG) data, leveraging two different types of machine learning models to predict an individual's sex. The best-performing model achieved an accuracy of 85% and a ROC AUC of 89%, surpassing all prior benchmarks set using EEG data and rivalling the top-tier results derived from fMRI studies.
Published in Neuroimage in January 2024
Optimization of the Deep Neural Networks for Seizure Detection
The goal of the present study was to optimize model selection and data preparation procedures for seizure detection in patients with epilepsy on wearable EEG data for the "ICASSP Signal Processing Grand Challenge’. We tested more than 100 deep convolutional neural networks (DCNN) architectures and hyperparameter combinations to achieve the most accurate, robust, and generalizable performance in seizure detection tasks. The best models included the spectral transformation of raw EEG data for the DCNN model input, using correct cross-validation procedures, tuning data sampling for class imbalance problems, and data augmentation procedures.
Published in IEEE Xplore on May 5th, 2023
Data Leakage Problem in Large Multi-site EEG Datasets
In the current study, we show that data leakage is an important problem in the existing large-scale EEG datasets. Using the DCNN model we demonstrate such non-physiological information of EEG as the recording location can be predicted with 99% accuracy. Our results show that crucial for advances in neuroscience large-scale EEG projects studies urgently require tools to harmonize data and eliminate the data leakage problem.
Presented at the International Symposium on Biomedical Imaging (ISBI - 2023) organized by IEEE in Colombia
“Brain sex” prediction from EEG data using
tree-based algorithms
Current research on sex-related electrical
signatures of the brain shows that some of these features are more common in females and others are more common in males. Overall, sex-related brain variance is better described as a continuous rather than a binary variable. Moreover, fMRI studies have found the mosaic “male” and “female” zones (Joel et al., 2015), and the distribution of such zones can be unique for a person. The “brain sex” phenotype may act as a
biomarker to mark certain mental health disorders (Phillips et al., 2019).
Published at the Max Planck Institute for Human Cognitive and Brain Sciences
Intellectual Property
We have secured 4 patents with several more in progress. We have more published more than 100+ articles in high-impact journals and conferences.