1
|
Bomatter P, Paillard J, Garces P, Hipp J, Engemann DA. Machine learning of brain-specific biomarkers from EEG. EBioMedicine 2024; 106:105259. [PMID: 39106531 DOI: 10.1016/j.ebiom.2024.105259] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Revised: 07/05/2024] [Accepted: 07/11/2024] [Indexed: 08/09/2024] Open
Abstract
BACKGROUND Electroencephalography (EEG) has a long history as a clinical tool to study brain function, and its potential to derive biomarkers for various applications is far from exhausted. Machine learning (ML) can guide future innovation by harnessing the wealth of complex EEG signals to isolate relevant brain activity. Yet, ML studies in EEG tend to ignore physiological artefacts, which may cause problems for deriving biomarkers specific to the central nervous system (CNS). METHODS We present a framework for conceptualising machine learning from CNS versus peripheral signals measured with EEG. A signal representation based on Morlet wavelets allowed us to define traditional brain activity features (e.g. log power) and alternative inputs used by state-of-the-art ML approaches based on covariance matrices. Using more than 2600 EEG recordings from large public databases (TUAB, TDBRAIN), we studied the impact of peripheral signals and artefact removal techniques on ML models in age and sex prediction analyses. FINDINGS Across benchmarks, basic artefact rejection improved model performance, whereas further removal of peripheral signals using ICA decreased performance. Our analyses revealed that peripheral signals enable age and sex prediction. However, they explained only a fraction of the performance provided by brain signals. INTERPRETATION We show that brain signals and body signals, both present in the EEG, allow for prediction of personal characteristics. While these results may depend on specific applications, our work suggests that great care is needed to separate these signals when the goal is to develop CNS-specific biomarkers using ML. FUNDING All authors have been working for F. Hoffmann-La Roche Ltd.
Collapse
Affiliation(s)
- Philipp Bomatter
- Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Joseph Paillard
- Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Pilar Garces
- Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Jörg Hipp
- Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Denis-Alexander Engemann
- Roche Pharma Research and Early Development, Neuroscience and Rare Diseases, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland.
| |
Collapse
|
2
|
Pascarella A, Manzo L, Ferlazzo E. Modern neurophysiological techniques indexing normal or abnormal brain aging. Seizure 2024:S1059-1311(24)00194-8. [PMID: 38972778 DOI: 10.1016/j.seizure.2024.07.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2024] [Accepted: 07/01/2024] [Indexed: 07/09/2024] Open
Abstract
Brain aging is associated with a decline in cognitive performance, motor function and sensory perception, even in the absence of neurodegeneration. The underlying pathophysiological mechanisms remain incompletely understood, though alterations in neurogenesis, neuronal senescence and synaptic plasticity are implicated. Recent years have seen advancements in neurophysiological techniques such as electroencephalography (EEG), magnetoencephalography (MEG), event-related potentials (ERP) and transcranial magnetic stimulation (TMS), offering insights into physiological and pathological brain aging. These methods provide real-time information on brain activity, connectivity and network dynamics. Integration of Artificial Intelligence (AI) techniques promise as a tool enhancing the diagnosis and prognosis of age-related cognitive decline. Our review highlights recent advances in these electrophysiological techniques (focusing on EEG, ERP, TMS and TMS-EEG methodologies) and their application in physiological and pathological brain aging. Physiological aging is characterized by changes in EEG spectral power and connectivity, ERP and TMS parameters, indicating alterations in neural activity and network function. Pathological aging, such as in Alzheimer's disease, is associated with further disruptions in EEG rhythms, ERP components and TMS measures, reflecting underlying neurodegenerative processes. Machine learning approaches show promise in classifying cognitive impairment and predicting disease progression. Standardization of neurophysiological methods and integration with other modalities are crucial for a comprehensive understanding of brain aging and neurodegenerative disorders. Advanced network analysis techniques and AI methods hold potential for enhancing diagnostic accuracy and deepening insights into age-related brain changes.
