{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T06:28:19Z","timestamp":1786429699629,"version":"build-2736575974"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"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>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Quantitative susceptibility mapping (QSM) enables non-invasive assessment of brain iron deposition in Parkinson's disease (PD), yet existing radiomics studies have predominantly focused on single subcortical nuclei, without systematically evaluating whether combining multiple regions improves diagnostic accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 59 PD patients and 73 healthy controls underwent QSM. Radiomic features were extracted from the substantia nigra (SN), caudate nucleus (CN), globus pallidus (GP), red nucleus (RN), and putamen (Put). For all 31 possible combinations of the five nuclei, feature selection was performed on the training set using Wilcoxon rank-sum tests, minimal redundancy maximal relevance, and least absolute shrinkage and selection operator regression. Four classifiers\u2014logistic regression (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)\u2014were trained and evaluated under a stratified five-fold nested cross-validation framework. Diagnostic performance was assessed primarily using the area under the receiver operating characteristic curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      LR achieved its best mean test AUC of 0.879 \u00b1 0.045 with CN + GP. SVM and RF yielded optimal mean test AUCs of 0.880 \u00b1 0.047 (GP + RN + Put) and 0.891 \u00b1 0.028 (CN + GP), respectively. XGBoost with GP + RN + Put produced the highest mean test AUC among all models (0.921 \u00b1 0.040) and was designated the global best model; bootstrap validation confirmed its robustness (AUC = 0.940, 95% confidence interval: 0.891\u20130.977). A significant positive correlation was observed between the number of combined nuclei and XGBoost test AUC (Spearman's rho = 0.614,\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt; 0.001).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A multi-nuclei QSM-based radiomics model integrating GP, RN, and Put with XGBoost achieves excellent diagnostic performance for PD, supporting the value of multi-regional information fusion in precision imaging-based diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2026.1869390","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T05:39:57Z","timestamp":1786426797000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based radiomics modeling of combined subcortical nuclei from quantitative susceptibility mapping for Parkinson's disease diagnosis"],"prefix":"10.3389","volume":"18","author":[{"given":"Fudong","family":"Wen","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Public Health College, Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Public Health College, Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubing","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Public Health College, Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Public Health College, Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Song","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Magnetic Resonance, The First Affiliated Hospital of Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yupeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Public Health College, Harbin Medical University, Harbin","place":["Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1002\/mds.27730","article-title":"Jr. Ventral posterior substantia nigra iron increases over 3 years in Parkinson's disease","volume":"34","author":"Bergsland","year":"2019","journal-title":"Movement Disord"},{"key":"B2","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1016\/j.neuroimage.2016.12.033","article-title":"Changes in brain iron concentration after exposure to high-altitude hypoxia measured by quantitative susceptibility mapping","volume":"147","author":"Chen","year":"2017","journal-title":"NeuroImage"},{"key":"B3","doi-asserted-by":"publisher","first-page":"105917","DOI":"10.1016\/j.ebiom.2025.105917","article-title":"Brain-clinical signatures of basal ganglia-related dysfunctional reorganisation in Parkinson's disease","volume":"120","author":"Chen","year":"","journal-title":"EBioMedicine"},{"key":"B4","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXGBoost: a scalable tree boosting system,\u201d","author":"Chen","year":"2016","journal-title":"Kdd '16"},{"key":"B5","doi-asserted-by":"publisher","first-page":"e14361","DOI":"10.1002\/alz.14361","article-title":"Integrated cerebellar radiomic-network model for predicting mild cognitive impairment in Alzheimer's disease","volume":"21","author":"Chen","year":"","journal-title":"Alzheimer's Dementia"},{"key":"B6","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3389\/fnagi.2019.00167","article-title":"Radiomic features of the nigrosome-1 region of the substantia Nigra: using quantitative susceptibility mapping to assist the diagnosis of idiopathic Parkinson's disease","volume":"11","author":"Cheng","year":"2019","journal-title":"Front. Aging Neurosci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1186\/s13244-021-01115-1","article-title":"Measuring the bias of incorrect application of feature selection when using cross-validation in radiomics","volume":"12","author":"Demircioglu","year":"2021","journal-title":"Insights Imaging"},{"key":"B8","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1038\/s41467-024-55659-z","article-title":"Multiparametric MRI along with machine learning predicts prognosis and treatment response in pediatric low-grade glioma","volume":"16","author":"Fathi Kazerooni","year":"2025","journal-title":"Nat. Commun"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D Slicer as an image computing platform for the quantitative imaging network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"B10","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's disease: a multicenter machine