{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T17:47:11Z","timestamp":1793036831486,"version":"4.5.0"},"reference-count":118,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:00:00Z","timestamp":1760054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Parkinson\u2019s disease (PD) is a progressive neurodegenerative disorder requiring early diagnosis and accurate staging for optimal treatment outcomes. Traditional clinical assessments have limitations in objectivity and reproducibility.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>To develop and validate an Attention-based Transformer-LSTM hybrid deep learning model (ATLAS-PD) for classifying early-stage PD patients (H&amp;amp;Y stages 1\u20132) and healthy controls using functional near-infrared spectroscopy (fNIRS) data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This cross-sectional study enrolled 240 participants: 80 healthy controls, 80 H&amp;amp;Y stage 1 PD patients, and 80 H&amp;amp;Y stage 2 PD patients. fNIRS data were collected during a pegboard task using a 22-channel system covering prefrontal cortex regions. To address task-specific bias, a pilot complementary gait imagery task was performed on a subset of 60 participants (20 per group), with additional ROC AUC analysis. The ATLAS-PD model was compared with traditional machine learning algorithms including Support Vector Machine, Random Forest, K-Nearest Neighbors, and Back-Propagation Neural Network. McNemar\u2019s test and bootstrap resampling were conducted to assess superiority. Interpretability analysis was conducted using permutation importance to quantify channel contributions, with regional aggregation and channel ranking to identify neurophysiologically relevant patterns. Additionally, t-SNE (t-distributed Stochastic Neighbor Embedding) dimensionality reduction was applied to visualize the feature space clustering.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The ATLAS-PD model achieved an accuracy of 88.9% (95% CI: 0.808\u20130.970), demonstrating superior robustness and generalization compared to traditional approaches. While SVM showed higher accuracy (92.6, 95% CI: 0.869\u20130.983) on the test set, it exhibited significant performance degradation under noise conditions (accuracy dropped to 45.2% at <jats:italic>\u03c3<\/jats:italic>\u202f=\u202f0.3). ATLAS-PD maintained 80.09% accuracy at the same noise level, indicating superior clinical applicability. The model achieved AUC values of 0.99, 0.78, and 0.88 for healthy controls, H&amp;amp;Y stage 1, and H&amp;amp;Y stage 2 groups, respectively. For the gait imagery task, macro-average AUC was 0.723, confirming model robustness across tasks. Statistical tests confirmed ATLAS-PD significantly outperformed baselines (<jats:italic>p<\/jats:italic>\u202f&amp;lt;\u202f0.05). Interpretability analysis using permutation importance and attention weight visualization revealed the model primarily utilizes bilateral frontal polar cortex signals, with channels CH01, CH04, CH05, and CH08 showing highest importance scores. t-SNE visualizations further demonstrated distinct clustering of healthy controls from PD groups, with partial overlap between H&amp;amp;Y stages 1 and 2, reflecting the disease continuum.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>ATLAS-PD provides an objective, non-invasive tool for early PD diagnosis and staging in H&amp;amp;Y stages 1\u20132. The inclusion of complementary tasks and statistical validations enhances its clinical applicability. Future studies should validate the model\u2019s performance in more advanced PD stages to enhance clinical applicability.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnagi.2025.1677722","type":"journal-article","created":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T05:30:04Z","timestamp":1760074204000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Attention-based Transformer-LSTM architecture for early diagnosis and staging of early-stage Parkinson\u2019s disease using fNIRS data"],"prefix":"10.3389","volume":"17","author":[{"given":"Huan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hujun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyan","family":"Qie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congxiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,10]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1109\/TNSRE.2020.2987888","article-title":"Merging fNIRS-EEG brain monitoring and body motion capture to distinguish Parkinson\u2019s disease","volume":"28","author":"Abtahi","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking inside the black-box: a survey on explainable artificial intelligence (xai)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1212\/WNL.0000000000000641","article-title":"Low clinical diagnostic accuracy of early vs advanced Parkinson disease: clinicopathologic study","volume":"83","author":"Adler","year":"2014","journal-title":"Neurology"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2450005","DOI":"10.4015\/S1016237224500054","article-title":"Automated detection of Parkinson\u2019s disease based on hybrid CNN and quantum machine learning techniques in MRI images","volume":"36","author":"Ahalya","year":"2024","journal-title":"Biomed. Eng. Appl. Basis Commun."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"584","DOI":"10.3389\/fnins.2020.00584","article-title":"Enhanced accuracy for multiclass mental workload detection using long short-term memory for brain\u2013computer interface","volume":"14","author":"Asgher","year":"2020","journal-title":"Front. Neurosci."},{"key":"ref6","article-title":"Benchmarking of EEG analysis techniques for Parkinson's disease diagnosis: a comparison between traditional ml methods and foundation dl methods","author":"Avola","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1007\/s00401-009-0538-8","article-title":"Unified staging system for Lewy body disorders: correlation with nigrostriatal degeneration, cognitive impairment and motor dysfunction","volume":"117","author":"Beach","year":"2009","journal-title":"Acta Neuropathol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.neuroscience.2019.07.024","article-title":"The association between prefrontal cortex activity and turning behavior in people with and without freezing of gait","volume":"416","author":"Belluscio","year":"2019","journal-title":"Neuroscience"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"773","DOI":"10.3390\/diagnostics15060773","article-title":"A comparative study of machine learning and deep learning models for automatic Parkinson\u2019s disease detection from electroencephalogram signals","volume":"15","author":"Bera","year":"2025","journal-title":"Diagnostics"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1002\/mds.26431","article-title":"MDS research criteria for prodromal Parkinson's disease","volume":"30","author":"Berg","year":"2015","journal-title":"Mov. Disord."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1177\/1073191114524271","article-title":"Grooved pegboard predicates more of cognitive than motor involvement in Parkinson\u2019s disease","volume":"21","author":"Bezdicek","year":"2014","journal-title":"Assessment"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"107140","DOI":"10.1016\/j.compbiomed.2023.107140","article-title":"Integrative gene expression analysis for the diagnosis of Parkinson\u2019s disease using machine learning and explainable AI","volume":"163","author":"Bhandari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"14897","DOI":"10.3390\/ijms232314897","article-title":"Whole-head functional near-infrared spectroscopy as an ecological monitoring tool for assessing cortical activity in Parkinson\u2019s disease patients at different stages","volume":"23","author":"Bonilauri","year":"2022","journal-title":"Int. J. Mol. Sci."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"102695","DOI":"10.1016\/j.jelekin.2022.102695","article-title":"Finger dexterity measured by the grooved pegboard test indexes Parkinson\u2019s motor severity in a tremor-independent manner","volume":"66","author":"Buard","year":"2022","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"103405","DOI":"10.1016\/j.nicl.2023.103405","article-title":"Explainable classification of Parkinson\u2019s disease using deep learning trained on a large multi-center database of T1-weighted MRI datasets","volume":"38","author":"Camacho","year":"2023","journal-title":"NeuroImage Clin."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"4890","DOI":"10.1038\/s41598-024-55483-x","article-title":"Advanced hybrid LSTM-Transformer architecture for real-time multi-task prediction in engineering systems","volume":"14","author":"Cao","year":"2024","journal-title":"Sci. Rep."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"126","DOI":"10.3389\/fnhum.2016.00126","article-title":"Hemodynamic response alteration as a function of task complexity and expertise\u2014an fNIRS study in jugglers","volume":"10","author":"Carius","year":"2016","journal-title":"Front. Hum. Neurosci."