SchizoNET: a robust and accurate Margenau–Hill time-frequency distribution based deep neural network model for schizophrenia detection using EEG signals

Physiological Measurement, Год журнала: 2023, Номер 44(3), С. 035005 - 035005

Опубликована: Фев. 14, 2023

Objective.Schizophrenia (SZ) is a severe chronic illness characterized by delusions, cognitive dysfunctions, and hallucinations that impact feelings, behaviour, thinking. Timely detection treatment of SZ are necessary to avoid long-term consequences. Electroencephalogram (EEG) signals one form biomarker can reveal hidden changes in the brain during SZ. However, EEG non-stationary nature with low amplitude. Therefore, extracting information from challenging.Approach.The time-frequency domain crucial for automatic this paper presents SchizoNET model combining Margenau-Hill distribution (MH-TFD) convolutional neural network (CNN). The instantaneous captured using MH-TFD. amplitude converted two-dimensional plots fed developed CNN model.Results.The three different validation techniques, including holdout, five-fold cross-validation, ten-fold cross-validation techniques separate public datasets (Dataset 1, 2, 3). proposed achieved an accuracy 97.4%, 99.74%, 96.35% on Dataset 1 (adolescents: 45 39 HC subjects), 2 (adults: 14 3 49 32 respectively. We have also evaluated six performance parameters area under curve evaluate our model.Significance.The robust, effective, accurate, as it performed better than state-of-the-art techniques. To best knowledge, first work explore publicly available automated Our help neurologists detect various scenarios.

Язык: Английский

---

A comparative analysis of meta-heuristic optimization algorithms for feature selection on ML-based classification of heart-related diseases

The Journal of Supercomputing, Год журнала: 2023, Номер 79(11), С. 11797 - 11826

Опубликована: Март 3, 2023

Язык: Английский

---

Unraveling the pathophysiology of schizophrenia: insights from structural magnetic resonance imaging studies

Frontiers in Psychiatry, Год журнала: 2023, Номер 14

Опубликована: Май 19, 2023

Background Schizophrenia affects about 1% of the global population. In addition to complex etiology, linking this illness genetic, environmental, and neurobiological factors, dynamic experiences associated with disease, such as delusions, hallucinations, disorganized thinking, abnormal behaviors, limit neurological consensuses regarding mechanisms underlying disease. Methods study, we recruited 72 patients schizophrenia 74 healthy individuals matched by age sex investigate structural brain changes that may serve prognostic biomarkers, indicating evidence neural dysfunction subsequent cognitive behavioral deficits. We used voxel-based morphometry (VBM) determine these in three tissue structures: gray matter (GM), white (WM), cerebrospinal fluid (CSF). For both image processing statistical analysis, parametric mapping (SPM). Results Our results show exhibited a significant volume reduction GM WM. particular, reductions were more evident frontal, temporal, limbic, parietal lobe, similarly WM predominantly limbic lobe. addition, demonstrated increase CSF left third lateral ventricle regions. Conclusion This VBM study supports existing research showing is alterations structure, including matter, volume. These findings provide insights into neurobiology inform development effective diagnostic therapeutic approaches.

Язык: Английский

---

A systematic review of EEG based automated schizophrenia classification through machine learning and deep learning

Frontiers in Human Neuroscience, Год журнала: 2024, Номер 18

Опубликована: Фев. 14, 2024

The electroencephalogram (EEG) serves as an essential tool in exploring brain activity and holds particular importance the field of mental health research. This review paper examines application artificial intelligence (AI), encompassing machine learning (ML) deep (DL), for classifying schizophrenia (SCZ) through EEG. It includes a thorough literature that addresses difficulties, methodologies, discoveries this field. ML approaches utilize conventional models like Support Vector Machines Decision Trees, which are interpretable effective with smaller data sets. In contrast, DL techniques, use neural networks such convolutional (CNNs) long short-term memory (LSTMs), more adaptable to intricate EEG patterns but require significant computational power. Both face challenges concerning quality ethical issues. underscores integrating various techniques enhance diagnosis highlights AI’s potential role process. also acknowledges necessity collaborative ethically informed automated classification SCZ using AI.

Язык: Английский

---

Advances of AI in image-based computer-aided diagnosis: A review

Array, Год журнала: 2024, Номер 23, С. 100357 - 100357

Опубликована: Июль 6, 2024

Over the past two decades, computer-aided detection and diagnosis have emerged as a field of research. The primary goal is to enhance diagnostic treatment procedures for radiologists clinicians in medical image analysis. With help big data advanced artificial intelligence (AI) technologies, such machine learning deep algorithms, healthcare system can be made more convenient, active, efficient, personalized. this literature survey was present thorough overview most important developments related (CAD) systems imaging. This considerable importance researchers professionals both computer sciences. Several reviews on specific facets CAD imaging been published. Nevertheless, main emphasis study cover complete range capabilities review article introduces background concepts used typical by outlining comparing several methods frequently employed recent studies. also presents comprehensive well-structured medicine, drawing meticulous selection relevant publications. Moreover, it describes process handling images state-of-the-art AI-based technologies imaging, along with future directions CAD. indicates that algorithms are effective method diagnose detect diseases.

Язык: Английский

---