Explainable machine learning algorithm predicting working memory performance in Parkinson’s disease using task-fMRI
Background Parkinson’s disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance im...
Uloženo v:
| Vydáno v: | Journal of neurology Ročník 272; číslo 10; s. 692 |
|---|---|
| Hlavní autoři: | , , , , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Berlin/Heidelberg
Springer Berlin Heidelberg
14.10.2025
Springer Nature B.V |
| Témata: | |
| ISSN: | 0340-5354, 1432-1459, 1432-1459 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Background
Parkinson’s disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data.
Methods
We enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an
n
-back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs.
Results
The model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model’s decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance.
Conclusions
We developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice. |
|---|---|
| AbstractList | Parkinson's disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data.BACKGROUNDParkinson's disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data.We enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an n-back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs.METHODSWe enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an n-back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs.The model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model's decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance.RESULTSThe model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model's decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance.We developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice.CONCLUSIONSWe developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice. BackgroundParkinson’s disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data.MethodsWe enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an n-back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs.ResultsThe model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model’s decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance.ConclusionsWe developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice. Parkinson's disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data. We enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an n-back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs. The model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model's decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance. We developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice. Background Parkinson’s disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning offers an advantage for decoding complex brain activity patterns, but its application to task-based functional magnetic resonance imaging (task-based fMRI) has been limited. This study aimed to develop an explainable machine learning model to classify WM performance levels in PD based on task-based fMRI data. Methods We enrolled 45 patients with PD and 15 healthy controls (HCs), all of whom performed an n -back WM task in an MRI scanner. Patients were stratified into three subgroups based on their 3-back task performance: better, intermediate, and worse WM. A three-dimensional convolutional neural network (3D-CNN) model, pre-trained with a 3D convolutional autoencoder, was developed to perform binary classifications between group pairs. Results The model achieved an accuracy of 93.3% in discriminating task-based fMRI images of PD patients with worse WM from HCs, surpassing the mean accuracy of three expert radiologists (70.0%). Saliency maps identified brain regions