The DOI matches its Crossref record; 58 of the 59 references it cites were found in a registry or an index.
GaborPDNet: gabor transformation and deep neural network for Parkinson's disease detection using EEG signals
Open accessAbstract
Parkinson’s disease (PD) is globally the most common neurodegenerative movement disorder. It is characterized by a loss of dopaminergic neurons in the substantia nigra of the brain. However, current methods to diagnose PD on the basis of clinical features of Parkinsonism may lead to misdiagnoses. Hence, noninvasive methods such as electroencephalographic (EEG) recordings of PD patients can be an alternative biomarker. In this study, a deep-learning model is proposed for automated PD diagnosis. EEG recordings of 16 healthy controls and 15 PD patients were used for analysis. Using Gabor transform, EEG recordings were converted into spectrograms, which were used to train the proposed two-dimensional convolutional neural network (2D-CNN) model. As a result, the proposed model achieved high classification accuracy of 99.46% (±0.73) for 3-class classification (healthy controls, and PD patients with and without medication) using tenfold cross-validation. This indicates the potential of proposed model to simultaneously automatically detect PD patients and their medication status. The proposed model is ready to be validated with a larger database before implementation as a computer-aided diagnostic (CAD) tool for clinical-decision support.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“For example, some EEG-based DNNs treat every channel independently, and use information from each channel as a separate observation (Loh et al., 2021).”
From Data leakage in deep learning studies of translational EEG (2024) · cites this paper as Loh et al., 2021
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“[45] achieved top five in the ImageNet Large Scale Visual Recognition Competition with their proposed CNN model.”
MethodMDS clinical diagnostic criteria for Parkinson’s disease
Postuma, R. B., Berg, D., Stern, M., Poewe, W., Olanow, C. W., Oertel, W., Obeso, J., Marek, K., Litvan, I., Lang, A. E., et al. (2015) · Movement Disorders · doi:10.1002/mds.26424 · Cited by 7,653 · cited 1×
“…criteria of bradykinesia with at least one feature of rest tremor or rigidity, symptoms closely linked to dopaminergic neurons, and the absence of certain exclusion criteria and presence of supportive criteria, the main being a clear and dramatic beneficial response to dopaminergic therapy [15,16].”
BackgroundUnderstanding of a convolutional neural network
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017) · 2017 International Conference on Engineering and Technology (ICET) · doi:10.1109/icengtechnol.2017.8308186 · Cited by 3,986 · cited 1×
“The input image (S) with the dimension of (i, j) undergoes a discrete convolution operation (∗) with (W), which is the convolutional kernel that updates its weight each time the kernel slides across the input image [46,47].”
BackgroundDorsey, E. R., Elbaz, A., Nichols, E., Abbasi, N., Abd-Allah, F., Abdelalim, A., Adsuar, J. C., Ansha, M. G., Brayne, C., Choi, J.-Y. J., et al. (2018) · The Lancet Neurology · doi:10.1016/s1474-4422(18)30295-3 · Cited by 2,816 · cited 4×
“Between 1990 and 2016, the number of globally affected individuals by PD increased from Electronics 2021 , 10 , 1740 3 of 15 2.5 million to 6.1 million [13].”
BackgroundInfluentialFeigin, V. L., Abajobir, A. A., Abate, K. H., Abd-Allah, F., Abdulle, A. M., Abera, S. F., Abyu, G. Y., Ahmed, M. B., Aichour, A. N., Aichour, I., et al. (2017) · The Lancet Neurology · doi:10.1016/s1474-4422(17)30299-5 · Cited by 2,275
Balestrino, R., & Schapira, A. H. V. (2020) · European Journal of Neurology · doi:10.1111/ene.14108 · Cited by 1,508 · cited 3×
“The set of supportive and exclusion criteria are complex, and misdiagnosis is not uncommon due to an array of differential diagnoses, many of which are not accompanied by a decrease in dopamine levels [4,17].”
BackgroundData-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
Brunton, S. L., & Kutz, J. N. (2019) · Cambridge University Press eBooks · doi:10.1017/9781108380690 · Cited by 1,154 · cited 5×
“The issue concerning Fourier transform is that only the frequency domain of the signal is provided, but the time when the frequencies occur is not included [44].”
