{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T15:51:51Z","timestamp":1790092311446,"version":"4.0.1"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T00:00:00Z","timestamp":1756944000000},"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. Neurol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Parkinson\u2019s disease (PD) is a common neurodegenerative disorder, and the early and accurate differentiation of its motor subtypes is of significant importance for clinical diagnosis and treatment planning. Research has shown that deep brain nuclei such as the thalamus, caudate nucleus, putamen, and globus pallidus play a critical role in the pathogenesis of different motor subtypes of Parkinson\u2019s disease. This study aims to utilize deep learning and radiomics technology to establish an automated method for differentiating motor subtypes of Parkinson\u2019s disease.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The data for this study were obtained from the Parkinson\u2019s Progression Markers Initiative (PPMI) database, including a total of 135 Parkinson\u2019s disease patients, comprising 43 cases of the Postural Instability\/Gait Difficulty (PIGD) subtype and 92 cases of the Tremor Dominant (TD) subtype. High-resolution MRI scans were used to extract 2,264 radiomics features from 8 deep brain nuclei, including bilateral thalamus, caudate nucleus, putamen, and globus pallidus. After dimensionality reduction, five independent machine learning classifiers [AdaBoost, Bagging Decision Tree (BDT), Gaussian Process (GP), Logistic Regression (LR), and Random Forest (RF)] were trained on the training set and validated on the test set. Model performance was evaluated using the Area Under the Curve (AUC) metric.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>After feature selection, 17 most discriminative radiomics features were retained. Among the models, the BDT-based diagnostic model demonstrated the best performance, achieving AUC values of 1.000 and 0.962 on the training and test sets, respectively. DeLong\u2019s test results indicated that the BDT model significantly outperformed other models. Calibration curve analysis showed that the Parkinson\u2019s disease subtype classification model based on MRI radiomics features exhibited good calibration and stability. Clinical decision curve analysis revealed that the BDT model demonstrated significant clinical net benefits across a wide probability range, indicating high clinical utility.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The BDT model based on MRI radiomics features constructed in this study exhibited excellent performance in differentiating motor subtypes of Parkinson\u2019s disease and can serve as an effective tool for clinical auxiliary diagnosis. This fully automated model is capable of processing MRI data and providing results within 3\u202fmin, offering an efficient and reliable solution for the early differentiation of Parkinson\u2019s disease motor subtypes, with significant clinical application value.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2025.1650985","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:55:57Z","timestamp":1756997757000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Automatic differentiation of Parkinson\u2019s disease motor subtypes based on deep learning and radiomics"],"prefix":"10.3389","volume":"16","author":[{"given":"Dongming","family":"Hui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengxi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojing","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,4]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1016\/j.amjmed.2019.03.001","article-title":"Parkinson's disease and parkinsonism","volume":"132","author":"Hayes","year":"2019","journal-title":"Am J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e080952","DOI":"10.1136\/bmj-2023-080952","article-title":"Projections for prevalence of Parkinson's disease and its driving factors in 195 countries and territories to 2050: modelling study of global burden of disease study 2021","volume":"388","author":"Su","year":"2025","journal-title":"BMJ (Clinical research ed)"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/S0140-6736(23)01419-8","article-title":"The epidemiology of Parkinson's disease","volume":"403","author":"Ben-Shlomo","year":"2024","journal-title":"Lancet (London, England)"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"63","DOI":"10.14366\/AD.2014.050063","article-title":"Evidence for gender differences in cognition, emotion and quality of life in Parkinson's disease?","volume":"5","author":"Heller","year":"2014","journal-title":"Aging Dis"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1001\/jamaneurol.2013.6233","article-title":"Parkinson disease subtypes","volume":"71","author":"Thenganatt","year":"2014","journal-title":"JAMA Neurol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1212\/WNL.0000000000012868","article-title":"Dopaminergic therapy for motor symptoms in early Parkinson disease practice guideline summary: a report of the AAN guideline subcommittee","volume":"97","author":"Pringsheim","year":"2021","journal-title":"Neurology"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"669638","DOI":"10.3389\/fphar.2021.669638","article-title":"Natural compounds as medical strategies in the prevention and treatment of psychiatric disorders seen in neurological diseases","volume":"12","author":"K\u00fcpeli Akkol","year":"2021","journal-title":"Front Pharmacol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.parkreldis.2017.07.018","article-title":"Motor subtype changes in early Parkinson's disease","volume":"43","author":"Eisinger","year":"2017","journal-title":"Parkinsonism Relat Disord"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1002\/mdc3.13107","article-title":"Neuroimaging detectable differences between Parkinson's disease motor subtypes: a systematic review","volume":"8","author":"Boonstra","year":"2021","journal-title":"Mov Disord Clin Pract"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1476","DOI":"10.1212\/WNL.0b013e31828cfaa4","article-title":"Gray matter atrophy distinguishes between Parkinson disease motor subtypes","volume":"80","author":"Rosenberg-Katz","year":"2013","journal-title":"Neurology"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"7249","DOI":"10.1111\/ejn.16612","article-title":"Cortical