influencing the model’s decisions, including the dorsolateral prefrontal cortex and superior/inferior parietal lobules. These regions were consistent with both the areas with intergroup differences in the task-based fMRI data and the anatomical areas that are crucial for better WM performance. Conclusions We developed an explainable deep learning model that is capable of classifying WM performance levels in PD using task-based fMRI. This approach may enhance the objective and interpretable assessment of brain function in clinical neuroimaging practice. |
| ArticleNumber | 692 |
| Author | Hase, Takeshi Yamagiwa, Ken Matsuzawa, Hitoshi Hallett, Mark Shimano, Kaoru Yasuda, Eiji Oyama, Jun Hattori, Takaaki Kawauchi, Miho Horovitz, Silvina G. Lungu, Codrin |
| Author_xml | – sequence: 1 givenname: Eiji surname: Yasuda fullname: Yasuda, Eiji organization: Department of Neurology and Neurological Science, Institute of Science Tokyo – sequence: 2 givenname: Takaaki orcidid: 0000-0002-4802-8606 surname: Hattori fullname: Hattori, Takaaki email: takaaki-hattori@umin.ac.jp organization: Department of Neurology and Neurological Science, Institute of Science Tokyo, Human Motor Control Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health – sequence: 3 givenname: Kaoru surname: Shimano fullname: Shimano, Kaoru organization: Department of Neurology and Neurological Science, Institute of Science Tokyo – sequence: 4 givenname: Takeshi surname: Hase fullname: Hase, Takeshi organization: Center for Education in Healthcare Innovation, Institute of Science Tokyo, The Systems Biology Institute, SBX BioSciences, Inc., Faculty of Pharmacy, Keio University, Center for Mathematical Modelling and Data Science, Osaka University – sequence: 5 givenname: Jun surname: Oyama fullname: Oyama, Jun organization: Department of Diagnostic Radiology, Institute of Science Tokyo – sequence: 6 givenname: Ken surname: Yamagiwa fullname: Yamagiwa, Ken organization: Department of Diagnostic Radiology, Institute of Science Tokyo – sequence: 7 givenname: Miho surname: Kawauchi fullname: Kawauchi, Miho organization: Department of Diagnostic Radiology, Institute of Science Tokyo – sequence: 8 givenname: Silvina G. surname: Horovitz fullname: Horovitz, Silvina G. organization: Human Motor Control Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health – sequence: 9 givenname: Codrin surname: Lungu fullname: Lungu, Codrin organization: Division of Clinical Research, National Institute of Neurological Disorders and Stroke, National Institutes of Health – sequence: 10 givenname: Hitoshi surname: Matsuzawa fullname: Matsuzawa, Hitoshi organization: Center for Integrated Human Brain Science, Brain Research Institute, Niigata University, Center for Advanced Medicine and Clinical Research, Sapporo Hakuyokai Hospital – sequence: 11 givenname: Mark surname: Hallett fullname: Hallett, Mark organization: Human Motor Control Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/41085732$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kc1u1TAQhS1URG8LL8ACWWLDJjD-vckSVQUqFYEQrC0nGd-6TexgJ7p0x2vwejwJTm8BiQWrkc58Z2Y054QchRiQkKcMXjKA7asMIJmqgKuKCSnqav-AbJgUvGJSNUdkA0JCpYSSx-Qk52sAqEvjETmWDGq1FXxDlvNv02B9sO2AdLTdlQ9IB7Qp-LCjdtjF5OerkU4Je9_Nq7iP6WatI44x3dIJk4tptKFD6gP9aNdujuHn9x-Z9j6jzUiXvDpmm28q9_7TxWPy0Nkh45P7ekq-vDn_fPauuvzw9uLs9WXVCV7PFcOmQS2w18x2olZO6FaD1g6kxZ61tRKs2XLLusaJWvDW6bbIjvUcW8W0OCUvDnOnFL8umGcz-tzhMNiAcclGcA01KKFlQZ__g17HJYVy3R3VAJdQF-rZPbW0I_ZmSn606db8fmgB-AHoUsw5ofuDMDBrauaQmimpmbvUzL6YxMGUCxx2mP7u_o_rF6hAnDQ |