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"53","DOI":"10.3389\/fninf.2018.00053","article-title":"Robust ensemble classification methodology for I123-ioflupane SPECT images and multiple heterogeneous biomarkers in the diagnosis of Parkinson's disease","volume":"12","author":"Castillo-Barnes","year":"2018","journal-title":"Front. Neuroinform."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1397896","DOI":"10.3389\/fnagi.2024.1397896","article-title":"An automated hybrid approach via deep learning and radiomics focused on the midbrain and substantia nigra to detect early-stage Parkinson\u2019s disease","volume":"16","author":"Chen","year":"2024","journal-title":"Front. Aging Neurosci."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"217","DOI":"10.3389\/fnagi.2014.00217","article-title":"Utilization of central nervous system resources for preparation and performance of complex walking tasks in older adults","volume":"6","author":"Clark","year":"2014","journal-title":"Front. Aging Neurosci."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e23120","DOI":"10.1002\/ima.23120","article-title":"A hybrid deep spatiotemporal attention-based model for Parkinson's disease diagnosis using resting state EEG signals","volume":"34","author":"Delfan","year":"2024","journal-title":"Int. J. Imaging Syst. Technol."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"20941","DOI":"10.1038\/s41598-024-70165-4","article-title":"Enhancing early Parkinson\u2019s disease detection through multimodal deep learning and explainable AI: insights from the PPMI database","volume":"14","author":"Dentamaro","year":"2024","journal-title":"Sci. Rep."},{"key":"ref23","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional Transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1615","DOI":"10.1002\/mds.29506","article-title":"Integrative brain states facilitate the expression of Parkinson's tremor","volume":"38","author":"Dirkx","year":"2023","journal-title":"Mov. Disord."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1016\/S1474-4422(18)30295-3","article-title":"Global, regional, and national burden of Parkinson\u2019s disease, 1990\u20132016: a systematic analysis for the Global Burden of Disease Study 2016","volume":"17","author":"Dorsey","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref26","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1016\/j.neuroimage.2013.03.067","article-title":"Application of functional near-infrared spectroscopy in psychiatry","volume":"85","author":"Ehlis","year":"2014","journal-title":"NeuroImage"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1515\/revneuro-2023-0117","article-title":"Diagnostic machine learning applications on clinical populations using functional near infrared spectroscopy: a review","volume":"35","author":"Eken","year":"2024","journal-title":"Rev. Neurosci."},{"key":"ref29","first-page":"153","article-title":"Unified Parkinson\u2019s disease rating scale","volume-title":"Recent developments in Parkinson\u2019s disease","author":"Fahn","year":"1987"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recogn. Lett."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1016\/j.neuroimage.2012.03.049","article-title":"A brief review on the history of human functional near-infrared spectroscopy (fNIRS) development and fields of application","volume":"63","author":"Ferrari","year":"2012","journal-title":"NeuroImage"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neuroimage.2018.09.025","article-title":"Temporal derivative distribution repair (TDDR): a motion correction method for fNIRS","volume":"184","author":"Fishburn","year":"2019","journal-title":"NeuroImage"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.1111\/itor.13469","article-title":"Combining convolution neural networks with long-short term memory layers to predict Parkinson's disease progression","volume":"32","author":"Frasca","year":"2025","journal-title":"Int. Trans. Oper. Res."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1186\/s13244-025-01961-3","article-title":"Harnessing routine MRI for the early screening of Parkinson\u2019s disease: a multicenter machine learning study using T2-weighted flair imaging","volume":"16","author":"Fu","year":"2025","journal-title":"Insights Imaging"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1002\/mds.26110","article-title":"Progression of gait dysfunction in incident Parkinson's disease: impact of medication and phenotype","volume":"30","author":"Galna","year":"2015","journal-title":"Mov. Disord."