BackgroundInfluentialDeep learning for healthcare applications based on physiological signals: A review
Faust, O., Hagiwara, Y., Hong, T. J., Lih, O. S., & Acharya, U. R. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.04.005 · Cited by 1,026 · cited 2×
“However, conventional machine-learning approaches require tedious feature-extraction and -selection procedures that might result in the information loss of EEG signals [35,36].”
BackgroundSelf-citationCollection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings
Sakar, B. E., Isenkul, M. E., Sakar, C. O., Sertbas, A., Gurgen, F., Delil, S., Apaydin, H., & Kursun, O. (2013) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2013.2245674 · Cited by 703 · cited 1×
“…methods of PD diagnosis. speech impairment and dysgraphia are commonly observed in 90% of PD opens This opens the possibility of automatic PD diagnosis based on speech and hand-writing recognition [53 – 55]. the possibility of automatic PD diagnosis based on speech and recognition [53–55].”
BackgroundDiagnosis and treatment of Parkinson disease: molecules to medicine
Savitt, J. M. (2006) · Journal of Clinical Investigation · doi:10.1172/jci29178 · Cited by 650
Cited by
Loh, H., Hong, W.-R., Ooi, C., Chakraborty, S., Barua, P., Deo, R., Soar, J., Palmer, E., & Acharya, U. R. (2021) · Italian National Conference on Sensors · doi:10.3390/s21217034 · Cited by 97
“Nearly half of these studies proposed the use of the CNN model [25,47,48], and the remaining three studies had proposed the application of an RNN [49], DNN [50], and a hybrid deep learning model that combines CNN and RNN algorithms [51] (Figure 5).”
BackgroundMethodInfluentialSelf-citationAljalal, M., Aldosari, S. A., Molinas, M., AlSharabi, K., & Alturki, F. A. (2022) · Scientific Reports · doi:10.1038/s41598-022-26644-7 · Cited by 144
“Compared with those who used the same dataset, only two studies 29,35 investigated the off-PD versus on-PD classification problem.”
BackgroundMethodResultInfluentialDeep Transfer Learning Based Parkinson’s Disease Detection Using Optimized Feature Selection
Abdullah, S. M., Abbas, T., Bashir, M. H., Khaja, I. A., Ahmad, M., Soliman, N. F., & El‐Shafai, W. (2023) · IEEE Access · doi:10.1109/access.2023.3233969 · Cited by 127
“Loh et al. [11] used the Electroencephalography (EEG) signals for the detection of Parkinson’s disease.”
MethodAlalayah, K. M. A., Senan, E. M., Atlam, H. F., Ahmed, I. A., & Shatnawi, H. S. A. (2023) · Diagnostics · doi:10.3390/diagnostics13111924 · Cited by 134
“Hui et al. [22] proposed a CNN for analyzing the EEG recordings of 16 healthy subjects and 15 Parkinson’s patients.”
BackgroundJunaid, M., Ali, S., Eid, F., El–Sappagh, S., & Abuhmed, T. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107495 · Cited by 122
Data leakage in deep learning studies of translational EEG
Brookshire, G., Kasper, J., Blauch, N. M., Wu, Y. C., Glatt, R., Merrill, D. A., Gerrol, S., Yoder, K. J., Quirk, C., & Lucero, C. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1373515 · Cited by 103
“For example, some EEG-based DNNs treat every channel independently, and use information from each channel as a separate observation (Loh et al., 2021).”
BackgroundParkinson’s disease detection and classification using EEG based on deep CNN-LSTM model
Li, K., Ao, B., Wu, X., Wen, Q., Haq, E. U., & Yin, J. (2023) · Biotechnology and Genetic Engineering Reviews · doi:10.1080/02648725.2023.2200333 · Cited by 89
“In addition, Loh et al. (Loh et al., 2021) used a 2D-CNN on the Gabor transform of a resting-state EEG dataset to categorize people into HC and PD with and without medication with a 99.5% accuracy.”