| Cites_doi | 10.1109/CSDE53843.2021.9718485 10.1111/j.1460-9568.2004.03438.x 10.1016/j.patcog.2015.03.009 10.1136/jnnp.55.3.181 10.1080/13803391003596421 10.1016/j.nicl.2022.103100 10.1101/lm.024018.111 10.1523/JNEUROSCI.23-15-06351.2003 10.3390/s20185097 10.3934/mbe.2024272 10.1016/j.patcog.2022.109031 10.1016/j.neuroimage.2016.05.051 10.1037/h0043688 10.1016/s0028-3932(02)00257-9 10.1590/1516-4446-2012-1048 10.1016/j.cub.2009.12.014 10.1002/mrm.1910250220 10.1038/s41598-019-54548-6 10.1016/j.neuroimage.2011.12.028 10.3390/s21227731 10.1126/science.1127647 10.48550/arXiv.1312.6034 10.1002/mds.25866 10.3390/e23010018 10.1109/ICSAI.2018.8599448 10.1007/s00221-010-2326-z 10.1590/s0004-282x2008000200001 |
| ContentType | Journal Article |
| Copyright | Springer-Verlag GmbH Germany, part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. 2025. Springer-Verlag GmbH Germany, part of Springer Nature. Springer-Verlag GmbH Germany, part of Springer Nature 2025. |
| Copyright_xml | – notice: Springer-Verlag GmbH Germany, part of Springer Nature 2025 Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. – notice: 2025. Springer-Verlag GmbH Germany, part of Springer Nature. – notice: Springer-Verlag GmbH Germany, part of Springer Nature 2025. |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7TK K9. 7X8 |
| DOI | 10.1007/s00415-025-13438-w |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Neurosciences Abstracts ProQuest Health & Medical Complete (Alumni) MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) ProQuest Health & Medical Complete (Alumni) Neurosciences Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic ProQuest Health & Medical Complete (Alumni) MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1432-1459 |
| ExternalDocumentID | 41085732 10_1007_s00415_025_13438_w |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: National Institute of Neurological Disorders and Stroke funderid: http://dx.doi.org/10.13039/100000065 – fundername: Niigata University grantid: Collaborative Research Project “2019-01” of Brain Research Institute funderid: http://dx.doi.org/10.13039/100012833 – fundername: Niigata University grantid: Collaborative Research Project "2019-01" of Brain Research Institute |
| GroupedDBID | --- .86 .VR 06C 06D 0R~ 0VY 199 1N0 203 29L 29~ 2J2 2JN 2JY 2KG 2KM 2LR 2~H 30V 36B 4.4 406 408 409 40D 40E 5RE 5VS 67Z 6NX 78A 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAPKM AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN ABAKF ABBBX ABBRH ABBXA ABDBE ABDZT ABECU ABFSG ABFTV ABHLI ABHQN ABIPD ABJNI ABJOX ABKCH ABKTR ABLJU ABMNI ABMQK ABNWP ABPLI ABQBU ABRTQ ABSXP ABTEG ABTKH ABTMW ABUWZ ABWNU ABXPI ACAOD ACDTI ACGFS ACHSB ACHXU ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACPRK ACSTC ACZOJ ADBBV ADHIR ADIMF ADKNI ADKPE ADRFC ADTPH ADURQ ADYFF ADZKW AEFQL AEGAL AEGNC AEJHL AEJRE AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AEZWR AFBBN AFDZB AFHIU AFJLC AFLOW AFOHR AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGVAE AGWIL AGWZB AGYKE AHAVH AHBYD AHIZS AHKAY AHMBA AHPBZ AHSBF AHWEU AHYZX AIAKS AIGIU AIIXL AILAN AITGF AIXLP AJRNO AJZVZ AKMHD ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AOCGG ARMRJ ATHPR AXYYD AYFIA AZFZN B-. BA0 BENPR BSONS CSCUP DDRTE DL5 DNIVK DPUIP DU5 EBLON EBS EIOEI EPAXT ESBYG F5P FEDTE FERAY FFXSO FIGPU FNLPD FRRFC FWDCC G-Y G-Z GGCAI GGRSB GJIRD GNWQR GQ7 GQ8 GXS HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ IHE IJ- IKXTQ IMOTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JBSCW JCJTX JZLTJ KDC KOV KPH LAS LLZTM MA- N9A NB0 NPVJJ NQJWS O93 O9G O9I O9J OAM P19 P2P P9S PF0 PT4 PT5 QOK QOR QOS R89 R9I RHV RNS ROL RPX RRX RSV S16 S1Z S27 S37 S3B SAP SDH SDM SHX SISQX SJYHP SMD SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW SSXJD STPWE SZ9 SZN T13 TSG TSK TSV TT1 TUC U2A U9L UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WJK WK8 YLTOR Z45 ZMTXR ZOVNA ~EX ~KM -Y2 .55 .GJ 2.D 28- 2P1 2VQ 3SX 53G 5QI 7X7 88E 8AO 8FI 8FJ AANXM AARHV AAYTO AAYXX ABQSL ABULA ABUWG ACBXY ACUDM ADHKG AEBTG AEFIE AEKMD AFDYV AFEXP AFFHD AFFNX AFKRA AGGDS AGQPQ AJBLW BBWZM BDATZ BGNMA BPHCQ BVXVI CAG CCPQU CITATION COF EBD EJD EMB EMOBN EN4 FINBP FSGXE FYUFA GRRUI H13 HMCUK KOW M1P M4Y N2Q NDZJH NU0 O9- OVD PHGZM PHGZT PJZUB PPXIY PQQKQ PROAC PSQYO Q2X RNI RZK S26 S28 SCLPG SDE SV3 T16 TEORI UKHRP WK6 X7M ZGI ZXP CGR CUY CVF ECM EIF NPM 7TK K9. 7X8 |