Collapse
Affiliation(s)
- Angelo Pascarella
- Department of Medical and Surgical Sciences, Magna Græcia University of Catanzaro, Italy; Regional Epilepsy Centre, Great Metropolitan "Bianchi-Melacrino-Morelli Hospital", Reggio Calabria, Italy.
| | - Lucia Manzo
- Regional Epilepsy Centre, Great Metropolitan "Bianchi-Melacrino-Morelli Hospital", Reggio Calabria, Italy
| | - Edoardo Ferlazzo
- Department of Medical and Surgical Sciences, Magna Græcia University of Catanzaro, Italy; Regional Epilepsy Centre, Great Metropolitan "Bianchi-Melacrino-Morelli Hospital", Reggio Calabria, Italy
| |
Collapse
|
3
|
Gaeta AM, Quijada-López M, Barbé F, Vaca R, Pujol M, Minguez O, Sánchez-de-la-Torre M, Muñoz-Barrutia A, Piñol-Ripoll G. Predicting Alzheimer's disease CSF core biomarkers: a multimodal Machine Learning approach. Front Aging Neurosci 2024; 16:1369545. [PMID: 38988328 PMCID: PMC11233742 DOI: 10.3389/fnagi.2024.1369545] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2024] [Accepted: 06/04/2024] [Indexed: 07/12/2024] Open
Abstract
Introduction Alzheimer's disease (AD) is a progressive neurodegenerative disorder. Current core cerebrospinal fluid (CSF) AD biomarkers, widely employed for diagnosis, require a lumbar puncture to be performed, making them impractical as screening tools. Considering the role of sleep disturbances in AD, recent research suggests quantitative sleep electroencephalography features as potential non-invasive biomarkers of AD pathology. However, quantitative analysis of comprehensive polysomnography (PSG) signals remains relatively understudied. PSG is a non-invasive test enabling qualitative and quantitative analysis of a wide range of parameters, offering additional insights alongside other biomarkers. Machine Learning (ML) gained interest for its ability to discern intricate patterns within complex datasets, offering promise in AD neuropathology detection. Therefore, this study aims to evaluate the effectiveness of a multimodal ML approach in predicting core AD CSF biomarkers. Methods Mild-moderate AD patients were prospectively recruited for PSG, followed by testing of CSF and blood samples for biomarkers. PSG signals underwent preprocessing to extract non-linear, time domain and frequency domain statistics quantitative features. Multiple ML algorithms were trained using four subsets of input features: clinical variables (CLINVAR), conventional PSG parameters (SLEEPVAR), quantitative PSG signal features (PSGVAR) and a combination of all subsets (ALL). Cross-validation techniques were employed to evaluate model performance and ensure generalizability. Regression models were developed to determine the most effective variable combinations for explaining variance in the biomarkers. Results On 49 subjects, Gradient Boosting Regressors achieved the best results in estimating biomarkers levels, using different loss functions for each biomarker: least absolute deviation (LAD) for the Aβ42, least squares (LS) for p-tau and Huber for t-tau. The ALL subset demonstrated the lowest training errors for all three biomarkers, albeit with varying test performance. Specifically, the SLEEPVAR subset yielded the best test performance in predicting Aβ42, while the ALL subset most accurately predicted p-tau and t-tau due to the lowest test errors. Conclusions Multimodal ML can help predict the outcome of CSF biomarkers in early AD by utilizing non-invasive and economically feasible variables. The integration of computational models into medical practice offers a promising tool for the screening of patients at risk of AD, potentially guiding clinical decisions.
Collapse
Affiliation(s)
- Anna Michela Gaeta
- Servicio de Neumología, Hospital Universitario Severo Ochoa, Leganés, Spain
| | - María Quijada-López
- Departamento de Bioingeniería, Universidad Carlos III de Madrid, Leganés, Spain
| | - Ferran Barbé
- Group of Translational Research in Respiratory Medicine, Hospital Universitari Arnau de Vilanova and Santa Maria, Institut de Recerca Biomedica de Lleida (IRBLleida), Lleida, Spain
- Centro de Investigación Biomédica en Red de Enfermedades Respiratorias (CIBERES), Madrid, Spain
| | - Rafaela Vaca
- Group of Translational Research in Respiratory Medicine, Hospital Universitari Arnau de Vilanova and Santa Maria, Institut de Recerca Biomedica de Lleida (IRBLleida), Lleida, Spain
| | - Montse Pujol
- Unitat Trastorns Cognitius, Clinical Neuroscience Research, Institut de Recerca Biomedica de Lleida (IRBLleida), Hospital Universitari Santa Maria, Lleida, Spain
| | - Olga Minguez
- Group of Translational Research in Respiratory Medicine, Hospital Universitari Arnau de Vilanova and Santa Maria, Institut de Recerca Biomedica de Lleida (IRBLleida), Lleida, Spain
| | - Manuel Sánchez-de-la-Torre
