001047431 001__ 1047431
001047431 005__ 20251031202035.0
001047431 0247_ $$2doi$$a10.1016/j.compbiomed.2025.111182
001047431 0247_ $$2ISSN$$a0010-4825
001047431 0247_ $$2ISSN$$a1879-0534
001047431 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04294
001047431 037__ $$aFZJ-2025-04294
001047431 082__ $$a570
001047431 1001_ $$0P:(DE-Juel1)180946$$aAntonopoulos, Georgios$$b0$$eCorresponding author
001047431 245__ $$aRegion-wise stacking ensembles for estimating brain-age using structural MRI
001047431 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2025
001047431 3367_ $$2DRIVER$$aarticle
001047431 3367_ $$2DataCite$$aOutput Types/Journal article
001047431 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1761910447_27254
001047431 3367_ $$2BibTeX$$aARTICLE
001047431 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001047431 3367_ $$00$$2EndNote$$aJournal Article
001047431 520__ $$aPredictive modeling using structural magnetic resonance imaging (MRI) data is a prominent approach to study brain-aging. Machine learning frameworks have been employed to improve predictions and explore healthy and accelerated aging due to diseases. The high-dimensional MRI data pose challenges to building generalizable and interpretable models as well as for data privacy. Common practices are resampling or averaging voxels within predefined parcels which reduces anatomical specificity and biological interpretability. Effectively, naive fusion by averaging can result in information loss and reduced accuracy. We present a conceptually novel two-level stacking ensemble (SE) approach. The first level comprises regional models for predicting individuals' age based on voxel-wise information, fused by a second-level model yielding final predictions. Eight data fusion scenarios were explored using Gray matter volume (GMV) estimates from four large datasets. Performance measured using mean absolute error (MAE), R2, correlation and prediction bias, showed that SE outperformed the region-wise averages. The best performance was obtained when first-level regional predictions were obtained as out-of-sample predictions on the application site with second-level models trained on independent and site-specific data (MAE = 4.75 vs baseline regional mean GMV MAE = 5.68). Performance improved as more datasets were used for training. First-level predictions showed improved and more robust aging signal providing new biological insights and enhanced data privacy. Overall, the SE improves accuracy compared to the baseline while preserving or enhancing data privacy. Finally, we show the utility of our SE model on a clinical cohort showing accelerated aging in cognitively impaired and Alzheimer's disease patients.
001047431 536__ $$0G:(DE-HGF)POF4-5252$$a5252 - Brain Dysfunction and Plasticity (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001047431 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001047431 7001_ $$0P:(DE-Juel1)177823$$aMore, Shammi$$b1
001047431 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b2
001047431 7001_ $$0P:(DE-Juel1)185083$$aRaimondo, Federico$$b3
001047431 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh R.$$b4
001047431 773__ $$0PERI:(DE-600)1496984-1$$a10.1016/j.compbiomed.2025.111182$$gVol. 198, p. 111182 -$$p111182 -$$tComputers in biology and medicine$$v198$$x0010-4825$$y2025
001047431 8564_ $$uhttps://juser.fz-juelich.de/record/1047431/files/1-s2.0-S0010482525015355-main.pdf$$yOpenAccess
001047431 909CO $$ooai:juser.fz-juelich.de:1047431$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001047431 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180946$$aForschungszentrum Jülich$$b0$$kFZJ
001047431 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b2$$kFZJ
001047431 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)131678$$a HHU Düsseldorf$$b2
001047431 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185083$$aForschungszentrum Jülich$$b3$$kFZJ
001047431 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b4$$kFZJ
001047431 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5252$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001047431 9141_ $$y2025
001047431 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-18
001047431 915__ $$0LIC:(DE-HGF)CCBYNCND4$$2HGFVOC$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
001047431 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bCOMPUT BIOL MED : 2022$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001047431 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bCOMPUT BIOL MED : 2022$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-18
001047431 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz$$d2024-12-18$$wger
001047431 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-18
001047431 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001047431 980__ $$ajournal
001047431 980__ $$aVDB
001047431 980__ $$aUNRESTRICTED
001047431 980__ $$aI:(DE-Juel1)INM-7-20090406
001047431 9801_ $$aFullTexts