learning study using T2-weighted FLAIR imaging","volume":"16","author":"Fu","year":"2025","journal-title":"Insights Imaging"},{"key":"B11","doi-asserted-by":"publisher","first-page":"631210","DOI":"10.3389\/fneur.2021.631210","article-title":"Time-specific pattern of iron deposition in different regions in Parkinson's disease measured by quantitative susceptibility mapping","volume":"12","author":"Fu","year":"2021","journal-title":"Front. Neurol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/S1474-4422(24)00038-3","article-title":"Global, regional, and national burden of disorders affecting the nervous system, 1990\u20132021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"23","year":"2024","journal-title":"Lancet Neurol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/S1474-4422(25)00386-2","article-title":"Azathioprine for the treatment of early Parkinson's disease (AZA-PD): a randomised, double-blind, placebo-controlled, proof-of-concept, phase 2 trial","volume":"25","author":"Greenland","year":"2026","journal-title":"Lancet Neurol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e70540","DOI":"10.1002\/mco2.70540","article-title":"Parkinson's disease: the epidemiology, risk factors, molecular pathogenesis, prevention, and therapy","volume":"6","author":"Guo","year":"2025","journal-title":"MedComm"},{"key":"B15","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1007\/s00702-017-1717-8","article-title":"Magnetic resonance imaging for the diagnosis of Parkinson's disease","volume":"124","author":"Heim","year":"2017","journal-title":"J. Neural Transm"},{"key":"B16","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":"B17","doi-asserted-by":"publisher","first-page":"6992","DOI":"10.1007\/s00330-022-08790-8","article-title":"Combining quantitative susceptibility mapping to radiomics in diagnosing Parkinson's disease and assessing cognitive impairment","volume":"32","author":"Kang","year":"2022","journal-title":"Eur. Radiol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2703114","DOI":"10.1155\/padi\/2703114","article-title":"Towards a biologically defined diagnosis: incorporating pathophysiological measures into Parkinson's disease clinical criteria","volume":"2026","author":"McNamara","year":"2026","journal-title":"Parkinson's Dis"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1752","DOI":"10.1212\/WNL.0000000000000398","article-title":"Visualization of nigrosome 1 and its loss in PD: pathoanatomical correlation and in vivo 7T MRI","volume":"82","author":"Mueller","year":"2014","journal-title":"Neurology"},{"key":"B21","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":"Movement Disord"},{"key":"B22","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s10020-021-00426-9","article-title":"Relationship between brain iron deposition and mitochondrial dysfunction in idiopathic Parkinson's disease","volume":"28","author":"Prasuhn","year":"2022","journal-title":"Mol. Med"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1030","DOI":"10.1038\/s41586-025-10059-1","article-title":"Parkinson's disease as a somato-cognitive action network disorder","volume":"651","author":"Ren","year":"2026","journal-title":"Nature"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1007\/s11547-021-01389-x","article-title":"deep look into radiomics","volume":"126","author":"Scapicchio","year":"2021","journal-title":"La Radiologia Medica"},{"key":"B25","doi-asserted-by":"publisher","first-page":"14490","DOI":"10.1038\/s41598-021-93651-5","article-title":"Impact of train\/test sample regimen on performance estimate stability of machine learning in cardiovascular imaging","volume":"11","author":"Singh","year":"2021","journal-title":"Sci. Rep"},{"key":"B26","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":"B27","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1002\/mds.27717","article-title":"Voxel-based quantitative susceptibility mapping in Parkinson's disease with mild cognitive impairment","volume":"34","author":"Uchida","year":"2019","journal-title":"Movement Disord"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"B29","doi-asserted-by":"publisher","first-page":"102070","DOI":"10.1016\/j.nicl.2019.102070","article-title":"Quantitative susceptibility mapping based hybrid feature extraction for diagnosis of Parkinson's disease","volume":"24","author":"Xiao","year":"2019","journal-title":"NeuroImage Clin"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/j.acra.2025.11.044","article-title":"Prediction of obstructive sleep apnea using hypothalamic radiomics and machine learning","volume":"33","author":"Xiong","year":"2026","journal-title":"Acad. Radiol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"792778","DOI":"10.3389\/fnagi.2022.792778","article-title":"Combined application of quantitative susceptibility mapping and diffusion kurtosis imaging techniques to investigate the effect of iron deposition on microstructural changes in the brain in Parkinson's disease","volume":"14","author":"Yang","year":"2022","journal-title":"Front. Aging Neurosci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"102477","DOI":"10.1016\/j.arr.2024.102477","article-title":"Ferroptosis in Parkinson's disease\u2014the iron-related degenerative disease","volume":"101","author":"Yao","year":"2024","journal-title":"Ageing Res. Rev"},{"key":"B33","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s10571-024-01459-4","article-title":"Iron deposition in Parkinson's disease: a mini-review","volume":"44","author":"Zeng","year":"2024","journal-title":"Cell. Mol. Neurobiol"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1869390\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T05:39:58Z","timestamp":1786426798000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1869390\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":33,"alternative-id":["10.3389\/fnagi.2026.1869390"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2026.1869390","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]},"article-number":"1869390"}}