| ID | FETCH-LOGICAL-c328t-1e99e63ed61ac385f36b6066f04aed1b8531972a1c9f3832bf6bd1bf1d2eb5163 |
| IEDL.DBID | RSV |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001594157900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0340-5354 1432-1459 |
| IngestDate | Wed Oct 15 09:51:24 EDT 2025 Wed Nov 05 08:28:30 EST 2025 Wed Oct 29 02:17:49 EDT 2025 Sat Nov 29 07:01:40 EST 2025 Wed Oct 29 01:24:54 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Keywords | Working memory Task-based fMRI Parkinson’s disease 3D convolutional neural network Explainable machine learning 3D convolutional autoencoder |
| Language | English |
| License | 2025. Springer-Verlag GmbH Germany, part of Springer Nature. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c328t-1e99e63ed61ac385f36b6066f04aed1b8531972a1c9f3832bf6bd1bf1d2eb5163 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-4802-8606 |
| PMID | 41085732 |
| PQID | 3260902408 |
| PQPubID | 47196 |
| ParticipantIDs | proquest_miscellaneous_3260805364 proquest_journals_3260902408 pubmed_primary_41085732 crossref_primary_10_1007_s00415_025_13438_w springer_journals_10_1007_s00415_025_13438_w |
| PublicationCentury | 2000 |
| PublicationDate | 20251014 |
| PublicationDateYYYYMMDD | 2025-10-14 |
| PublicationDate_xml | – month: 10 year: 2025 text: 20251014 day: 14 |
| PublicationDecade | 2020 |
| PublicationPlace | Berlin/Heidelberg |
| PublicationPlace_xml | – name: Berlin/Heidelberg – name: Germany – name: Heidelberg |
| PublicationTitle | Journal of neurology |
| PublicationTitleAbbrev | J Neurol |
| PublicationTitleAlternate | J Neurol |
| PublicationYear | 2025 |
| Publisher | Springer Berlin Heidelberg Springer Nature B.V |
| Publisher_xml | – name: Springer Berlin Heidelberg – name: Springer Nature B.V |
| References | K Oh (13438_CR22) 2019; 9 W Zeng (13438_CR30) 2024; 21 T-T Wong (13438_CR29) 2015 YB Dumitru Erhan (13438_CR7) 2010; 11 T Hattori (13438_CR10) 2022; 35 13438_CR25 SJ Lewis (13438_CR18) 2003; 41 AJ Hughes (13438_CR12) 1992; 55 GE Hinton (13438_CR11) 2006; 313 SJ Lewis (13438_CR19) 2003; 23 E Pintelas (13438_CR23) 2021; 20 Z Hussain (13438_CR13) 2017; 2017 D Bor (13438_CR4) 2004; 19 P Kundu (13438_CR17) 2012; 60 13438_CR5 P Linardatos (13438_CR20) 2021; 23 S Abbas (13438_CR24) 2023; 133 WK Kirchner (13438_CR16) 1958; 55 A Jeneson (13438_CR14) 2012; 19 BC Haatveit (13438_CR9) 2010; 32 S Shomstein (13438_CR26) 2010; 206 13438_CR15 SP Singh (13438_CR27) 2020; 20 A Baddeley (13438_CR1) 2010; 20 R Beato (13438_CR3) 2008; 66 PA Bandettini (13438_CR2) 1992; 25 YP Wang (13438_CR28) 2013; 35 L Yu (13438_CR21) 2022; 131 J Davey (13438_CR6) 2016; 137 JG Goldman (13438_CR8) 2014; 29 |