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"e0317566","DOI":"10.1371\/journal.pone.0317566","article-title":"Predicting Parkinson\u2019s disease trajectory using clinical and functional MRI features: a reproduction and replication study","volume":"20","author":"Germani","year":"2025","journal-title":"PLoS One"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1002\/mds.22340","article-title":"Movement Disorder Society-sponsored revision of the Unified Parkinson's Disease Rating Scale (MDS-UPDRS): scale presentation and clinimetric testing results","volume":"23","author":"Goetz","year":"2008","journal-title":"Mov. Disord."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1177\/1545968317693304","article-title":"Near-infrared spectroscopy in gait disorders: is it time to begin?","volume":"31","author":"Gramigna","year":"2017","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.bosn.2024.04.001","article-title":"Exploring motor cortex functional connectivity in Parkinson's disease using fNIRS","volume":"2","author":"Guevara","year":"","journal-title":"Brain Organ. Syst. Neurosci. J."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"763","DOI":"10.17179\/excli2024-7151","article-title":"Integrating fNIRS and machine learning: shedding light on Parkinson's disease detection","volume":"23","author":"Guevara","year":"","journal-title":"EXCLI J."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/BF02985802","article-title":"The elements of statistical learning: data mining, inference and prediction","volume":"27","author":"Hastie","year":"2005","journal-title":"Math. Intell."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1002\/mds.28468","article-title":"Brain motor network changes in Parkinson's disease: evidence from meta-analytic modeling","volume":"36","author":"Herz","year":"2021","journal-title":"Mov. Disord."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1212\/wnl.17.5.427","article-title":"Parkinsonism: onset, progression, and mortality","volume":"17","author":"Hoehn","year":"1967","journal-title":"Neurology"},{"key":"ref45","article-title":"What do we need to build explainable AI systems for the medical domain?","author":"Holzinger","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.heares.2016.01.009","article-title":"Decoding four different sound-categories in the auditory cortex using functional near-infrared spectroscopy","volume":"333","author":"Hong","year":"2016","journal-title":"Hear. Res."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"106496","DOI":"10.1016\/j.bspc.2024.106496","article-title":"Enhancing fNIRS data analysis with a novel motion artifact detection algorithm and improved correction","volume":"95","author":"Huang","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"1354147","DOI":"10.3389\/fnagi.2024.1354147","article-title":"Exploring the application and challenges of fNIRS technology in early detection of Parkinson\u2019s disease","volume":"16","author":"Hui","year":"2024","journal-title":"Front. Aging Neurosci."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.neuroimage.2005.08.065","article-title":"A temporal comparison of bold, ASL, and NIRS hemodynamic responses to motor stimuli in adult humans","volume":"29","author":"Huppert","year":"2006","journal-title":"NeuroImage"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.aiia.2019.05.004","article-title":"A comprehensive review on automation in agriculture using artificial intelligence","volume":"2","author":"Jha","year":"2019","journal-title":"Artif. Intell. Agric."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"20552076241297355","DOI":"10.1177\/20552076241297355","article-title":"Parkinson's disease detection from EEG signal employing autoencoder and RBFNN-based hybrid deep learning framework utilizing power spectral density","volume":"10","author":"Jibon","year":"2024","journal-title":"Digit. Health."},{"key":"ref52","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1016\/S0140-6736(14)61393-3","article-title":"Parkinson's disease","volume":"386","author":"Kalia","year":"2015","journal-title":"Lancet"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1016\/j.bbe.2021.04.014","article-title":"An improved framework for Parkinson\u2019s disease prediction using variational mode decomposition-Hilbert spectrum of speech signal","volume":"41","author":"Karan","year":"2021","journal-title":"Biocybern. Biomed. Eng."