Scholarlink

The hippocampus is a critical brain structure for learning and memory formation, with its function being largely dictated by the complex dynamics of synaptic transmission. Precise classification of different synaptic responses is fundamental to understanding hippocampal circuit integrity, plasticity, and their disruption in neurological disorders. Traditional methods for analyzing these electrophysiological signals are often labor-intensive and susceptible to subjective bias. The aim of this work is to classify electrophysiological signals obtained in biological experiments with mice hippocampal slices in vitro. These signals were recorded in CA1 area of the hippocampus as responses to stimulus in CA3 area of the hippocampus with different positions of the recording electrode. We compare the effectiveness of several machine learning algorithms, such as Random Forest, Gradient Boosting, Support Vector Machine, K-Nearest Neighbours and others, for accurate classification of synaptic signals. We also analyze which features contribute most to separating signals of different types. This study can be useful for automatic classification of described data, which can be a first step in the pipeline for different studies in the field of neuroinformatics and biomedical technologies.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Classification of Synaptic Responses in Mice Hippocampal Slices Using Machine Learning Approach

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Daniil Vershinin,
  • Alexander Naumov,
  • Svetlana Gerasimova,
  • Anton Malkov,
  • Lev Smirnov,
  • Tatiana Levanova,
  • Albina Lebedeva

摘要

The hippocampus is a critical brain structure for learning and memory formation, with its function being largely dictated by the complex dynamics of synaptic transmission. Precise classification of different synaptic responses is fundamental to understanding hippocampal circuit integrity, plasticity, and their disruption in neurological disorders. Traditional methods for analyzing these electrophysiological signals are often labor-intensive and susceptible to subjective bias. The aim of this work is to classify electrophysiological signals obtained in biological experiments with mice hippocampal slices in vitro. These signals were recorded in CA1 area of the hippocampus as responses to stimulus in CA3 area of the hippocampus with different positions of the recording electrode. We compare the effectiveness of several machine learning algorithms, such as Random Forest, Gradient Boosting, Support Vector Machine, K-Nearest Neighbours and others, for accurate classification of synaptic signals. We also analyze which features contribute most to separating signals of different types. This study can be useful for automatic classification of described data, which can be a first step in the pipeline for different studies in the field of neuroinformatics and biomedical technologies.