| References_xml | – ident: 13438_CR25 doi: 10.1109/CSDE53843.2021.9718485 – volume: 19 start-page: 3365 year: 2004 ident: 13438_CR4 publication-title: Eur J Neurosci doi: 10.1111/j.1460-9568.2004.03438.x – year: 2015 ident: 13438_CR29 publication-title: Pattern Recognit doi: 10.1016/j.patcog.2015.03.009 – volume: 55 start-page: 181 year: 1992 ident: 13438_CR12 publication-title: J Neurol Neurosurg Psychiatry doi: 10.1136/jnnp.55.3.181 – volume: 32 start-page: 871 year: 2010 ident: 13438_CR9 publication-title: J Clin Exp Neuropsychol doi: 10.1080/13803391003596421 – volume: 35 year: 2022 ident: 13438_CR10 publication-title: Neuroimage Clin doi: 10.1016/j.nicl.2022.103100 – volume: 2017 start-page: 979 year: 2017 ident: 13438_CR13 publication-title: AMIA Annu Symp Proc – volume: 11 start-page: 625 year: 2010 ident: 13438_CR7 publication-title: J Mach Learn Res – volume: 19 start-page: 15 year: 2012 ident: 13438_CR14 publication-title: Learn Mem doi: 10.1101/lm.024018.111 – volume: 23 start-page: 6351 year: 2003 ident: 13438_CR19 publication-title: J Neurosci doi: 10.1523/JNEUROSCI.23-15-06351.2003 – volume: 20 year: 2020 ident: 13438_CR27 publication-title: Sensors doi: 10.3390/s20185097 – volume: 21 start-page: 6190 year: 2024 ident: 13438_CR30 publication-title: Math Biosci Eng doi: 10.3934/mbe.2024272 – volume: 133 year: 2023 ident: 13438_CR24 publication-title: Pattern Recognit doi: 10.1016/j.patcog.2022.109031 – volume: 137 start-page: 165 year: 2016 ident: 13438_CR6 publication-title: Neuroimage doi: 10.1016/j.neuroimage.2016.05.051 – volume: 55 start-page: 352 year: 1958 ident: 13438_CR16 publication-title: J Exp Psychol doi: 10.1037/h0043688 – volume: 41 start-page: 645 year: 2003 ident: 13438_CR18 publication-title: Neuropsychologia doi: 10.1016/s0028-3932(02)00257-9 – volume: 35 start-page: 416 year: 2013 ident: 13438_CR28 publication-title: Braz J Psychiatry doi: 10.1590/1516-4446-2012-1048 – volume: 20 start-page: R136 year: 2010 ident: 13438_CR1 publication-title: Curr Biol doi: 10.1016/j.cub.2009.12.014 – volume: 25 start-page: 390 year: 1992 ident: 13438_CR2 publication-title: Magn Reson Med doi: 10.1002/mrm.1910250220 – volume: 9 start-page: 18150 year: 2019 ident: 13438_CR22 publication-title: Sci Rep doi: 10.1038/s41598-019-54548-6 – volume: 60 start-page: 1759 year: 2012 ident: 13438_CR17 publication-title: Neuroimage doi: 10.1016/j.neuroimage.2011.12.028 – volume: 20 issue: 18 year: 2021 ident: 13438_CR23 publication-title: Sensors doi: 10.3390/s21227731 – volume: 313 start-page: 504 year: 2006 ident: 13438_CR11 publication-title: Science doi: 10.1126/science.1127647 – ident: 13438_CR15 doi: 10.48550/arXiv.1312.6034 – volume: 29 start-page: 608 year: 2014 ident: 13438_CR8 publication-title: Mov Disord doi: 10.1002/mds.25866 – volume: 23 start-page: 18 year: 2021 ident: 13438_CR20 publication-title: Entropy doi: 10.3390/e23010018 – ident: 13438_CR5 doi: 10.1109/ICSAI.2018.8599448 – volume: 206 start-page: 197 year: 2010 ident: 13438_CR26 publication-title: Exp Brain Res doi: 10.1007/s00221-010-2326-z – volume: 66 start-page: 147 year: 2008 ident: 13438_CR3 publication-title: Arq Neuropsiquiatr doi: 10.1590/s0004-282x2008000200001 – volume: 131 start-page: 108876 year: 2022 ident: 13438_CR21 publication-title: Pattern Recognit doi: 10.3390/e23010018 |
| SSID | ssj0008459 |
| Score | 2.4661503 |
| Snippet | Background
Parkinson’s disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine... Parkinson's disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine learning... BackgroundParkinson’s disease (PD) is a neurodegenerative disorder that affects both motor and cognitive functions, particularly working memory (WM). Machine... |
| SourceID | proquest pubmed crossref springer |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 692 |
| SubjectTerms | Activity patterns Aged Algorithms Alzheimer's disease Brain - diagnostic imaging Brain - physiopathology Brain research Cognition & reasoning Cognitive ability Consent Cortex (parietal) Data processing Decision making Deep learning Female Functional magnetic resonance imaging Humans Learning algorithms Machine Learning Magnetic resonance imaging Magnetic Resonance Imaging - methods Male Medical imaging Medicine Medicine & Public Health Memory Memory, Short-Term - physiology Middle Aged Movement disorders Neural networks Neural Networks, Computer Neurodegenerative diseases Neuroimaging Neurological disorders Neurology Neuroradiology Neurosciences Original Communication Parkinson Disease - complications Parkinson Disease - diagnostic imaging Parkinson Disease - physiopathology Parkinson Disease - psychology Parkinson's disease Prefrontal cortex Scanners |