InfluentialMaitín, A. M., Romero, J. P., & García-Tejedor, Á. J. (2022) · Applied Sciences · doi:10.3390/app12146967 · Cited by 83
Deep learning for neurodegenerative disorder (2016 to 2022): A systematic review
Chaki, J., & Woźniak, M. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104223 · Cited by 82
Gupta, K., Bajaj, V., & Ansari, I. A. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3132072 · Cited by 74
EEG Signal Processing for Medical Diagnosis, Healthcare, and Monitoring: A Comprehensive Review
Amer, N. S., & Belhouari, S. B. (2023) · IEEE Access · doi:10.1109/access.2023.3341419 · Cited by 80
“Most of these studies in used DL methods [124], [125], [209].”
ResultDeep Learning for Parkinson's Disease Diagnosis: A Short Survey
Shaban, M. (2023) · De Computis · doi:10.3390/computers12030058 · Cited by 70
“The spatial autoencoder achieved the best AUC of ROC Prasuhn et al. used a binary Support Vector Machine (bSVM) and Multiple-Kernal Learning (MKL) to detect PD based on DTI MRI [35].”
MethodResting-state electroencephalography based deep-learning for the detection of Parkinson’s disease
Shaban, M., & Amara, A. (2022) · PLoS ONE · doi:10.1371/journal.pone.0263159 · Cited by 60
“The achieved performance is the highest achieved among the recent state-of-the-art deep-learning applications on EEG for PD detection and diagnosis [23–28].”
BackgroundMethodResultInfluentialSiuly, S., Khare, S. K., Kabir, E., Sadiq, M. T., & Wang, H. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108462 · Cited by 58
“[3,31,32].”
Machine learning- and statistical-based voice analysis of Parkinson’s disease patients: A survey
Amato, F., Saggio, G., Cesarini, V., Olmo, G., & Costantini, G. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119651 · Cited by 58
Diagnosis and classification of Parkinson's disease using ensemble learning and 1D-PDCovNN
Nour, M., Şentürk, Ü., & Polat, K. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107031 · Cited by 52
Parkinson’s disease diagnosis using deep learning: A bibliometric analysis and literature review
Abumalloh, R. A., Nilashi, M., Samad, S., Ahmadi, H., Alghamdi, A., Alrizq, M., & AlYami, S. S. (2024) · Ageing Research Reviews · doi:10.1016/j.arr.2024.102285 · Cited by 51
Parkinson’s disease diagnosis using neural networks: Survey and comprehensive evaluation
Tanveer, M., Rashid, A. H., Kumar, R., & Raman, B. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.102909 · Cited by 51
Ibrahim, A. M., & Mohammed, M. A. (2024) · International Journal of Mathematics Statistics and Computer Science · doi:10.59543/ijmscs.v2i.8915 · Cited by 45
“Studies conducted by[17], [18], [19], [20], [21], [22], [23], [24], used convolutional neural networks (CNNs) and recurrent neural networks.”
BackgroundMethodInfluentialNovel automated PD detection system using aspirin pattern with EEG signals
Barua, P. D., Doğan, Ş., Tuncer, T., Baygin, M., & Acharya, U. R. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104841 · Cited by 45
Self-citationParsa, M. G., Rad, H. Y., Vaezi, H., Hossein‐Zadeh, G., Setarehdan, S. K., Rostami, R., Rostami, H., & Vahabie, A. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107683 · Cited by 46
Generalizable electroencephalographic classification of Parkinson's disease using deep learning
Sugden, R. J., & Diamandis, P. (2023) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2023.101352 · Cited by 24
Qiu, L., Li, J., & Pan, J. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.957181 · Cited by 40
“For the UC San Diego dataset (15 PD patients and 16 controls), the classification performance (accuracy, sensitivity, specificity, and AUC are above 93% in γ band) of our proposed MCNN model is comparable, although not the highest, compared to other related studies (Khare et al., 2021a,b; Loh et al., 2021; Shaban, 202…”
MethodResultInfluentialPratihar, R., & Sankar, R. T. (2024) · Computers · doi:10.3390/computers13110293 · Cited by 53
Zhang, T., Lin, L., & Xue, Z. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119650 · Cited by 35
Lati̇foğlu, F., Penekli, S., Orhanbulucu, F., & Chowdhury, M. E. H. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09569-2 · Cited by 36
AAL and Internet of Medical Things for Monitoring Type-2 Diabetic Patients
Ahmed, S., Srinivasu, P. N., Alhumam, A., & Alarfaj, M. (2022) · Diagnostics · doi:10.3390/diagnostics12112739 · Cited by 32
“The Gabor transform’s Gaussian distribution function acts as a kernel, moving over the one-dimensional signals and calculating the Fourier transform and Gaussian function multiplication inside its frame to provide information on time when various frequencies occur [34,35].”
