Gast ::
| Hauptseite > Publikationsdatenbank > Confound-leakage: Confound Removal in Machine Learning Leads to Leakage > print |
| Hauptseite > Publikationsdatenbank > Confound-leakage: Confound Removal in Machine Learning Leads to Leakage > print |
| 001 | 1010545 | ||
| 005 | 20240429104900.0 | ||
| 024 | 7 | _ | |a 10.1093/gigascience/giad071 |2 doi |
| 024 | 7 | _ | |a 10.34734/FZJ-2023-03119 |2 datacite_doi |
| 024 | 7 | _ | |a 37776368 |2 pmid |
| 024 | 7 | _ | |a WOS:001189196000001 |2 WOS |
| 037 | _ | _ | |a FZJ-2023-03119 |
| 082 | _ | _ | |a 610 |
| 100 | 1 | _ | |a Hamdan, Sami |0 P:(DE-Juel1)184874 |b 0 |u fzj |
| 245 | _ | _ | |a Confound-leakage: Confound Removal in Machine Learning Leads to Leakage |
| 260 | _ | _ | |a Oxford |c 2023 |b Oxford University Press |
| 336 | 7 | _ | |a article |2 DRIVER |
| 336 | 7 | _ | |a Output Types/Journal article |2 DataCite |
| 336 | 7 | _ | |a Journal Article |b journal |m journal |0 PUB:(DE-HGF)16 |s 1697798276_11492 |2 PUB:(DE-HGF) |
| 336 | 7 | _ | |a ARTICLE |2 BibTeX |
| 336 | 7 | _ | |a JOURNAL_ARTICLE |2 ORCID |
| 336 | 7 | _ | |a Journal Article |0 0 |2 EndNote |
| 500 | _ | _ | |a This work was partly supported by the Helmholtz-AI project DeGen (ZT-I-PF-5-078), the Helmholtz Portfolio Theme “Supercomputing and Modeling for the Human Brain,” and Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), project-ID 431549029–SFB 1451 project B05. |
| 520 | _ | _ | |a BackgroundMachine learning (ML) approaches are a crucial component of modern data analysis in many fields, including epidemiology and medicine. Nonlinear ML methods often achieve accurate predictions, for instance, in personalized medicine, as they are capable of modeling complex relationships between features and the target. Problematically, ML models and their predictions can be biased by confounding information present in the features. To remove this spurious signal, researchers often employ featurewise linear confound regression (CR). While this is considered a standard approach for dealing with confounding, possible pitfalls of using CR in ML pipelines are not fully understood.ResultsWe provide new evidence that, contrary to general expectations, linear confound regression can increase the risk of confounding when combined with nonlinear ML approaches. Using a simple framework that uses the target as a confound, we show that information leaked via CR can increase null or moderate effects to near-perfect prediction. By shuffling the features, we provide evidence that this increase is indeed due to confound-leakage and not due to revealing of information. We then demonstrate the danger of confound-leakage in a real-world clinical application where the accuracy of predicting attention-deficit/hyperactivity disorder is overestimated using speech-derived features when using depression as a confound.ConclusionsMishandling or even amplifying confounding effects when building ML models due to confound-leakage, as shown, can lead to untrustworthy, biased, and unfair predictions. Our expose of the confound-leakage pitfall and provided guidelines for dealing with it can help create more robust and trustworthy ML models. |
| 536 | _ | _ | |a 5252 - Brain Dysfunction and Plasticity (POF4-525) |0 G:(DE-HGF)POF4-5252 |c POF4-525 |f POF IV |x 0 |
| 536 | _ | _ | |a SFB 1451 B05 - Einzelfallvorhersagen der motorischen Fähigkeiten bei Gesunden und Patienten mit motorischen Störungen (B05) (458640473) |0 G:(GEPRIS)458640473 |c 458640473 |x 1 |
| 588 | _ | _ | |a Dataset connected to DataCite |
| 700 | 1 | _ | |a Love, Bradley C |0 P:(DE-HGF)0 |b 1 |
| 700 | 1 | _ | |a Polier, Georg von |0 P:(DE-HGF)0 |b 2 |
| 700 | 1 | _ | |a Weis, Susanne |0 P:(DE-Juel1)172811 |b 3 |u fzj |
| 700 | 1 | _ | |a Schwender, Holger |0 P:(DE-HGF)0 |b 4 |
| 700 | 1 | _ | |a Eickhoff, Simon |0 P:(DE-Juel1)131678 |b 5 |u fzj |
| 700 | 1 | _ | |a Patil, Kaustubh |0 P:(DE-Juel1)172843 |b 6 |e Corresponding author |u fzj |
