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

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 20; p. 7792
• Main Authors: Kim, Minju, Kim, Hyun, Seo, Pukyeong, Jung, Ki-Young, Kim, Kyung Hwan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.10.2022; MDPI
• Subjects: Anxiety; convolutional neural network; Electroencephalography; event-related potential; Evoked Potentials; Experiments; explainable machine learning; Humans; Insomnia; Machine Learning; Magnetic resonance imaging; Memory; Memory tasks; Memory, Short-Term; Neural networks; Restless legs syndrome; Restless Legs Syndrome - complications; Short-term memory; Signal to noise ratio; Sleep; Statistical analysis; working memory; United States > US; explainable machine learning; event-related potential; working memory; convolutional neural network; restless legs syndrome
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22207792

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.