BackgroundParajuli, M., Amara, A. W., & Shaban, M. (2023) · PLoS ONE · doi:10.1371/journal.pone.0286506 · Cited by 37
Bubble detection in photoresist with small samples based on GAN augmentations and modified YOLO
Yang, G., Song, C., Yang, Z., & Cui, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106224 · Cited by 33
Diagnosis of Parkinson Disease from EEG Signals Using a CNN-LSTM Model and Explainable AI
Bdaqli, M., Shoeibi, A., Moridian, P., Sadeghi, D., Pouyani, M. F., Shalbaf, A., & Górriz, J. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-61140-7_13 · Cited by 30
A Speech-Based Hybrid Decision Support System for Early Detection of Parkinson's Disease
Lamba, R., Gulati, T., Jain, A., & Rani, P. (2022) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-022-07249-8 · Cited by 30
“[35] presented a system using EEG signals.”
Li, J., Li, X., Mao, Y., Yao, J., Gao, J. P., & Liu, X. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105872 · Cited by 30
Miah, A. S. M., Suzuki, T., & Shin, J. (2025) · IEEE Access · doi:10.1109/access.2025.3575023 · Cited by 33
“…[28], [29], [30], [31], [32], [33], handwriting exams [34], [35], [36], [37], [38], [39], [40], speech patterns [41], [42], [43], [44], [45], [46], [47], Electroencephalogram phy (EEG) [38], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57] and multi-modal fusion data modalities [58].”
Delfan, N., Shahsavari, M., Hussain, S., Damaševičius, R., & Acharya, U. R. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23120 · Cited by 31
Self-citationBDD-Net: An End-to-End Multiscale Residual CNN for Earthquake-Induced Building Damage Detection
Seydi, S. T., Rastiveis, H., Kalantar, B., Halin, A. B. A., & Ueda, N. (2022) · Remote Sensing · doi:10.3390/rs14092214 · Cited by 22
Al-Najjar, H., al-Rousan, N., & Al-Najjar, D. (2024) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2024.101524 · Cited by 11
Bera, S., Geem, Z. W., Cho, Y. I., & Singh, P. K. (2025) · Diagnostics · doi:10.3390/diagnostics15060773 · Cited by 24
“Studies such as Loh et al., 2021 [20] have demonstrated PD classification using CNN-based models which may be highly accurate, but it mostly relies on spectrogram representations instead of raw EEG features, which can cause the potential loss of critical time-domain information.”
InfluentialMotin, M. A., Mahmud, M., & Brown, D. J. (2022) · IEEE International Conference on Application of Information and Communication Technologies (AICT) · doi:10.1109/aict55583.2022.10013589 · Cited by 20
“In addition to classical machine learning, deep learning models were investigated in [11]–[16].”
BackgroundMethodSasidharan, D., Sowmya, V., & Gopalakrishnan, E. A. (2025) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-025-01521-5 · Cited by 18
FCN-PD: An Advanced Deep Learning Framework for Parkinson’s Disease Diagnosis Using MRI Data
Alrawis, M., Mohammad, F., Al-Ahmadi, S. A., & Al-Muhtadi, J. F. (2025) · Diagnostics · doi:10.3390/diagnostics15080992 · Cited by 18
Optimized MobileNetV3: a deep learning-based Parkinson’s disease classification using fused images
Sukanya, P., & Rao, B. S. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1702 · Cited by 18
“The second most performance was presented in reference ( Loh et al., 2021 ).”