- Centro de Investigación Biomédica en Red de Enfermedades Respiratorias (CIBERES), Madrid, Spain
- Group of Precision Medicine in Chronic Diseases, Hospital Nacional de Parapléjicos, IDISCAM, Department of Nursing, Physiotherapy and Occupational Therapy, Faculty of Physiotherapy and Nursing, University of Castilla-La Mancha, Toledo, Spain
| | - Arrate Muñoz-Barrutia
- Departamento de Bioingeniería, Universidad Carlos III de Madrid, Leganés, Spain
- Departamento de Bioingegneria, Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain
| | - Gerard Piñol-Ripoll
- Unitat Trastorns Cognitius, Clinical Neuroscience Research, Institut de Recerca Biomedica de Lleida (IRBLleida), Hospital Universitari Santa Maria, Lleida, Spain
| |
Collapse
|
4
|
Maniam S, Maniam S. Screening Techniques for Drug Discovery in Alzheimer's Disease. ACS OMEGA 2024; 9:6059-6073. [PMID: 38371787 PMCID: PMC10870277 DOI: 10.1021/acsomega.3c07046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/14/2023] [Revised: 12/22/2023] [Accepted: 12/25/2023] [Indexed: 02/20/2024]
Abstract
Alzheimer's disease (AD) is a neurodegenerative disorder characterized by progressive and irreversible impairment of memory and other cognitive functions of the aging brain. Pathways such as amyloid beta neurotoxicity, tau pathogenesis and neuroinflammatory have been used to understand AD, despite not knowing the definite molecular mechanism which causes this progressive disease. This review attempts to summarize the small molecules that target these pathways using various techniques involving high-throughput screening, molecular modeling, custom bioassays, and spectroscopic detection tools. Novel and evolving screening methods developed to advance drug discovery initiatives in AD research are also highlighted.
Collapse
Affiliation(s)
- Sandra Maniam
- Department
of Human Anatomy, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, 43400 UPM Serdang, Selangor Darul Ehsan, Malaysia
| | - Subashani Maniam
- School
of Science, STEM College, RMIT University, Melbourne, Victoria 3001, Australia
| |
Collapse
|
5
|
Kim NN, Tan C, Ma E, Kutlu S, Carrazana E, Vimala V, Viereck J, Liow K. Abnormal Temporal Slowing on EEG Findings in Preclinical Alzheimer's Disease Patients With the ApoE4 Allele: A Pilot Study. Cureus 2023; 15:e47852. [PMID: 38021568 PMCID: PMC10679961 DOI: 10.7759/cureus.47852] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/28/2023] [Indexed: 12/01/2023] Open
Abstract
INTRODUCTION Currently, there are limited accessible and cost-effective biomarkers for preclinical Alzheimer's disease (AD) patients. However, the apolipoprotein E (ApoE) polymorphic alleles can predict if someone is at high (e4), neutral (e3), or low (e2) genetic risk for developing AD. This study analyzed electroencephalogram (EEG) reports from individuals with various ApoE genotypes, aiming to identify EEG changes and patterns that could potentially serve as predictive markers for preclinical AD progression. METHODS Participants aged 64-78 were selected from the patient database at an outpatient neurology clinic. Genotype studies were performed to determine ApoE status, followed by EEG analysis to identify any apparent trends. A case-control design was used, categorizing participants into cases (e2e3, e2e4, e3e4, e4e4) and controls (e3e3). EEG recordings were compared between the groups to identify potential differences in EEG characteristics, including abnormal temporal slowing, frequency, and ApoE genotype association. RESULTS Among 43 participants, 49% demonstrated evidence of abnormal temporal slowing on EEG. Of these, 48% displayed focal left temporal slowing, and 52% displayed bilateral temporal slowing. The right-sided temporal slowing was not observed. Among participants with abnormal slowing, 95% exhibited theta frequency (4-8 Hz) slowing, while only 4.8% displayed delta frequency (0-4 Hz) slowing. Among participants with the ApoE4 allele, 61.5% demonstrated evidence of abnormal slowing, compared to 43.3% without it. Furthermore, the presence of an ApoE4 allele was associated with a significantly higher proportion of males (54%) compared to those without it (13%) (p=0.009). CONCLUSIONS Although we did not find a statistically significant difference in temporal EEG slowing among different ApoE genotypes, our findings suggest a potential association between temporal slowing on EEG and the presence of an ApoE4 allele in individuals with preclinical AD. These observations highlight the need for further exploration into the potential influence of the ApoE4 allele on EEG findings and the utility of EEG as a complementary diagnostic tool for AD. Longitudinal studies with large sample sizes are needed to establish the precise relationship between EEG patterns, ApoE genotypes, and AD progression.
