001034776 001__ 1034776
001034776 005__ 20250203103400.0
001034776 0247_ $$2doi$$a10.1101/2024.02.02.24302198
001034776 037__ $$aFZJ-2024-07530
001034776 1001_ $$0P:(DE-Juel1)187351$$aKomeyer, Vera$$b0$$eCorresponding author
001034776 245__ $$aConfounder control in biomedicine necessitates conceptual considerations beyond statistical evaluations
001034776 260__ $$c2024
001034776 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1736237966_17716
001034776 3367_ $$2ORCID$$aWORKING_PAPER
001034776 3367_ $$028$$2EndNote$$aElectronic Article
001034776 3367_ $$2DRIVER$$apreprint
001034776 3367_ $$2BibTeX$$aARTICLE
001034776 3367_ $$2DataCite$$aOutput Types/Working Paper
001034776 520__ $$aMachine learning (ML) models hold promise in precision medicine by enabling personalized predictions basedon high-dimensional biomedical data. Yet, transitioning models from prototyping to clinical applications poseschallenges, with confounders being a significant hurdle by undermining the reliability, generalizability, andinterpretability of ML models. Using hand grip strength (HGS) prediction from neuroimaging data from theUK Biobank as a case study, we demonstrate that confounder adjustment can have a greater impact on modelperformance than changes in features or algorithms. An ubiquitous and necessary approach to confounding isby statistical means. However, a pure statistical viewpoint overlooks the biomedical relevance of candidateconfounders, i.e. their biological link and conceptual similarity to actual variables of interest. Problematically,this can lead to biomedically not-meaningful confounder-adjustment, which limits the usefulness of resultingmodels, both in terms of biological insights and clinical applicability. To address this, we propose a two-dimensional framework, the Confound Continuum, that combines both statistical association and biomedicalrelevance, i.e. conceptual similarity, of a candidate confounder. The evaluation of conceptual similarityassesses on a continuum how much two variables overlap in their biological meaning, ranging from negligiblelinks to expressing the same underlying biology. It thereby acknowledges the gradual nature of the biologicallink between candidate confounders and a predictive task. Our framework aims to create awareness for theimperative need to complement statistical confounder considerations with biomedical, conceptual domainknowledge (without going into causal considerations) and thereby offers a means to arrive at meaningful andinformed confounder decisions. The position of a candidate confoudner in the two-dimensional grid of theConfound Continuum can support informed and context-specific confounder decisions and thereby not onlyenhance biomedical validity of predictions but also support translation of predictive models into clinicalpractice.
001034776 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001034776 536__ $$0G:(GEPRIS)431549029$$aDFG project G:(GEPRIS)431549029 - SFB 1451: Schlüsselmechanismen normaler und krankheitsbedingt gestörter motorischer Kontrolle (431549029)$$c431549029$$x1
001034776 588__ $$aDataset connected to DataCite
001034776 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b1
001034776 7001_ $$0P:(DE-Juel1)161406$$aGrefkes, Christian$$b2
001034776 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh R.$$b3
001034776 7001_ $$0P:(DE-Juel1)185083$$aRaimondo, Federico$$b4$$eCorresponding author$$ufzj
001034776 773__ $$a10.1101/2024.02.02.24302198$$tmedrxiv$$y2024
001034776 8564_ $$uhttps://www.medrxiv.org/content/10.1101/2024.02.02.24302198v2.full.pdf+html
001034776 909CO $$ooai:juser.fz-juelich.de:1034776$$pVDB
001034776 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187351$$aForschungszentrum Jülich$$b0$$kFZJ
001034776 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b1$$kFZJ
001034776 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)161406$$aForschungszentrum Jülich$$b2$$kFZJ
001034776 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b3$$kFZJ
001034776 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185083$$aForschungszentrum Jülich$$b4$$kFZJ
001034776 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)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001034776 9141_ $$y2024
001034776 920__ $$lyes
001034776 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001034776 9201_ $$0I:(DE-Juel1)INM-3-20090406$$kINM-3$$lKognitive Neurowissenschaften$$x1
001034776 980__ $$apreprint
001034776 980__ $$aVDB
001034776 980__ $$aI:(DE-Juel1)INM-7-20090406
001034776 980__ $$aI:(DE-Juel1)INM-3-20090406
001034776 980__ $$aUNRESTRICTED