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"7943","DOI":"10.3390\/s21237943","article-title":"Classification of individual finger movements from right hand using fNIRS signals","volume":"21","author":"Khan","year":"2021","journal-title":"Sensors"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"1286586","DOI":"10.3389\/fnrgo.2024.1286586","article-title":"Optimizing spatial specificity and signal quality in fNIRS: an overview of potential challenges and possible options for improving the reliability of real-time applications","volume":"5","author":"Klein","year":"2024","journal-title":"Front. Neuroergon."},{"key":"ref56","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.tics.2011.04.005","article-title":"Frontal pole function: what is specifically human?","volume":"15","author":"Koechlin","year":"2011","journal-title":"Trends Cogn. Sci."},{"key":"ref57","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.1002\/mds.28706","article-title":"International multicenter analysis of brain structure across clinical stages of Parkinson's disease","volume":"36","author":"Laansma","year":"2021","journal-title":"Mov. Disord."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"015006","DOI":"10.1117\/1.NPh.8.1.015006","article-title":"Monitoring the motor cortex hemodynamic response function in freely moving walking subjects: a time-domain fNIRS pilot study","volume":"8","author":"Lacerenza","year":"2021","journal-title":"Neurophotonics."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1007\/s10772-021-09837-9","article-title":"A hybrid system for Parkinson\u2019s disease diagnosis using machine learning techniques","volume":"25","author":"Lamba","year":"2022","journal-title":"Int. J. Speech Technol."},{"key":"ref60","doi-asserted-by":"publisher","first-page":"e26617","DOI":"10.1002\/hbm.26617","article-title":"Phase-encoded fMRI tracks down brainstorms of natural language processing with subsecond precision","volume":"45","author":"Lei","year":"2024","journal-title":"Hum. Brain Mapp."},{"key":"ref61","doi-asserted-by":"publisher","first-page":"110363","DOI":"10.1016\/j.jneumeth.2025.110363","article-title":"PIDGN: an explainable multimodal deep learning framework for early prediction of Parkinson's disease","volume":"415","author":"Li","year":"2025","journal-title":"J. Neurosci. Methods"},{"key":"ref62","doi-asserted-by":"publisher","first-page":"1062889","DOI":"10.3389\/fnins.2022.1062889","article-title":"Early-stage fusion of EEG and fNIRS improves classification of motor imagery","volume":"16","author":"Li","year":"2023","journal-title":"Front. Neurosci."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"1127719","DOI":"10.3389\/fnimg.2023.1127719","article-title":"Editorial: Deep learning in neuroimaging-based neurological disease analysis","volume":"2","author":"Li","year":"2023","journal-title":"Front. Neuroimaging"},{"key":"ref64","doi-asserted-by":"publisher","first-page":"102233","DOI":"10.1016\/j.media.2021.102233","article-title":"BrainGNN: interpretable brain graph neural network for fMRI analysis","volume":"74","author":"Li","year":"2021","journal-title":"Med. Image Anal."},{"key":"ref65","article-title":"Learning to diagnose with LSTM recurrent neural networks","author":"Lipton","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","first-page":"1740","DOI":"10.3390\/electronics10141740","article-title":"GaborPDNet: Gabor transformation and deep neural network for Parkinson\u2019s disease detection using EEG signals","volume":"10","author":"Loh","year":"2021","journal-title":"Electronics"},{"key":"ref67","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1109\/TNSRE.2023.3242263","article-title":"An fNIRS-based dynamic functional connectivity analysis method to signify functional neurodegeneration of Parkinson\u2019s disease","volume":"31","author":"Lu","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref68","doi-asserted-by":"publisher","first-page":"5964","DOI":"10.1038\/s41598-021-85386-0","article-title":"Deconvolution of hemodynamic responses along the cortical surface using personalized functional near infrared spectroscopy","volume":"11","author":"Machado","year":"2021","journal-title":"Sci. Rep."},{"key":"ref69","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1177\/1545968316650426","article-title":"The role of the frontal lobe in complex walking among patients with Parkinson\u2019s disease and healthy older adults: an fNIRS study","volume":"30","author":"Maidan","year":"2016","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref70","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.pneurobio.2011.09.005","article-title":"The Parkinson progression marker initiative (PPMI)","volume":"95","author":"Marek","year":"2011","journal-title":"Prog. Neurobiol."