Collapse
Affiliation(s)
- Nathan N Kim
- Neurology, John A. Burns School of Medicine (JABSOM), University of Hawaii, Honolulu, USA
| | - Charissa Tan
- Neurology, John A. Burns School of Medicine (JABSOM), University of Hawaii, Honolulu, USA
| | - Enze Ma
- Neurology, John A. Burns School of Medicine (JABSOM), University of Hawaii, Honolulu, USA
| | - Selin Kutlu
- Neurology, John A. Burns School of Medicine (JABSOM), University of Hawaii, Honolulu, USA
| | - Enrique Carrazana
- Brain Research, Innovation, & Translation Laboratory, Comprehensive Epilepsy Center & Video-EEG Epilepsy Monitoring Unit, Hawaii Pacific Neuroscience, Honolulu, USA
| | | | - Jason Viereck
- Brain Research, Innovation, & Translation Laboratory, Hawaii Pacific Neuroscience, Honolulu, USA
| | - Kore Liow
- Neurology, Hawaii Pacific Neuroscience, Honolulu, USA
| |
Collapse
|
6
|
Mohamed AA, Marques O. Diagnostic Efficacy and Clinical Relevance of Artificial Intelligence in Detecting Cognitive Decline. Cureus 2023; 15:e47004. [PMID: 37965412 PMCID: PMC10641267 DOI: 10.7759/cureus.47004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/13/2023] [Indexed: 11/16/2023] Open
Abstract
Cognitive impairment is an age-associated disorder of increasing prevalence as the aging population continues to grow. Classified based on the level of cognitive decline, memory, function, and capacity to conduct activities of daily living, cognitive impairment ranges from mild cognitive impairment to dementia. When considering the insidious nature of the etiologies responsible for varying degrees of cognitive impairment, early diagnosis may provide a clinical benefit through the facilitation of early treatment. Typical diagnosis relies heavily on evaluation in a primary care setting. However, there is evidence that other diagnostic tools may aid in an earlier diagnosis of the different underlying pathologies responsible for cognitive impairment. Artificial intelligence represents a new intersecting field with healthcare that may aid in the early detection of neurodegenerative disorders. When assessing the role of AI in detecting cognitive decline, it is important to consider both the diagnostic efficacy of AI algorithms and the clinical relevance and impact of early interventions as a result of early detection. Thus, this review highlights promising investigations and developments in the space of artificial intelligence and healthcare and their potential to impact patient outcomes.
Collapse
Affiliation(s)
- Ali A Mohamed
- Neurological Surgery, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, USA
- Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA
| | - Oge Marques
- Biomedical Sciences, Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, USA
- Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA
| |
Collapse
|
7
|
Kleiman MJ, Ariko T, Galvin JE. Hierarchical Two-Stage Cost-Sensitive Clinical Decision Support System for Screening Prodromal Alzheimer's Disease and Related Dementias. J Alzheimers Dis 2023; 91:895-909. [PMID: 36502329 PMCID: PMC10515190 DOI: 10.3233/jad-220891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
BACKGROUND The detection of subtle cognitive impairment in a clinical setting is difficult. Because time is a key factor in small clinics and research sites, the brief cognitive assessments that are relied upon often misclassify patients with very mild impairment as normal. OBJECTIVE In this study, we seek to identify a parsimonious screening tool in one stage, followed by additional assessments in an optional second stage if additional specificity is desired, tested using a machine learning algorithm capable of being integrated into a clinical decision support system. METHODS The best primary stage incorporated measures of short-term memory, executive and visuospatial functioning, and self-reported memory and daily living questions, with a total time of 5 minutes. The best secondary stage incorporated a measure of neurobiology as well as additional cognitive assessment and brief informant report questionnaires, totaling 30 minutes including delayed recall. Combined performance was evaluated using 25 sets of models, trained on 1,181 ADNI participants and tested on 127 patients from a memory clinic. RESULTS The 5-minute primary stage was highly sensitive (96.5%) but lacked specificity (34.1%), with an AUC of 87.5% and diagnostic odds ratio of 14.3. The optional secondary stage increased specificity to 58.6%, resulting in an overall AUC of 89.7% using the best model combination of logistic regression and gradient-boosted machine. CONCLUSION The primary stage is brief and effective at screening, with the optional two-stage technique further increasing specificity. The hierarchical two-stage technique exhibited similar accuracy but with reduced costs compared to the more common single-stage paradigm.
