US DE COOKIES
Utilitzem cookies necessaries de sistema pel correcte funcionament de la web i cookies opcionals de Google Analytics per obtenir estadístiques de visita (sense obtenir dades personales). + Info
Acceptar cookies
Tornar als resultats
FI
2.424
2021 Psychiatry Research-Neuroimaging
Biased accuracy in multisite machine-learning studies due to incomplete removal of the effects of the site.
Solanes A, Palau P, Fortea L, Salvador R, González-Navarro L, Llach CD, Valentí M, Vieta E, Radua J

Servei limitat a col·laboradors/res de la xarxa de centres de Germanes Hospitalàries. Rebreu un missatge al vostre correu-e amb un enllaç per a la descàrrega del present article.

Abstract

Brain MRI researchers conducting multisite studies, such as within the ENIGMA Consortium, are very aware of the importance of controlling the effects of the site (EoS) in the statistical analysis. Conversely, authors of the novel machine-learning MRI studies may remove the EoS when training the machine-learning models but not control them when estimating the models' accuracy, potentially leading to severely biased estimates. We show examples from a toy simulation study and real MRI data in which we remove the EoS from both the "training set" and the "test set" during the training and application of the model. However, the accuracy is still inflated (or occasionally shrunk) unless we further control the EoS during the estimation of the accuracy. We also provide several methods for controlling the EoS during the estimation of the accuracy, and a simple R package ("multisite.accuracy") that smoothly does this task for several accuracy estimates (e.g., sensitivity/specificity, area under the curve, correlation, hazard ratio, etc.).
Formem part de
HH Província Espanya
Contacteu-nos

Avda. Jordà , 8 - 08035 Barcelona
Telèfon: 93 652 99 99 - Ext 1486
E-mail: fundacio@fidmag.com
Formulari de contacte online 

         

 

Reconeixements a la qualitat i l'excel·lència
Darrera modificació: 26/11/2021
AGAUR
CIBERSAM
Generalitat de Catalunya
ISCIII
Unión Europea
MICINN