| Title | Explainable machine learning algorithm predicting working memory performance in Parkinson’s disease using task-fMRI |
| URI | https://link.springer.com/article/10.1007/s00415-025-13438-w https://www.ncbi.nlm.nih.gov/pubmed/41085732 https://www.proquest.com/docview/3260902408 https://www.proquest.com/docview/3260805364 |
| Volume | 272 |
| WOSCitedRecordID | wos001594157900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1432-1459 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008459 issn: 0340-5354 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NTtwwEB4VihCX_kEhLUWu1BtYimMncY5VVdRKBVW0oL1FcTJeVnSzq02WVW99jb5en6S24wQh4NBeE8exPJ4fe75vDPDO7JFFgk4CmFKBGo0dLJGaUJ_HhZKKuYo3F1_S01M5GmVfPSms6dHufUrSWeqB7GZLQ1k2cUwZF0ZNV2vw2Lg7adXx7NvFYH-lcFekhVyENOax8FSZ-_u47Y7uxJh38qPO7Rw__b8BP4MnPswk77t18RweYf0CNk98In0blhZ754lTZOoAlUj8DRJjUvwYzxaT9nJK5gv7iYVGk1V3rE6mFpv7k8xvGAdkUhPLnnZEsj-_fjfEp32IRdWPSVs0V1SfnH3egfPjj98_fKL-BgZa8ki2lGGWYcKxSlhRchlrnii749GhKLBiSloNTqOClZk2W91I6USZx5pVEarYhHovYb2e1bgHRCSiUKiELiUzDhEzwapMx6gjlfGqVAEc9oLI512hjXwoqexmMjczmbuZzFcB7Peyyr3SNbmJRC3KVIQygLfDa6MuNgdS1Dhbdm2kMTyJCGC3k_HwO2GZGCmPAjjqBXrT-cNjefVvzV_DVuTWREiZ2If1drHEN7BRXreTZnEAa-lIHrgF_RfPyfGN |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NbtQwEB5BQdALFCg0UFojcQNLcexknSNCVK3YXVWlVL1FcTLerspmV5ssK259jb4eT4LtOKlQ4QDXxHEsj-fHnu8bA7w1e2SRoJMADqhAjcYOFkhNqM_jXEnFXMWbs-FgPJbn5-mxJ4XVHdq9S0k6S92T3WxpKMsmjinjwqjp-i7cE8ZjWSDfyZez3v5K4a5IC7kIacxj4akyf-7jd3d0K8a8lR91bufg8f8NeAse-TCTfGjXxRO4g9VTeDDyifRnsLLYO0-cIjMHqETib5CYkPzbZL6cNhczsljaTyw0mqzbY3Uys9jcH2Rxwzgg04pY9rQjkv28uq6JT_sQi6qfkCavL6kenRxtw9eDT6cfD6m_gYEWPJINZZimmHAsE5YXXMaaJ8rueHQociyZklaDB1HOilSbrW6kdKLMY83KCFVsQr3nsFHNK9wBIhKRK1RCF5IZh4ipYGWqY9SRSnlZqADedYLIFm2hjawvqexmMjMzmbmZzNYB7HayyrzS1ZmJRC3KVIQygDf9a6MuNgeSVzhftW2kMTyJCOBFK-P-d8IyMQY8CuB9J9Cbzv8-lpf_1nwfHh6ejobZ8Gj8-RVsRm59hJSJXdholit8DfeL7820Xu65Zf0LeevziQ |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1RT9swED4xmBAvDLYBGTA8ibfNIo6d1HlE2yrQoELAEG9RnJxLBU2rNqXaG3-Dv7dfMttJwxDsYeI1cZzId2ff5b7vDmDXxMgiQicBbFGBGs0-mCE1rj4PUyUVcxVvLo5anY68vIxP_mLxO7T7LCVZcRpslaai3Bvmeq8hvtkyUZZZHFLGhTHZ6StYELZpkI3Xzy6avVgK1y7N58KnIQ9FTZt5fo7HR9MTf_NJrtQdQe03L__4FViu3U-yX-nLKsxh8RYWj-sE-zuYWExeTagifQe0RFJ3luiS9KY7GPXKqz4ZjuwjFjJNptXvdtK3mN1fZPjARCC9glhWtSOY_b67H5M6HUQs2r5LynR8TfXx6eF7-Nn-fv71gNadGWjGA1lShnGMEcc8YmnGZah5pGwkpH2RYs6UtJbdClKWxdqEwIHSkTKXNcsDVKFxAddgvhgUuAFERCJVqITOJDMHJcaC5bEOUQcq5nmmPPg8E0oyrApwJE2pZbeSiVnJxK1kMvVgaya3pDbGcWI8VIs-Fb704FNz25iRzY2kBQ4m1RhpNqRIeLBeybt5nVWssMUDD77MhPsw-b-_5cP_Dd-BxZNv7eTosPNjE5YCpx4-ZWIL5svRBLfhdXZb9sajj07D_wB_l_xt |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Explainable+machine+learning+algorithm+predicting+working+memory+performance+in+Parkinson%E2%80%99s+disease+using+task-fMRI&rft.jtitle=Journal+of+neurology&rft.au=Yasuda%2C+Eiji&rft.au=Hattori%2C+Takaaki&rft.au=Shimano%2C+Kaoru&rft.au=Hase%2C+Takeshi&rft.date=2025-10-14&rft.pub=Springer+Berlin+Heidelberg&rft.issn=0340-5354&rft.eissn=1432-1459&rft.volume=272&rft.issue=10&rft_id=info:doi/10.1007%2Fs00415-025-13438-w&rft.externalDocID=10_1007_s00415_025_13438_w |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0340-5354&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0340-5354&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0340-5354&client=summon |