BackgroundMethodDrawing-Aware Parkinson’s Disease Detection Through Hierarchical Deep Learning Models
Kansizoglou, I., Tsintotas, K. A., Bratanov, D., & Gasteratos, A. C. (2025) · IEEE Access · doi:10.1109/access.2025.3535232 · Cited by 17
“D CNN architecture [28].”
Hammoud, M., Kovalenko, E., Somov, A., Витальевна, Б. Е., & Baldycheva, A. V. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100914 · Cited by 17
Balnarsaiah, B., Nayak, B. A., Sujeetha, G. S., Babu, B. S., & Vallabhaneni, R. B. (2023) · Soft Computing · doi:10.1007/s00500-023-08535-9 · Cited by 16
“The authors in Loh et al. (2021) discussed that noninvasive techniques like EEG have the potential to serve as an alternative biomarker for the diagnosis of Parkinson’s disease.”
BackgroundRetractedA review of emergent intelligent systems for the detection of Parkinson’s disease
Dhanalakshmi, S., Maanasaa, R. S., Maalikaa, R. S., & Senthil, R. (2023) · Biomedical Engineering Letters · doi:10.1007/s13534-023-00319-2 · Cited by 20
“Another database [39, 42] used open neuro, which is a publicly available dataset with and without medication and HC were considered in their work.”
MethodAçıkgöz, H., Korkmaz, D., & Talan, T. (2024) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-024-01316-2 · Cited by 17
“Parkinson’s disease (PD), which has become a global health problem, is a neurodegenerative disease that usually occurs in the elderly and was first described in the 1800s [1].”
Sha, M., & Rahamathulla, M. P. (2024) · Quantum Information Processing · doi:10.1007/s11128-024-04588-3 · Cited by 21
“Researches proved that the deep learning approach produces high performance compared to other well defined algorithms [11, 12].”
Aggarwal, N., Saini, B. S., & Gupta, S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106008 · Cited by 17
Zarei, O., moghaddam, M. T., & Vastegani, S. M. (2025) · Brain Research Bulletin · doi:10.1016/j.brainresbull.2025.111667 · Cited by 22
Hasanzadeh, M., & Mahmoodian, H. (2023) · Applied Acoustics · doi:10.1016/j.apacoust.2023.109561 · Cited by 12
Automatic Diagnosis of Parkinson's Disease Based on Deep Learning Models and Multimodal Data
Li, L. J., Dai, F., He, S., Yu, H., & Liu, H. (2024) · Advances in medical diagnosis, treatment, and care (AMDTC) book series · doi:10.4018/979-8-3693-1281-0.ch009 · Cited by 11
Machine learning approaches for neurological disease prediction: A systematic review
Fatima, A., & Masood, S. (2024) · Expert Systems · doi:10.1111/exsy.13569 · Cited by 12
Goyal, P., Rani, R., & Singh, K. (2024) · Journal of Neural Transmission · doi:10.1007/s00702-024-02830-x · Cited by 13
“In Loh et al. (2021), the authors explored the potential for noninvasive methods like EEG to be used as an alternative biomarker for the diagnosis of Parkinson’s disease.”
Voice feature description of Parkinson’s disease based on co-occurrence direction attribute topology
Zhang, T., Lin, L., Tian, J., Xue, Z., & Guo, X. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106097 · Cited by 12
Bhat, S., & Szczuko, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-98356-7 · Cited by 13
“A review of the literature reveals that a 10-fold cross-validation improves ML model performance; therefore, the study evaluates classifiers’ performances using the 10-fold stratified cross-validation technique 6,34,36,42,43,47 .”
InfluentialGómez-Rodellar, A., Mekyska, J., Gómez‐Vilda, P., Brabenec, L., Šimko, P., & Rektorová, I. (2023) · International Journal of Neural Systems · doi:10.1142/s0129065723500284 · Cited by 9
EEG classification based on Grassmann manifold and matrix recovery
Li, X., Qiao, Y., Duan, L., & Miao, J. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105491 · Cited by 7
Alanís, A. Y., Sánchez, O. D., Vaca-González, A., & Rangel-Heras, E. (2023) · Mathematics · doi:10.3390/math11194065 · Cited by 7
“Models generated by deep neural networks offer a promising approach to automatic feature extraction from complex data model representations [26].”