Collapse
Affiliation(s)
- Michael J. Kleiman
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| | - Taylor Ariko
- Department of Neurology, Evelyn F. McKnight Brain Institute, University of Miami Miller School of Medicine, Miami, FL, USA
| | - James E. Galvin
- Department of Neurology, Comprehensive Center for Brain Health, University of Miami Miller School of Medicine, Boca Raton, FL, USA
| |
Collapse
|
8
|
Hu Z, Wang X, Meng L, Liu W, Wu F, Meng X. Detection of Association Features Based on Gene Eigenvalues and MRI Imaging Using Genetic Weighted Random Forest. Genes (Basel) 2022; 13:2344. [PMID: 36553611 PMCID: PMC9777775 DOI: 10.3390/genes13122344] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Revised: 12/07/2022] [Accepted: 12/07/2022] [Indexed: 12/14/2022] Open
Abstract
In the studies of Alzheimer's disease (AD), jointly analyzing imaging data and genetic data provides an effective method to explore the potential biomarkers of AD. AD can be separated into healthy controls (HC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI) and AD. In the meantime, identifying the important biomarkers of AD progression, and analyzing these biomarkers in AD provide valuable insights into understanding the mechanism of AD. In this paper, we present a novel data fusion method and a genetic weighted random forest method to mine important features. Specifically, we amplify the difference among AD, LMCI, EMCI and HC by introducing eigenvalues calculated from the gene p-value matrix for feature fusion. Furthermore, we construct the genetic weighted random forest using the resulting fused features. Genetic evolution is used to increase the diversity among decision trees and the decision trees generated are weighted by weights. After training, the genetic weighted random forest is analyzed further to detect the significant fused features. The validation experiments highlight the performance and generalization of our proposed model. We analyze the biological significance of the results and identify some significant genes (CSMD1, CDH13, PTPRD, MACROD2 and WWOX). Furthermore, the calcium signaling pathway, arrhythmogenic right ventricular cardiomyopathy and the glutamatergic synapse pathway were identified. The investigational findings demonstrate that our proposed model presents an accurate and efficient approach to identifying significant biomarkers in AD.
Collapse
Affiliation(s)
- Zhixi Hu
- School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213032, China
| | - Xuanyan Wang
- School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213032, China
| | - Li Meng
- School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UK
| | - Wenjie Liu
- School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213032, China
| | - Feng Wu
- School of Electrical & Information Engineering, Changzhou Institute of Technology, Changzhou 213032, China
| | - Xianglian Meng
- School of Computer Information and Engineering, Changzhou Institute of Technology, Changzhou 213032, China
| |
Collapse
|
9
|
Battineni G, Chintalapudi N, Hossain MA, Losco G, Ruocco C, Sagaro GG, Traini E, Nittari G, Amenta F. Artificial Intelligence Models in the Diagnosis of Adult-Onset Dementia Disorders: A Review. Bioengineering (Basel) 2022; 9:370. [PMID: 36004895 PMCID: PMC9405227 DOI: 10.3390/bioengineering9080370] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Revised: 07/25/2022] [Accepted: 08/02/2022] [Indexed: 11/16/2022] Open
Abstract
Background: The progressive aging of populations, primarily in the industrialized western world, is accompanied by the increased incidence of several non-transmittable diseases, including neurodegenerative diseases and adult-onset dementia disorders. To stimulate adequate interventions, including treatment and preventive measures, an early, accurate diagnosis is necessary. Conventional magnetic resonance imaging (MRI) represents a technique quite common for the diagnosis of neurological disorders. Increasing evidence indicates that the association of artificial intelligence (AI) approaches with MRI is particularly useful for improving the diagnostic accuracy of different dementia types. Objectives: In this work, we have systematically reviewed the characteristics of AI algorithms in the early detection of adult-onset dementia disorders, and also discussed its performance metrics. Methods: A document search was conducted with three databases, namely PubMed (Medline), Web of Science, and Scopus. The search was limited to the articles published after 2006 and in English only. The screening of the articles was performed using quality criteria based on the Newcastle-Ottawa Scale (NOS) rating. Only papers with an NOS score ≥ 7 were considered for further review. Results: The document search produced a count of 1876 articles and, because of duplication, 1195 papers were not considered. Multiple screenings were performed to assess quality criteria, which yielded 29 studies. All the selected articles were further grouped based on different attributes, including study type, type of AI model used in the identification of dementia, performance metrics, and data type. Conclusions: The most common adult-onset dementia disorders occurring were Alzheimer's disease and vascular dementia. AI techniques associated with MRI resulted in increased diagnostic accuracy ranging from 73.3% to 99%. These findings suggest that AI should be associated with conventional MRI techniques to obtain a precise and early diagnosis of dementia disorders occurring in old age.