complexity alterations in motor subtypes of Parkinson's disease: a surface-based morphometry analysis of fractal dimension","volume":"60","author":"Dehghan","year":"2024","journal-title":"Eur J Neurosci"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1016\/j.parkreldis.2013.08.011","article-title":"Motor phenotype and magnetic resonance measures of basal ganglia iron levels in Parkinson's disease","volume":"19","author":"Bunzeck","year":"2013","journal-title":"Parkinsonism Relat Disord"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1002\/mds.27372","article-title":"International Parkinson and movement disorder society evidence-based medicine review: update on treatments for the motor symptoms of Parkinson's disease","volume":"33","author":"Fox","year":"2018","journal-title":"Mov Disord"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information from medical images using advanced feature analysis","volume":"48","author":"Lambin","year":"2012","journal-title":"Eur J Cancer"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.2174\/1570159X18666200528142429","article-title":"Recent advancements in pathogenesis, diagnostics and treatment of Alzheimer's disease","volume":"18","author":"Khan","year":"2020","journal-title":"Curr Neuropharmacol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.neuchi.2022.05.004","article-title":"MRI-based whole-tumor radiomics to classify the types of pediatric posterior fossa brain tumor","volume":"68","author":"Wang","year":"2022","journal-title":"Neuro-Chirurgie"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"2272","DOI":"10.1007\/s00330-020-07284-9","article-title":"How can we combat multicenter variability in MR radiomics? Validation of a correction procedure","volume":"31","author":"Orlhac","year":"2021","journal-title":"Eur Radiol"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1007\/s00702-014-1349-1","article-title":"Cognitive function and other non-motor features in non-demented Parkinson's disease motor subtypes","volume":"122","author":"Herman","year":"1996","journal-title":"J Neural Transm"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"471","DOI":"10.3389\/fneur.2019.00471","article-title":"Alteration of tremor dominant and postural instability gait difficulty subtypes during the progression of Parkinson's disease: analysis of the PPMI cohort","volume":"10","author":"Lee","year":"2019","journal-title":"Front Neurol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.exger.2018.06.031","article-title":"Head and trunk stability during gait before and after levodopa intake in Parkinson's disease subtypes","volume":"111","author":"Pelicioni","year":"2018","journal-title":"Exp Gerontol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1002\/mds.25383","article-title":"How to identify tremor dominant and postural instability\/gait difficulty groups with the movement disorder society unified Parkinson's disease rating scale: comparison with the unified Parkinson's disease rating scale","volume":"28","author":"Stebbins","year":"2013","journal-title":"Mov Disord"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"113","DOI":"10.3760\/cma.j.issn.2095-2848.2020.02.012","article-title":"Research progress of 6-[18F]fluoro-L-dopa PET\/CT imaging","volume":"40","author":"Jingnan","year":"2020","journal-title":"Chin J Nucl Med Mol Imaging"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1111\/jnc.15516","article-title":"The role of neuroimaging in Parkinson's disease","volume":"159","author":"Bidesi","year":"2021","journal-title":"J Neurochem"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1136\/jnnp-2016-314471","article-title":"REM sleep behaviour disorder: prodromal and mechanistic insights for Parkinson's disease","volume":"88","author":"Tekriwal","year":"2017","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"379","DOI":"10.3760\/cma.j.issn.1006-7876.2019.05.004","article-title":"Comparative study of diffusion kurtosis imaging in deep brain nucleus in different subtypes of Parkinson\u2032s disease","author":"Si","year":"2019","journal-title":"Chin J Neurol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00234-017-1846-7","article-title":"White matter microstructure damage in tremor-dominant Parkinson's disease patients","volume":"59","author":"Luo","year":"2017","journal-title":"Neuroradiology"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"137249","DOI":"10.1016\/j.neulet.2023.137249","article-title":"Distribution pattern of iron deposition in the basal ganglia of different motor subtypes of Parkinson's disease","volume":"807","author":"Zhang","year":"2023","journal-title":"Neurosci Lett"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"2251","DOI":"10.1007\/s00415-014-7302-2","article-title":"Dopamine receptor mapping with PET imaging in Parkinson's disease","volume":"261","author":"Niccolini","year":"2014","journal-title":"J Neurol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3389\/fnana.2016.00017","article-title":"Microstructural changes within the basal ganglia differ between Parkinson disease subtypes","volume":"10","author":"Nagae","year":"2016","journal-title":"Front Neuroanat"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1097\/CM9.0000000000003167","article-title":"Iron deposition in subcortical nuclei of Parkinson's disease: a meta-analysis of quantitative iron-sensitive magnetic resonance imaging studies","volume":"138","author":"Jin","year":"2025","journal-title":"Chin Med J"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1093\/cercor\/bhu076","article-title":"Widespread monoaminergic dysregulation of both motor and non-motor circuits in parkinsonism and dyskinesia","volume":"25","author":"Engeln","year":"2015","journal-title":"Cereb Cortex"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1650985\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:56:00Z","timestamp":1756997760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1650985\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,4]]},"references-count":32,"alternative-id":["10.3389\/fneur.2025.1650985"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1650985","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,4]]},"article-number":"1650985"}}