Artificial Intelligence-Based Effective Detection of Parkinson’s Disease Using Voice Measurements
Reddy, G. P., Rohan, D., Kumar, Y. V. P., Kasaraneni, P. P., & Srikanth, M. (2024) · International Electronic Conference on Sensors and Applications (ECSA) · doi:10.3390/ecsa-11-20481 · Cited by 7
Afonso, M. M., Edla, D. R., & Reddy, R. R. (2025) · SN Computer Science · doi:10.1007/s42979-025-03685-z · Cited by 7
“…mixed models, Li et al. in [45] introduced two [45] 98.6 San Diego Lina et al. [46] 84.5 San Diego Nayana et al. [47] 86–97 San Diego Loh et al. [10] 99.46 San Diego Khare et al. [9] 100 San Diego Shaban et al. [48] 98 San Diego Soojin et al. [49] 96.9 UNM Lina et al. [46] 92.5 UNM Oh et al.…”
InfluentialA Hybrid CNN-BiLSTM Neural Network Architecture for Early Prediction of Parkinson's Disease
Chauhan, M. K., & Ghosal, P. (2024) · IEEE International Symposium on Smart Electronic Systems (iSES) · doi:10.1109/ises63344.2024.00071 · Cited by 7
“Table 3 compares the performance metrics of HC vs. PD While some studies like [7] and [8] from Table 3 out-perform our model, their techniques used manual feature extraction, which incorporate domain-specific knowledge about signal processing and time-frequency analysis and”
Dong, S., Jin, Y. M., Bak, S., Yoon, B., & Jeong, J. (2021) · Electronics · doi:10.3390/electronics10233020 · Cited by 8
Emad-Ud-Din, M., Almuteb, I., Wang, Y., & Hubbard, J. E. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3562448 · Cited by 6
“This study does not explicitly state whether they ensured SICV. d) Loh et al. [8] do not specify subject-wise splitting while claiming high accuracy for a three-class classification problem.”
InfluentialPatro, P., & Das, T. K. (2025) · IEEE Access · doi:10.1109/access.2025.3583572 · Cited by 6
“A Gabor transformation-based deep learning model proposed by Loh et al. [13] for PD detection using EEG signals.”
Wang, H., Wang, H.-J., Qie, S.-Y., Wang, C.-X., Li, N., & Wang, H.-M. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1677722 · Cited by 5
Ramzani, E., Yadollahzadeh‐Tabari, M., golesorkhtabaramiri, M., & Pouyan, A. A. (2023) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.22948 · Cited by 8
“In 12 – 17 But, it should be noted that this method requires the presence of the patient in a special laboratory, connecting the device signal measurement, and so on.”
MethodAkram, S. W., & Kumar, A. P. S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17762-z · Cited by 6
Hamidi, A., Mohamedpour, K., & Yousefi, M. (2024) · doi:10.1109/icee63041.2024.10667765 · Cited by 6
“For example, Loh et al. [7] achieved an impressive accuracy of 99.46% by applying Gabor transformation using a convolutional neural network.”
MethodInfluentialGarehdaghi, F., & Sarbaz, Y. (2024) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2024.104276 · Cited by 6
Shaban, M., Cahoon, S., Khan, F. F., & Polk, M. (2021) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci50451.2021.9660178 · Cited by 6
Alıcı, Y. H., Öztoprak, H., Rizaner, N., Başkak, B., & Özgüven, H. D. (2022) · Psychiatry Research Neuroimaging · doi:10.1016/j.pscychresns.2022.111537 · Cited by 6
Afonso, M. M., Edla, D. R., Chintala, S., & Ragoju, R. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.107922 · Cited by 5
Afonso, M. M., Edla, D. R., & Ramesh, D. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.04.660 · Cited by 5
Sharma, K., Shanbhog, M., & Singh, K. (2025) · Asian Journal of Psychiatry · doi:10.1016/j.ajp.2025.104537 · Cited by 5
Afonso, M. M., Edla, D. R., Reddy, R. R., & Ramadevi, Y. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111012 · Cited by 5
Integrative Federated Learning Framework for Multimodal Parkinson’s Disease Biomarker Fusion
Pratihar, R., & Sankar, R. T. (2025) · Computers · doi:10.3390/computers14090388 · Cited by 6
“Techniques ranging from HOS-based ML [26–28] to CNNs, RNNs, hybrid RNNs, and wavelet-CSP classifiers have reported AUCs up to 99.5% [29,30].”