Collapse
Affiliation(s)
- Gopi Battineni
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Nalini Chintalapudi
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Mohammad Amran Hossain
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Giuseppe Losco
- School of Architecture and Design, University of Camerino, 63100 Ascoli Piceno, Italy
| | - Ciro Ruocco
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Getu Gamo Sagaro
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Enea Traini
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Giulio Nittari
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| | - Francesco Amenta
- Clinical Research Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy
| |
Collapse
|
10
|
Saravanakumar S, Saravanan T. An effective convolutional neural network-based stacked long short-term memory approach for automated Alzheimer’s disease prediction. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022. [DOI: 10.3233/jifs-212797] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
In today’s world, Alzheimer’s Disease (AD) is one of the prevalent neurological diseases where early disease prediction can significantly enhance the compatibility of patient treatment. Nevertheless, accurate diagnosis and optimal feature selection play a vital challenge in AD detection. Most of the existing diagnosis systems failed to attain superior prediction accuracy and precision rate. In order to mitigate these constraints, a new efficient Convolutional Neural Network-based Stacked Long Short-Term Memory (CNN-SLSTM) methodology has been proposed in this paper. The key objective of the proposed model is to examine the brain’s condition and evaluate the changes that occur throughout the interracial period. The proposed model includes multi-feature learning and categorization in which the raw Electroencephalography (EEG) data will be passed via the feature extractor to decrease the computing complexity and execution time. Afterward, the SLSTM network is constructed with completely linked layer and activation layers to record the temporal relationship between features and the next stage of AD. The proposed CNN-SLSTM model can be trained using real-time EEG sensor data. The performance results clearly apparent that the proposed model can efficiently predict the AD with superior accuracy of 98.67% and precision of 98.86% when compared with existing state-of-the-art techniques.
Collapse
Affiliation(s)
- S. Saravanakumar
- Department of Computer Science and Engineering, Adithya Institute of Technology, Coimbatore, India
| | - T. Saravanan
- Department of Computer Science and Engineering, St Martins Engineering college Telangana, India
| |
Collapse
|
11
|
Wu YQ, Wang YN, Zhang LJ, Liu LQ, Pan YC, Su T, Liao XL, Shu HY, Kang M, Ying P, Xu SH, Shao Y. Regional Homogeneity in Patients With Mild Cognitive Impairment: A Resting-State Functional Magnetic Resonance Imaging Study. Front Aging Neurosci 2022; 14:877281. [PMID: 35493938 PMCID: PMC9050296 DOI: 10.3389/fnagi.2022.877281] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Accepted: 03/22/2022] [Indexed: 12/31/2022] Open
Abstract
Objective To analyze the potential changes in brain neural networks in resting state functional magnetic resonance imaging (rs-fMRI) scans by regional homogeneity (ReHo) in patients with mild cognitive impairment (MCI). Methods We recruited and selected 24 volunteers, including 12 patients (6 men and 6 women) with MCI and 12 healthy controls matched by age, sex, and lifestyle. All subjects were examined with rs-fMRI to evaluate changes in neural network connectivity, and the data were analyzed by ReHo method. Correlation analysis was used to investigate the relationship between ReHo values and clinical features in different brain regions of MCI patients. The severity of MCI was determined by the Mini-Mental State Examination (MMSE) scale. Results The signals of the right cerebellum areas 4 and 5, left superior temporal, right superior temporal, left fusiform, and left orbital middle frontal gyri in the patient group were significantly higher than those in the normal group (P < 0.01 by t-test of paired samples). The signal intensity of the right inferior temporal and left inferior temporal gyri was significantly lower than that of the normal group (P < 0.01). The ReHO value for the left inferior temporal gyrus correlated negatively with disease duration, and the value for the right inferior temporal gyrus correlated positively with MMSE scores. Conclusion Mild cognitive impairment in patients with pre- Alzheimer's disease may be related to the excitation and inhibition of neural networks in these regions. This may have a certain guiding significance for clinical diagnosis.