},{"key":"ref71","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1038\/s41531-018-0058-0","article-title":"Prevalence of Parkinson\u2019s disease across North America","volume":"4","author":"Marras","year":"2018","journal-title":"npj Parkinsons Dis."},{"key":"ref72","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1002\/mds.870090112","article-title":"Unified Parkinson's disease rating scale characteristics and structure","volume":"9","author":"Mart\u00ednez-Mart\u00edn","year":"1994","journal-title":"Mov. Disord."},{"key":"ref73","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1016\/j.neuroimage.2011.12.039","article-title":"Towards the utilization of EEG as a brain imaging tool","volume":"61","author":"Michel","year":"2012","journal-title":"NeuroImage"},{"key":"ref74","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: review, opportunities and challenges","volume":"19","author":"Miotto","year":"2018","journal-title":"Brief. Bioinform."},{"key":"ref75","doi-asserted-by":"publisher","first-page":"873239","DOI":"10.3389\/fnbot.2022.873239","article-title":"EEG-fNIRS-based hybrid image construction and classification using CNN-LSTM","volume":"16","author":"Mughal","year":"2022","journal-title":"Front. Neurorobot."},{"key":"ref76","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/s40814-016-0099-2","article-title":"Measuring prefrontal cortical activity during dual task walking in patients with Parkinson\u2019s disease: feasibility of using a new portable fNIRS device","volume":"2","author":"Nieuwhof","year":"2016","journal-title":"Pilot Feasibility Stud."},{"key":"ref77","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.tele.2017.01.007","article-title":"A knowledge-based system for breast cancer classification using fuzzy logic method","volume":"34","author":"Nilashi","year":"2017","journal-title":"Telemat. Inform."},{"key":"ref78","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s42979-024-02728-1","article-title":"Parkinson disease prediction using CNN-LSTM model from voice signal","volume":"5","author":"Pandey","year":"2024","journal-title":"SN Comput. Sci."},{"key":"ref79","doi-asserted-by":"publisher","first-page":"98","DOI":"10.31083\/j.jin2103098","article-title":"The immediate and sustained effects of exercise-induced hemodynamic response on executive function during fine motor-cognitive tasks using functional near-infrared spectroscopy","volume":"21","author":"Park","year":"2022","journal-title":"J. Integr. Neurosci."},{"key":"ref80","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1016\/S1474-4422(19)30024-9","article-title":"Csf and blood biomarkers for Parkinson's disease","volume":"18","author":"Parnetti","year":"2019","journal-title":"Lancet Neurol."},{"key":"ref81","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1111\/nyas.13948","article-title":"The present and future use of functional near-infrared spectroscopy (fNIRS) for cognitive neuroscience","volume":"1464","author":"Pinti","year":"2020","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"ref82","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nrn.2016.167","article-title":"Scanning the horizon: towards transparent and reproducible neuroimaging research","volume":"18","author":"Poldrack","year":"2017","journal-title":"Nat. Rev. Neurosci."},{"key":"ref83","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.heares.2013.11.007","article-title":"Auditory cortex activation to natural speech and simulated cochlear implant speech measured with functional near-infrared spectroscopy","volume":"309","author":"Pollonini","year":"2014","journal-title":"Hear. Res."},{"key":"ref84","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","article-title":"MDS clinical diagnostic criteria for Parkinson's disease","volume":"30","author":"Postuma","year":"2015","journal-title":"Mov. Disord."},{"key":"ref85","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.physio.2019.12.002","article-title":"Construct validity of the 9-hole peg test and Purdue Pegboard test in people with mild to moderately severe Parkinson\u2019s disease","volume":"107","author":"Proud","year":"2020","journal-title":"Physiotherapy"},{"key":"ref86","doi-asserted-by":"publisher","first-page":"957181","DOI":"10.3389\/fnins.2022.957181","article-title":"Parkinson\u2019s disease detection based on multi-pattern analysis and multi-scale convolutional neural networks","volume":"16","author":"Qiu","year":"2022","journal-title":"Front. Neurosci."