{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:51:49Z","timestamp":1781801509894,"version":"3.54.5"},"reference-count":46,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01\u2010 DC14942"],"award-info":[{"award-number":["R01\u2010 DC14942"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01\u2010DC12519"],"award-info":[{"award-number":["R01\u2010DC12519"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01\u2010NS89757"],"award-info":[{"award-number":["R01\u2010NS89757"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01\u2010AG50603"],"award-info":[{"award-number":["R01\u2010AG50603"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Annals of Neurology"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To determine whether a machine learning model of voxel level [<jats:sup>18<\/jats:sup>f]fluorodeoxyglucose positron emission tomography (PET) data could predict progressive supranuclear palsy (PSP) pathology, as well as outperform currently available biomarkers.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>One hundred and thirty\u2010seven autopsied patients with PSP (n\u2009=\u200942) and other neurodegenerative diseases (n\u2009=\u200995) who underwent antemortem [<jats:sup>18<\/jats:sup>f]fluorodeoxyglucose PET and 3.0 Tesla magnetic resonance imaging (MRI) scans were analyzed. A linear support vector machine was applied to differentiate pathological groups with sensitivity analyses performed to assess the influence of voxel size and region removal. A radial basis function was also prepared to create a secondary model using the most important voxels. The models were optimized on the main dataset (n\u2009=\u2009104), and their performance was compared with the magnetic resonance parkinsonism index measured on MRI in the independent test dataset (n\u2009=\u200933).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The model had the highest accuracy (0.91) and F\u2010score (0.86) when voxel size was 6mm. In this optimized model, important voxels for differentiating the groups were observed in the thalamus, midbrain, and cerebellar dentate. The secondary models found the combination of thalamus and dentate to have the highest accuracy (0.89) and F\u2010score (0.81). The optimized secondary model showed the highest accuracy (0.91) and F\u2010scores (0.86) in the test dataset and outperformed the magnetic resonance parkinsonism index (0.81 and 0.70, respectively).<\/jats:p><\/jats:sec><jats:sec><jats:title>Interpretation<\/jats:title><jats:p>The results suggest that glucose hypometabolism in the thalamus and cerebellar dentate have the highest potential for predicting PSP pathology. Our optimized machine learning model outperformed the best currently available biomarker to predict PSP pathology. ANN NEUROL 2025;98:410\u2013420<\/jats:p><\/jats:sec>","DOI":"10.1002\/ana.27265","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T06:10:02Z","timestamp":1748585402000},"page":"410-420","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine Learning Models of Voxel\u2010Level [<sup>18<\/sup>F] Fluorodeoxyglucose Positron Emission Tomography Data Excel at Predicting Progressive Supranuclear Palsy Pathology"],"prefix":"10.1002","volume":"98","author":[{"given":"Addison S.","family":"Braun","sequence":"first","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester MN"},{"name":"Department of Neurology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3418-2987","authenticated-orcid":false,"given":"Ryota","family":"Satoh","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nha Trang Thu","family":"Pham","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3614-9179","authenticated-orcid":false,"given":"Neha","family":"Singh\u2010Reilly","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farwa","family":"Ali","sequence":"additional","affiliation":[{"name":"Department of Neurology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7189-7917","authenticated-orcid":false,"given":"Dennis W.","family":"Dickson","sequence":"additional","affiliation":[{"name":"Department of Neuroscience Mayo Clinic  Jacksonville FL"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Val J.","family":"Lowe","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6914-1563","authenticated-orcid":false,"given":"Jennifer L.","family":"Whitwell","sequence":"additional","affiliation":[{"name":"Department of Radiology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2930-8634","authenticated-orcid":false,"given":"Keith A.","family":"Josephs","sequence":"additional","affiliation":[{"name":"Department of Neurology Mayo Clinic  Rochester MN"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/arclin\/acs098"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awm032"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.26987"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(09)70042-0"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30157-6"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.27619"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.10488"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/jon.12932"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.2463\/mrms.3.125"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2453061703"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.28901"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2022.9588"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.21933"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocn.2020.06.008"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.116.186403"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.4103\/aian.aian_642_21"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.2967\/jnumed.121.263194"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-024-12350-z"},{"key":"e_1_2_9_20_1","first-page":"1741","article-title":"Differential diagnosis of parkinsonism based on deep metabolic imaging indices","volume":"63","author":"Wu P","year":"2022","journal-title":"J Nucl Med"},{"key":"e_1_2_9_21_1","first-page":"3531","article-title":"A 3D deep residual convolutional neural network for differential diagnosis of parkinsonian syndromes on (18)F\u2010FDG PET images","volume":"2019","author":"Zhao Y","year":"2019","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parkreldis.2013.10.023"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1097\/00005072-199601000-00010"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1097\/WCO.0b013e32833be924"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/aws032"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cortex.2015.05.013"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2017.01.014"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e31821103e6"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awr179"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/alz.14076"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1212\/CPJ.0000000000000708"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1532-5415.2005.53221.x"},{"key":"e_1_2_9_33_1","volume-title":"Western aphasia battery\u2010\u2010revised","author":"Kertesz A","year":"2007"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/mds.22340"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1001\/archneurol.2011.107"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1002\/gps.4756"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.17.5.427"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/jnen\/61.11.935"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000004058"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-009-0612-2"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-011-0910-3"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-013-1171-0"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awm336"},{"key":"e_1_2_9_44_1","volume-title":"A practical guide to support vector classification","author":"Hsu C\u2010W","year":"2003"},{"key":"e_1_2_9_45_1","first-page":"P792","article-title":"The Mayo clinic adult lifespan template: better quantification across the lifespan","volume":"13","author":"Schwarz C","year":"2018","journal-title":"Alzheimers Dement J Alzheimer Assoc"},{"key":"e_1_2_9_46_1","first-page":"53","volume-title":"Proceedings of the Workshop on the Causation and Prediction Challenge at WCCI 2008","author":"Chang Y\u2010W","year":"2008"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"}],"container-title":["Annals of Neurology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ana.27265","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,21]],"date-time":"2025-07-21T09:13:38Z","timestamp":1753089218000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ana.27265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["10.1002\/ana.27265"],"URL":"https:\/\/doi.org\/10.1002\/ana.27265","archive":["Portico"],"relation":{},"ISSN":["0364-5134","1531-8249"],"issn-type":[{"value":"0364-5134","type":"print"},{"value":"1531-8249","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]},"assertion":[{"value":"2024-09-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}