TABLE 1.
Studies employing Machine Learning methods for detection of SCZ.
| Study | Preprocessing | Method | Signal | Database | Accuracy |
| Vázquez et al., 2021 | Low- and high-pass Butterworth filters | RF Classifier | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | NR |
| Rajesh and Sunil Kumar, 2021 | Symmetrically Weighted local binary patterns (SLBP) and correlation | Logit Boost classifier | EEG | Laboratory for Neurophysiology and Neuro-Computer Interfaces, MHRC | 91.66 |
| Agarwal and Singhal, 2023 | Fast Fourier transform (FFT) and statistical feature | SVM, KNN, BT, and DT | EEG | IPN (Olejarczyk and Jernajczyk, 2017) and Kaggle SCZ dataset (Ford et al., 2014) | 99.25 |
| Khare and Bajaj, 2022 | Robust variational mode decomposition (RVMD) | Optimized extreme machine classifier | EEG | Kaggle SCZ dataset (Ford et al., 2014) | 92.93 |
| Aydemir et al., 2022 | CGP17Pat and Iterative neighborhood component analysis (INCA) | KNN | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 99.91 |
| Jahmunah et al., 2019 | Butterworth filter and Segmentation | DT, Linear-Discriminant Analysis (LDA), KNN, Probabilistic-Neural- Network (PNN), and SVM | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 92.91 |
| Devia et al., 2019 | Butterworth filter and Independent component analysis (ICA) | LDA, and Rule-based classifier | EEG | Private | 71 |
| Neuhaus et al., 2013 | Digital filters and ICA | KNN, LDA, SVM, | EEG | Private | 72.4 |
| Luján et al., 2022 | Spatial filters and Bandpass filter | SVM, Bayesian LDA, Gaussian NB, KNN, Adaboost, and Radial basis function (RBF) | EEG | Private | 93.40 |
| Khare and Bajaj, 2021 | Flexible tunable Q wavelet transform (F-TQWT) | Flexible least square support vector machine (F-LSSVM) classifier and grey wolf optimization (GWO) algorithm | EEG | Kaggle SCZ dataset (Ford et al., 2014) | 91.39 |
| Zandbagleh et al., 2022 | EEGLAB and ICA | KNN, LDA, and SVM | EEG | Private | 89.21 |
| Du et al., 2020 | Wavelet Transform | Non-linear dynamic and Functional brain networks | EEG | Private | 76.77 |
| Aksöz et al., 2022 | Finite impulse response (FIR) filter | KNN, ANN, and SVM | EEG | Kaggle SCZ dataset (Ford et al., 2014) | 93.9 |
| Najafzadeh et al., 2021 | Butterworth filter | Adaptive neuro fuzzy inference system (ANFIS), SVM, and ANN | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 100 |
| Azizi et al., 2021 | Bandpass filter and ICA | LR classifier | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 97 |
| Shim et al., 2016 | Bandpass filter | SVM | EEG | Private | 88.24 |
| Kim et al., 2021 | Bandpass filter | SVN | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 76.85 |
| Keihani et al., 2022 | Bandpass filter | SVM and Bayesian optimization | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 90.93 |
| Prabhakar et al., 2020 | ICA | Black Hole (BH) optimization and SVM | EEG | IPN (Olejarczyk and Jernajczyk, 2017) | 92.17 |
| Kim et al., 2020 | Bandpass filter and notch filter | LDA | EEG | Private | 88.10 |
| Jeong et al., 2017 | Bandpass filter and ICA | LDA | EEG | Private | 98 |
| Lai et al., 2019 | Bandpass filter and ICA | NB and SVM | EEG | Private | 86.3 |
| Guo et al., 2022 | Vietoris–Rips filtering algorithm | Bottleneck and Wasserstein distances | EEG | Private | NR |
| Santos-Mayo et al., 2016 | Bandpass filter + ICA + Grand average + Segmentation | Multilayer Perceptron (MLP) and SVM | EEG-ERP | Private | 93.42 |
IPN, Institute of Psychiatry and Neurology; MHRC, Mental Health Research Center; ERP, Evoked Related Potential.