},{"key":"ref87","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.3390\/electronics12132856","article-title":"Parkinson\u2019s disease detection using hybrid LSTM-GRU deep learning model","volume":"12","author":"Rehman","year":"2023","journal-title":"Electronics"},{"key":"ref88","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1212\/WNL.0000000000002350","article-title":"Accuracy of clinical diagnosis of Parkinson disease: a systematic review and meta-analysis","volume":"86","author":"Rizzo","year":"2016","journal-title":"Neurology"},{"key":"ref89","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1007\/978-3-031-63592-2_17","article-title":"Interpretable classification of early stage Parkinson\u2019s disease from EEG","volume-title":"AI for health equity and fairness: leveraging AI to address social determinants of health","author":"Sahota","year":"2024"},{"key":"ref90","doi-asserted-by":"publisher","first-page":"6732","DOI":"10.1364\/BOE.409317","article-title":"Signal quality index: an algorithm for quantitative assessment of functional near infrared spectroscopy signal quality","volume":"11","author":"Sappia","year":"2020","journal-title":"Biomed. Opt. Express"},{"key":"ref91","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/j.neuroimage.2013.05.004","article-title":"A review on continuous wave functional near-infrared spectroscopy and imaging instrumentation and methodology","volume":"85","author":"Scholkmann","year":"2014","journal-title":"NeuroImage"},{"key":"ref92","doi-asserted-by":"publisher","first-page":"109603","DOI":"10.1016\/j.mehy.2020.109603","article-title":"Early diagnosis of Parkinson\u2019s disease using machine learning algorithms","volume":"138","author":"Senturk","year":"2020","journal-title":"Med. Hypotheses"},{"key":"ref93","doi-asserted-by":"publisher","first-page":"806828","DOI":"10.3389\/fnagi.2022.806828","article-title":"Machine learning for detecting Parkinson\u2019s disease by resting-state functional magnetic resonance imaging: a multicenter radiomics analysis","volume":"14","author":"Shi","year":"2022","journal-title":"Front. Aging Neurosci."},{"key":"ref94","doi-asserted-by":"publisher","first-page":"1029784","DOI":"10.3389\/fnhum.2022.1029784","article-title":"Explainable artificial intelligence model to predict brain states from fNIRS signals","volume":"16","author":"Shibu","year":"2023","journal-title":"Front. Hum. Neurosci."},{"key":"ref95","doi-asserted-by":"publisher","first-page":"110031","DOI":"10.1016\/j.jneumeth.2023.110031","article-title":"fNIRS-based graph frequency analysis to identify mild cognitive impairment in Parkinson\u2019s disease","volume":"402","author":"Shu","year":"2024","journal-title":"J. Neurosci. Methods"},{"key":"ref96","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1038\/s41531-022-00341-8","article-title":"Longitudinal trimodal imaging of midbrain-associated network degeneration in Parkinson\u2019s disease","volume":"8","author":"Steidel","year":"2022","journal-title":"npj Parkinsons Dis."},{"key":"ref97","doi-asserted-by":"publisher","first-page":"536","DOI":"10.3389\/fneur.2019.00536","article-title":"Pre-frontal cortical activity during walking and turning is reliable and differentiates across young, older adults and people with Parkinson's disease","volume":"10","author":"Stuart","year":"2019","journal-title":"Front. Neurol."},{"key":"ref98","doi-asserted-by":"publisher","first-page":"101352","DOI":"10.1016\/j.imu.2023.101352","article-title":"Generalizable electroencephalographic classification of Parkinson's disease using deep learning","volume":"42","author":"Sugden","year":"2023","journal-title":"Inform. Med. Unlocked"},{"key":"ref99","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1016\/S1474-4422(21)00030-2","article-title":"Challenges in the diagnosis of Parkinson's disease","volume":"20","author":"Tolosa","year":"2021","journal-title":"Lancet Neurol."},{"key":"ref100","doi-asserted-by":"publisher","first-page":"046011","DOI":"10.1088\/1741-2552\/ab9842","article-title":"Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network","volume":"17","author":"Tortora","year":"2020","journal-title":"J. Neural Eng."},{"key":"ref101","doi-asserted-by":"publisher","first-page":"110307","DOI":"10.1016\/j.apacoust.2024.110307","article-title":"TPat: transition pattern feature extraction based Parkinson\u2019s disorder detection using fNIRS signals","volume":"228","author":"Tuncer","year":"2025","journal-title":"Appl. Acoust."},{"key":"ref102","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref103","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref104","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.neubiorev.2017.10.002","article-title":"Fnirs response during walking\u2014artefact or cortical activity? A systematic review","volume":"83","author":"Vitorio","year":"2017","journal-title":"Neurosci. Biobehav. Rev."