Collapse
Affiliation(s)
- Yu-Qian Wu
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yi-Ning Wang
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Li-Juan Zhang
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Li-Qi Liu
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yi-Cong Pan
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Ting Su
- Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, United States
| | - Xu-Lin Liao
- Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Sha Tin, Hong Kong SAR, China
| | - Hui-Ye Shu
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Min Kang
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Ping Ying
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - San-Hua Xu
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yi Shao
- Department of Ophthalmology and Neurology, The First Affiliated Hospital of Nanchang University, Nanchang, China,*Correspondence: Yi Shao,
| |
Collapse
|
12
|
Automated diagnosis of depression from EEG signals using traditional and deep learning approaches: A comparative analysis. Biocybern Biomed Eng 2022. [DOI: 10.1016/j.bbe.2021.12.005] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
|
13
|
Battineni G, Hossain MA, Chintalapudi N, Traini E, Dhulipalla VR, Ramasamy M, Amenta F. Improved Alzheimer's Disease Detection by MRI Using Multimodal Machine Learning Algorithms. Diagnostics (Basel) 2021; 11:diagnostics11112103. [PMID: 34829450 PMCID: PMC8623867 DOI: 10.3390/diagnostics11112103] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2021] [Revised: 11/10/2021] [Accepted: 11/11/2021] [Indexed: 11/16/2022] Open
Abstract
Adult-onset dementia disorders represent a challenge for modern medicine. Alzheimer's disease (AD) represents the most diffused form of adult-onset dementias. For half a century, the diagnosis of AD was based on clinical and exclusion criteria, with an accuracy of 85%, which did not allow for a definitive diagnosis, which could only be confirmed by post-mortem evaluation. Machine learning research applied to Magnetic Resonance Imaging (MRI) techniques can contribute to a faster diagnosis of AD and may contribute to predicting the evolution of the disease. It was also possible to predict individual dementia of older adults with AD screening data and ML classifiers. To predict the AD subject status, the MRI demographic information and pre-existing conditions of the patient can help to enhance the classifier performance. In this work, we proposed a framework based on supervised learning classifiers in the dementia subject categorization as either AD or non-AD based on longitudinal brain MRI features. Six different supervised classifiers are incorporated for the classification of AD subjects and results mentioned that the gradient boosting algorithm outperforms other models with 97.58% of accuracy.
Collapse
Affiliation(s)
- Gopi Battineni
- Telemedicine and Telepharmacy Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy; (M.A.H.); (N.C.); (E.T.); (F.A.)
- Correspondence: ; Tel.: +39-3331728206
| | - Mohmmad Amran Hossain
- Telemedicine and Telepharmacy Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy; (M.A.H.); (N.C.); (E.T.); (F.A.)
| | - Nalini Chintalapudi
- Telemedicine and Telepharmacy Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy; (M.A.H.); (N.C.); (E.T.); (F.A.)
| | - Enea Traini
- Telemedicine and Telepharmacy Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy; (M.A.H.); (N.C.); (E.T.); (F.A.)
| | - Venkata Rao Dhulipalla
- The Research Centre of the ECE Department, V.R. Siddhartha Engineering College, Vijayawada 521002, Andhra Pradesh, India; (V.R.D.); (M.R.)
| | - Mariappan Ramasamy
- The Research Centre of the ECE Department, V.R. Siddhartha Engineering College, Vijayawada 521002, Andhra Pradesh, India; (V.R.D.); (M.R.)
| | - Francesco Amenta
- Telemedicine and Telepharmacy Centre, School of Medicinal and Health Products Sciences, University of Camerino, 62032 Camerino, Italy; (M.A.H.); (N.C.); (E.T.); (F.A.)
