John Thomas

John Thomas

Neuroengineering Scientist at Duke University:Biomedical Signal Processing | Deep Learning | Epilepsy | Sleep | Brain-Computer Interfaces

Automated Systems

This theme explores the use of automated systems, including traditional algorithms, deep learning, and large language models, to enhance diagnostics, predictive modeling, and decision-making in clinical and research settings.

Equipment and Recording

Investigates innovative methods for optimizing EEG electrode placement and improving electrical source imaging in epilepsy.

  • A. Horrillo-Maysonnial, …, J. Thomas, N. von Ellenrieder, J. Royer, B. Bernhardt, et al. (2023). Targeted density electrode placement achieves high concordance with traditional high-density EEG for electrical source imaging in epilepsy. Clinical Neurophysiology.

Signal Processing and Traditional Systems

Utilizes traditional machine learning algorithms and signal processing techniques to develop predictive models for clinical outcomes.

  • K. Jaber, T. Avigdor, …, J. Thomas, C. Abdallah, et al. (2024). A spatial perturbation framework to validate implantation of the epileptogenic zone. Nature Communications, 15(1), 5253.

  • S. Abirami, J. Thomas, R. Yuvaraj, and J. F. Agastinose Ronickom (2022). A Comparative Study on EEG Features for Neonatal Seizure Detection. In Springer, pp. 43–64.

  • P. Thangavel, J. Thomas, W. Y. Peh, et al. (2021). Time–frequency decomposition of scalp electroencephalograms improves deep learning-based epilepsy diagnosis. International Journal of Neural Systems, 31(08), 2150032. https://doi.org/10.1142/S0129065721500325

  • J. Thomas, J. Jin, J. Dauwels, S. S. Cash, and M. B. Westover (2017). Automated epileptiform spike detection via affinity propagation-based template matching. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, pp. 3057–3060.

  • J. Thomas, J. Jin, J. Dauwels, S. S. Cash, and M. B. Westover (2016). Clustering of interictal spikes by dynamic time warping and affinity propagation. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 749–753.

Deep Learning Systems

Focuses on using deep learning techniques, such as convolutional neural networks, to analyze complex neuroimaging data and enhance diagnostic accuracy.

  • W. Y. Peh, P. Thangavel, Y. Yao, J. Thomas, Y.-L. Tan, and J. Dauwels (2023). Six-center assessment of CNN-transformer with belief matching loss for patient-independent seizure detection in EEG. International Journal of Neural Systems, 33(03), 2350012. https://www.worldscientific.com/doi/abs/10.1142/S0129065723500120

  • W. Y. Peh, J. Thomas, E. Bagheri, et al. (2021). Multi-center validation study of automated classification of pathological slowing in adult scalp electroencephalograms via frequency features. International Journal of Neural Systems, 31(06), 2150016. https://doi.org/10.1142/S0129065721500167

  • T. Prasanth, J. Thomas, R. Yuvaraj, et al. (2020). Deep learning for interictal epileptiform spike detection from scalp EEG frequency sub bands. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, pp. 3703–3706.

  • J. Thomas, L. Comoretto, J. Jin, J. Dauwels, S. S. Cash, and M. B. Westover (2018). EEG classification via convolutional neural network-based interictal epileptiform event detection. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), IEEE, pp. 3148–3151.

  • R. Yuvaraj, J. Thomas, T. Kluge, and J. Dauwels (2018). *A deep learning scheme for automatic seizure detection f