},{"key":"ref105","doi-asserted-by":"publisher","first-page":"e12739","DOI":"10.1111\/exsy.12739","article-title":"Deep learning-based scheme to diagnose Parkinson's disease","volume":"39","author":"Vyas","year":"2022","journal-title":"Expert. Syst."},{"key":"ref106","doi-asserted-by":"publisher","first-page":"1148855","DOI":"10.3389\/fnins.2023.1148855","article-title":"EEGformer: a Transformer-based brain activity classification method using EEG signal","volume":"17","author":"Wan","year":"2023","journal-title":"Front. Neurosci."},{"key":"ref107","doi-asserted-by":"publisher","first-page":"1454598","DOI":"10.3389\/fnagi.2024.1454598","article-title":"Decrease in walking ability with increased functional connectivity between multiple brain areas in Parkinson\u2019s disease: a functional near-infrared spectroscopy study","volume":"16","author":"Wang","year":"2024","journal-title":"Front. Aging Neurosci."},{"key":"ref108","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1002\/jmri.20591","article-title":"Role of functional imaging in neurological disorders","volume":"23","author":"Weiller","year":"2006","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref109","doi-asserted-by":"publisher","first-page":"1425095","DOI":"10.3389\/fnagi.2024.1425095","article-title":"Classification of Parkinson\u2019s disease by deep learning on midbrain MRI","volume":"16","author":"Welton","year":"2024","journal-title":"Front. Aging Neurosci."},{"key":"ref110","first-page":"202","article-title":"A ternary bi-directional lstm classification for brain activation pattern recognition using fNIRS","author":"Wickramaratne","year":"2020"},{"key":"ref111","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1002\/mds.29679","article-title":"Persistence of basal ganglia oscillatory activity during tremor attenuation by movement in Parkinson's disease patients","volume":"39","author":"Wilken","year":"2024","journal-title":"Mov. Disord."},{"key":"ref112","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1038\/s41531-023-00521-0","article-title":"Distinct cortical and subcortical predictors of Purdue Pegboard decline in Parkinson\u2019s disease and atypical parkinsonism","volume":"9","author":"Wilkes","year":"2023","journal-title":"npj Parkinsons Dis."},{"key":"ref113","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1093\/brain\/aws360","article-title":"The cerebellum in Parkinson\u2019s disease","volume":"136","author":"Wu","year":"2013","journal-title":"Brain"},{"key":"ref114","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41531-020-0117-1","article-title":"Current and projected future economic burden of Parkinson\u2019s disease in the US","volume":"6","author":"Yang","year":"2020","journal-title":"npj Parkinsons Dis."},{"key":"ref115","doi-asserted-by":"publisher","first-page":"e16679","DOI":"10.1111\/ejn.16679","article-title":"Motion artifact removal in functional near-infrared spectroscopy based on long short-term memory-autoencoder model","volume":"61","author":"Yang","year":"2025","journal-title":"Eur. J. Neurosci."},{"key":"ref116","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1016\/j.neuroimage.2008.08.036","article-title":"NIRS-SPM: statistical parametric mapping for near-infrared spectroscopy","volume":"44","author":"Ye","year":"2009","journal-title":"NeuroImage"},{"key":"ref117","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1016\/S0140-6736(05)17909-4","article-title":"Parkinson's disease in China: prevalence in Beijing, Xian, and Shanghai","volume":"365","author":"Zhang","year":"2005","journal-title":"Lancet"},{"key":"ref118","doi-asserted-by":"publisher","first-page":"1562203","DOI":"10.3389\/fnagi.2025.1562203","article-title":"Stage-specific functional networks associated with cognitive impairment in Parkinson's disease: a pilot fNIRS study","volume":"17","author":"Zhao","year":"2025","journal-title":"Front. Aging Neurosci."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1677722\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T05:30:07Z","timestamp":1760074207000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1677722\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,10]]},"references-count":118,"alternative-id":["10.3389\/fnagi.2025.1677722"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1677722","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,10]]},"article-number":"1677722"}}