InfluentialMancazzo, V., Sibilano, E., Buongiorno, D., Carli, R., Bevilacqua, V., & Brunetti, A. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.109811 · Cited by 9
Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics
Li, J., Chen, X., Shen, F., Chen, J., Liu, Y., Zhang, D., Yuan, Z., Zhao, F., Li, M., & Yang, Y. (2025) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2025.3625973 · Cited by 16
“Time–frequencytransformationssuch as Gabor Transform and CWT have been widely adopted: spec-trograms [47] and scalograms [178] capture temporal–spectral dynamics more effectively than raw waveforms.”
An FPGA Prototype for Parkinson’s Disease Detection Using Machine Learning on Voice Signal
Khan, M., Moiz, A., Khan, G. N., Wajid, M., Usman, M. J., & Ali, J. (2025) · IEEE Access · doi:10.1109/access.2025.3572092 · Cited by 7
“A convolutional neural network (CNN) was proposed by [21] to analyze the EEG signals of 15 PD patients and 16 healthy people.”
Shaban, M. (2024) · Machine Learning with Applications · doi:10.1016/j.mlwa.2024.100553 · Cited by 7
Das, P., Nanda, S., Panda, G., Dash, S., Ksibi, A., Alsenan, S. A., Bouchelligua, W., & Mallik, S. (2024) · BMC Neurology · doi:10.1186/s12883-024-04001-7 · Cited by 7
Zhang, J., Zhang, Y., Weng, Y., Hosseini, A. A., Wang, B., Dening, T., Fan, W., & Xiao, W. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11347-y · Cited by 13
Paroxysmal Slow-Wave Events Are Uncommon in Parkinson’s Disease
Milikovsky, D. Z., Sharabi, Y., Giladi, N., Mirelman, A., Sosnik, R., Fahoum, F., & Maidan, I. (2023) · Sensors · doi:10.3390/s23020918 · Cited by 4
“In one study, a deep learning model was used to analyze EEG recordings and achieved high accuracy for detecting PD and medication status [21].”
MethodWearable Sensors and Machine Learning Fusion for Parkinson's Disease Assessment
Hammoud, M., Shcherbak, A., Getahun, M. N., Istrakova, O., Shindryaeva, N., Zimniakova, O., Витальевна, Б. Е., Semenov, M., Baldycheva, A. V., & Somov, A. (2024) · IEEE International Instrumentation and Measurement Technology Conference · doi:10.1109/i2mtc60896.2024.10561139 · Cited by 6
“Authors in [4] built a 2D Convolutional Neural Network (CNN) for automated PD diagnosed-based Electroencephalogram (EEG) recordings.”
BackgroundGraph-Based EEG Analysis for Parkinson’s Disease Classification: A Residual Neural Network Approach
Santos, L. D. O., Medeiros, A. G., Rêgo, P. A. L., & Filho, P. P. R. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651047 · Cited by 4
“On the other hand, the methodology proposed by Loh et al. (2021) proves to be computationally expensive, considering the architecture of the proposed CNN.”
MethodResultInfluentialA Brief Review on EEG-Based Diagnosis of Parkinson's Disease Using Deep Learning Models
Ghasemi, M., Boostani, R., & Lak, A. J. (2024) · E-Health and Bioengineering Conference (EHB) · doi:10.1109/ehb64556.2024.10805584 · Cited by 4
NeuroParkNet: A New Neural Network Model for Classification of Parkinson's Disease
Çelik, B., & Akbal, A. (2025) · GAZI UNIVERSITY JOURNAL OF SCIENCE · doi:10.35378/gujs.1602747 · Cited by 4
Afonso, M. M., Edla, D. R., & Reddy, R. R. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108899 · Cited by 3
Quantifying instability in neurological disorders EEG based on phase space DTM function
Cai, T., Zhao, G., Zang, J., Zong, C., Zhang, Z., & Xue, C. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108951 · Cited by 4
Falkowski, P., Oleksiuk, J., Jeznach, K., & Aktan, M. E. (2024) · International Conference on Robotics and Control Engineering (RobCE) · doi:10.1145/3674746.3674793 · Cited by 5
Zebra based optimal deep learning for Parkinson’s disease detection using brain MRI images
Santhosh Kumar, B., Praveen Yadav, P., & Raghavendra Reddy, M. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20404-7 · Cited by 3
Bhongade, A., & Gandhi, T. K. (2024) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc54092.2024.10831322 · Cited by 3
“Because the images of joint Time-Frequency representation (TFR) include more detailed information about the signal, numerous techniques have been used recently to convert per-minute ECG data into TFR images [19], [20], [21].”