| 773 | _ | _ | |a 10.1093/gigascience/giad071 |g Vol. 12, p. giad071 |0 PERI:(DE-600)2708999-X |p giad071 |t GigaScience |v 12 |y 20323 |x 2047-217X |
| 856 | 4 | _ | |u https://juser.fz-juelich.de/record/1010545/files/Invoice_SOA23LT000561.pdf |
| 856 | 4 | _ | |y OpenAccess |u https://juser.fz-juelich.de/record/1010545/files/giad071.pdf |
| 909 | C | O | |o oai:juser.fz-juelich.de:1010545 |p openaire |p open_access |p OpenAPC |p driver |p VDB |p openCost |p dnbdelivery |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 0 |6 P:(DE-Juel1)184874 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 3 |6 P:(DE-Juel1)172811 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 5 |6 P:(DE-Juel1)131678 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 6 |6 P:(DE-Juel1)172843 |
| 913 | 1 | _ | |a DE-HGF |b Key Technologies |l Natural, Artificial and Cognitive Information Processing |1 G:(DE-HGF)POF4-520 |0 G:(DE-HGF)POF4-525 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-500 |4 G:(DE-HGF)POF |v Decoding Brain Organization and Dysfunction |9 G:(DE-HGF)POF4-5252 |x 0 |
| 914 | 1 | _ | |y 2023 |
| 915 | p | c | |a APC keys set |0 PC:(DE-HGF)0000 |2 APC |
| 915 | p | c | |a DOAJ Journal |0 PC:(DE-HGF)0003 |2 APC |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0501 |2 StatID |b DOAJ Seal |d 2022-07-04T06:14:53Z |
| 915 | _ | _ | |a Article Processing Charges |0 StatID:(DE-HGF)0561 |2 StatID |d 2023-08-24 |
| 915 | _ | _ | |a WoS |0 StatID:(DE-HGF)0113 |2 StatID |b Science Citation Index Expanded |d 2023-08-24 |
| 915 | _ | _ | |a Fees |0 StatID:(DE-HGF)0700 |2 StatID |d 2023-08-24 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0500 |2 StatID |b DOAJ |d 2022-07-04T06:14:53Z |
| 915 | _ | _ | |a OpenAccess |0 StatID:(DE-HGF)0510 |2 StatID |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1190 |2 StatID |b Biological Abstracts |d 2023-08-24 |
| 915 | _ | _ | |a Creative Commons Attribution CC BY 4.0 |0 LIC:(DE-HGF)CCBY4 |2 HGFVOC |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0160 |2 StatID |b Essential Science Indicators |d 2023-08-24 |
| 915 | _ | _ | |a JCR |0 StatID:(DE-HGF)0100 |2 StatID |b GIGASCIENCE : 2022 |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0200 |2 StatID |b SCOPUS |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0300 |2 StatID |b Medline |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0320 |2 StatID |b PubMed Central |d 2023-10-26 |
| 915 | _ | _ | |a Peer Review |0 StatID:(DE-HGF)0030 |2 StatID |b DOAJ : Open peer review |d 2022-07-04T06:14:53Z |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0600 |2 StatID |b Ebsco Academic Search |d 2023-10-26 |
| 915 | _ | _ | |a Peer Review |0 StatID:(DE-HGF)0030 |2 StatID |b ASC |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0199 |2 StatID |b Clarivate Analytics Master Journal List |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1050 |2 StatID |b BIOSIS Previews |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)0150 |2 StatID |b Web of Science Core Collection |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1030 |2 StatID |b Current Contents - Life Sciences |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1060 |2 StatID |b Current Contents - Agriculture, Biology and Environmental Sciences |d 2023-10-26 |
| 915 | _ | _ | |a DBCoverage |0 StatID:(DE-HGF)1040 |2 StatID |b Zoological Record |d 2023-10-26 |
| 915 | _ | _ | |a IF >= 5 |0 StatID:(DE-HGF)9905 |2 StatID |b GIGASCIENCE : 2022 |d 2023-10-26 |
| 920 | _ | _ | |l yes |
| 920 | 1 | _ | |0 I:(DE-Juel1)INM-7-20090406 |k INM-7 |l Gehirn & Verhalten |x 0 |
| 980 | _ | _ | |a journal |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a UNRESTRICTED |
| 980 | _ | _ | |a I:(DE-Juel1)INM-7-20090406 |
| 980 | _ | _ | |a APC |
| 980 | 1 | _ | |a APC |
| 980 | 1 | _ | |a FullTexts |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|