| |
Collapse
|
14
|
Application of Machine Learning to Electroencephalography for the Diagnosis of Primary Progressive Aphasia: A Pilot Study. Brain Sci 2021; 11:brainsci11101262. [PMID: 34679327 PMCID: PMC8534262 DOI: 10.3390/brainsci11101262] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2021] [Revised: 08/22/2021] [Accepted: 09/23/2021] [Indexed: 11/17/2022] Open
Abstract
Background. Primary progressive aphasia (PPA) is a neurodegenerative syndrome in which diagnosis is usually challenging. Biomarkers are needed for diagnosis and monitoring. In this study, we aimed to evaluate Electroencephalography (EEG) as a biomarker for the diagnosis of PPA. Methods. We conducted a cross-sectional study with 40 PPA patients categorized as non-fluent, semantic, and logopenic variants, and 20 controls. Resting-state EEG with 32 channels was acquired and preprocessed using several procedures (quantitative EEG, wavelet transformation, autoencoders, and graph theory analysis). Seven machine learning algorithms were evaluated (Decision Tree, Elastic Net, Support Vector Machines, Random Forest, K-Nearest Neighbors, Gaussian Naive Bayes, and Multinomial Naive Bayes). Results. Diagnostic capacity to distinguish between PPA and controls was high (accuracy 75%, F1-score 83% for kNN algorithm). The most important features in the classification were derived from network analysis based on graph theory. Conversely, discrimination between PPA variants was lower (Accuracy 58% and F1-score 60% for kNN). Conclusions. The application of ML to resting-state EEG may have a role in the diagnosis of PPA, especially in the differentiation from controls. Future studies with high-density EEG should explore the capacity to distinguish between PPA variants.
Collapse
|
15
|
Öhman F, Hassenstab J, Berron D, Schöll M, Papp KV. Current advances in digital cognitive assessment for preclinical Alzheimer's disease. ALZHEIMER'S & DEMENTIA (AMSTERDAM, NETHERLANDS) 2021; 13:e12217. [PMID: 34295959 PMCID: PMC8290833 DOI: 10.1002/dad2.12217] [Citation(s) in RCA: 59] [Impact Index Per Article: 19.7] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2021] [Revised: 05/30/2021] [Accepted: 06/04/2021] [Indexed: 12/24/2022]
Abstract
There is a pressing need to capture and track subtle cognitive change at the preclinical stage of Alzheimer's disease (AD) rapidly, cost-effectively, and with high sensitivity. Concurrently, the landscape of digital cognitive assessment is rapidly evolving as technology advances, older adult tech-adoption increases, and external events (i.e., COVID-19) necessitate remote digital assessment. Here, we provide a snapshot review of the current state of digital cognitive assessment for preclinical AD including different device platforms/assessment approaches, levels of validation, and implementation challenges. We focus on articles, grants, and recent conference proceedings specifically querying the relationship between digital cognitive assessments and established biomarkers for preclinical AD (e.g., amyloid beta and tau) in clinically normal (CN) individuals. Several digital assessments were identified across platforms (e.g., digital pens, smartphones). Digital assessments varied by intended setting (e.g., remote vs. in-clinic), level of supervision (e.g., self vs. supervised), and device origin (personal vs. study-provided). At least 11 publications characterize digital cognitive assessment against AD biomarkers among CN. First available data demonstrate promising validity of this approach against both conventional assessment methods (moderate to large effect sizes) and relevant biomarkers (predominantly weak to moderate effect sizes). We discuss levels of validation and issues relating to usability, data quality, data protection, and attrition. While still in its infancy, digital cognitive assessment, especially when administered remotely, will undoubtedly play a major future role in screening for and tracking preclinical AD.
Collapse
Affiliation(s)
- Fredrik Öhman
- Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, Sahlgrenska AcademyUniversity of GothenburgGothenburgSweden
- Wallenberg Centre for Molecular and Translational MedicineUniversity of GothenburgGothenburgSweden
| | - Jason Hassenstab
- Department of NeurologyWashington University in St. LouisSt. LouisMissouriUSA
- Department of Psychological & Brain SciencesWashington University in St. LouisSt. LouisMissouriUSA
| | - David Berron
- German Center for Neurodegenerative Diseases (DZNE)MagdeburgGermany
- Clinical Memory Research Unit, Department of Clinical Sciences MalmöLund UniversityLundSweden
| | - Michael Schöll
- Department of Psychiatry and Neurochemistry, Institute of Neuroscience and Physiology, Sahlgrenska AcademyUniversity of GothenburgGothenburgSweden
- Wallenberg Centre for Molecular and Translational MedicineUniversity of GothenburgGothenburgSweden
- Dementia Research Centre, Queen Square Institute of NeurologyUniversity College LondonLondonUK
| | - Kathryn V. Papp
- Center for Alzheimer Research and TreatmentDepartment of Neurology, Brigham and Women's HospitalHarvard Medical SchoolBostonMassachusettsUSA
- Department of Neurology, Massachusetts General HospitalHarvard Medical SchoolBostonMassachusettsUSA
| |
Collapse
|