Review of Parkinson’s disease detection with deep‑learning machines
Aldujaili, A. A., Rosa-Zurera, M., & Utrilla-Manso, M. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-20466-7 · Cited by 4
“For example, in [72], the Gabor transform is utilized to obtain a 2D time–frequency representation, which is then used as input for a convolutional network structure designed for a classification problem with three classes: healthy persons and PD patients with and without medication.”
Unveiling Parkinson’s Disease Severity Using EEG-Driven Deep CNN Model
Salah, F. B., Echtioui, A., & BenAyed, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-5887-9_6 · Cited by 3
Independent component analysis of oddball EEG recordings to detect Parkinson’s disease
Smrdel, A. (2025) · Scientific Reports · doi:10.1038/s41598-025-07645-8 · Cited by 4
Bunterngchit, C., Moctar, S. M. S., Baniata, L. H., Aslam, S., & Rasool, A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116141 · Cited by 3
Automatic Detection of Parkinson’s Disease using EEG Signals: A Machine Learning Approach
Bhatt, K., Jayanthi, N., & Kumar, M. (2024) · IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) · doi:10.1109/iatmsi60426.2024.10503404 · Cited by 2
“Time-frequency analysis methods were also used to convert the EEG signals into images and applied as input to the DL modules for PD detection [16], [17].”
MethodJayasudha, V., Deepa, N., & Devi, T. M. (2025) · Discover Computing · doi:10.1007/s10791-025-09534-0 · Cited by 3
“Retrogression models like direct [14] with logistic [15] have also been exercised for PD inquiry, which involve modelling among a dependent and an independent variable [16, 17], in extension to classification approaches.”
Nguyen, T., Vo, H., Nguyen, H. A., & Huynh, T. V. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-19694-2_10 · Cited by 2
A Review of EEG-Based Computer-Aided Detection of Brain Disorders Using a Different Strategy
Shanmugam, S., & Radhakrishnan, M. (2023) · Advances in business strategy and competitive advantage book series · doi:10.4018/979-8-3693-1634-4.ch017 · Cited by 2
Metadata
- Authors
- Loh, H. W., Ooi, C. P., Palmer, E., Barua, P. D., Dogan, S., Tuncer, T., Baygin, M., & Acharya, U. R.
- Affiliations
- Singapore University of Social Sciences (SG)
- UNSW Sydney (AU)
- University of Technology Sydney (AU)
- Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig 23119, Turkey
- Department of Computer Engineering, Faculty of Engineering, Ardahan University, Ardahan 75000, Turkey
- Asia University (TW)
- Corresponding author
- Acharya, U. Rajendra
- ORCID
- Venue
- Electronics
- Publisher
- MDPI AG
- Published
- 2021-07-20
- Volume
- 10
- Issue
- 14
- Pages
- 1740
- ISSN
- 2079-9292 (ISSN-L)
- OpenAlex
- W3185004711
- Cited by
- 144
- References
- 57
- Citations by year
- 2026: 15 · 2025: 43 · 2024: 40 · 2023: 28 · 2022: 13 · 2021: 5
- FWCI
- 11.30
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Electronics (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- DSpace - FIRAT (Fırat University) (submittedVersion, cc-by-nc-nd)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Keywords
- Parkinson's disease, EEG, Gabor transform, spectrogram, 2D convolutional neural network, automated diagnosis, computer-aided diagnosis, biomarkers
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.