Key result
CNN-LSTM deep learning outperforms other methods in separating schizophrenia patients from healthy subjects using EEG.
Why the study?
Interpreting numerous EEG signal patterns for diagnosing schizophrenia is difficult for physicians, motivating development of deep learning methods using small datasets.
Does a CNN-LSTM deep learning method accurately detect schizophrenia from EEG signals in a small dataset?
Does a CNN-LSTM deep learning method accurately detect schizophrenia from EEG signals in a small dataset?
A CNN-LSTM deep learning model can effectively detect schizophrenia from EEG signals even when trained on a small dataset.
May aid EEG-based schizophrenia screening research; leaves open larger validation before any clinical use.
Schizophrenia (SZ) is a brain disorder that disrupts normal thoughts, actions and emotions of a person. A common, cost-effective method of diagnosing SZ is using electroencephalography (EEG) signals. Since EEG signals are collected from many different channels over a long period of time, it sometimes become difficult for physicians to interpret numerous patterns of signals. In this work, authors proposed a number of deep learning (DL) based methods to separate the SZ patients from normal subjects from their EEG data using a small dataset of 14 SZ patients and 14 healthy subjects. Results were compared with works of others and the proposed CNN-LSTM method was found to perform better.
No takes yet. Share an insight, caveat, or question.
Sarkar et al. (2023) studied Schizophrenia (n=28). CNN-LSTM deep learning method vs. Other deep learning methods was evaluated on Separation of schizophrenia patients from normal subjects. A proposed CNN-LSTM deep learning method performed better than other methods in separating schizophrenia patients from healthy subjects using EEG data.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: