Neural Mosaics: Detecting Aberrant Brain Interactions using Algebraic Topology and Generative Artificial Intelligence.

Journal: AMIA ... Annual Symposium proceedings. AMIA Symposium
Published Date:

Abstract

Epilepsy affects over 50 million persons worldwide, with less than 50% achieving long-term success following surgery. Traditional electrophysiology signal-based seizure detection methods are resource-intensive, laborious, and overlook multifocal brain interactions. Algebraic topology methods, particularly persistent homology, offer robust representations of complex brain interaction patterns. Leveraging persistent homology and the Google Gemini Pro Vision 1.0 large language model (LLM), we present a novel prompting template to classify topological structures computed from intracranial electroencephalography (iEEG) recordings from refractory epilepsy patients. This study marks the first use of persistence diagrams as input to a LLM for analyzing brain interaction dynamics. Our results indicate that simply prompting LLMs with persistence diagrams is insufficient for accurate seizure detection. Nonetheless, unlike traditional approaches using machine learning algorithms for EEG classification, our approach does not require large volumes of representative training data or brittle hyperparameter tuning, which highlights the promise of more scalable analyses in the future.

Authors

  • Katrina Prantzalos
    Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, OH, USA.
  • Dipak Upadhyaya
    Department of Population and Quantitative Health Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA.
  • Pedram Golnari
    Department of Population and Quantitative Health Sciences, Case Western Reserve University School of Medicine, Cleveland, OH, USA.
  • Guadalupe Fernandez-BacaVaca
    Department of Neurology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA.
  • Geronimo Pacheco Aispuro
    Department of Neurology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA.
  • Saeideh Salehizadeh
    Department of Neurology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA.
  • Suraj Thyagaraj
    Department of Neurology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA.
  • Nick Gurski
    Department of Mathematics, Case Western Reserve University School of Medicine, Cleveland, OH, USA.
  • Kenneth Yoshimoto
    San Diego Supercomputer Center, University of California, San Diego, CA, USA.
  • Subhashini Sivagnanam
    San Diego Supercomputer Center, University of California, San Diego, CA, USA.
  • Amitava Majumdar
    University of California, San Diego, San Diego, CA, USA.
  • Satya S Sahoo
    Division of Medical Informatics, School of Medicine, Case Western Reserve University, Cleveland, OH.