Explainable Machine-Learning-Based Characterization of Abnormal Cortical Activities for Working Memory of Restless Legs Syndrome Patients

Minju Kim, Hyun Kim, Pukyeong Seo, Ki Young Jung, Kyung Hwan Kim

Research output: Contribution to journalArticlepeer-review

Abstract

Restless legs syndrome (RLS) is a sensorimotor disorder accompanied by a strong urge to move the legs and an unpleasant sensation in the legs, and is known to accompany prefrontal dysfunction. Here, we aimed to clarify the neural mechanism of working memory deficits associated with RLS using machine-learning-based analysis of single-trial neural activities. A convolutional neural network classifier was developed to discriminate the cortical activities between RLS patients and normal controls. A layer-wise relevance propagation was applied to the trained classifier in order to determine the critical nodes in the input layer for the output decision, i.e., the time/location of cortical activities discriminating RLS patients and normal controls during working memory tasks. Our method provided high classification accuracy (~94%) from single-trial event-related potentials, which are known to suffer from high inter-trial/inter-subject variation and low signal-to-noise ratio, after strict separation of training/test/validation data according to leave-one-subject-out cross-validation. The determined critical areas overlapped with the cortical substrates of working memory, and the neural activities in these areas were correlated with some significant clinical scores of RLS.

Original languageEnglish
Article number7792
JournalSensors
Volume22
Issue number20
DOIs
StatePublished - Oct 2022
Externally publishedYes

Keywords

  • convolutional neural network
  • event-related potential
  • explainable machine learning
  • restless legs syndrome
  • working memory

Fingerprint

Dive into the research topics of 'Explainable Machine-Learning-Based Characterization of Abnormal Cortical Activities for Working Memory of Restless Legs Syndrome Patients'. Together they form a unique fingerprint.

Cite this