000130901 001__ 130901
000130901 005__ 20240319081005.0
000130901 0247_ $$2doi$$a10.1371/journal.pone.0264695
000130901 0248_ $$2sideral$$a129157
000130901 037__ $$aART-2022-129157
000130901 041__ $$aeng
000130901 100__ $$0(orcid)0000-0003-1270-5852$$aHernandez, Mónica$$uUniversidad de Zaragoza
000130901 245__ $$aExplainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis
000130901 260__ $$c2022
000130901 5060_ $$aAccess copy available to the general public$$fUnrestricted
000130901 5203_ $$aThe Alzheimer0s Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge is the most comprehensive challenge to date with regard to the number of subjects, considered features, and challenge participants. The initial objective of TADPOLE was the identification of the most predictive data, features, and methods for the progression of subjects at risk of developing Alzheimer0s. The challenge was successful in recognizing tree-based ensemble methods such as gradient boosting and random forest as the best methods for the prognosis of the clinical status in Alzheimer’s disease (AD). However, the challenge outcome was limited to which combination of data processing and methods exhibits the best accuracy; hence, it is difficult to determine the contribution of the methods to the accuracy. The quantification of feature importance was globally approached by all the challenge participant methods. In addition, TADPOLE provided general answers that focused on improving performance while ignoring important issues such as interpretability. The purpose of this study is to intensively explore the models of the top three TADPOLE Challenge methods in a common framework for fair comparison. In addition, for these models, the most meaningful features for the prognosis of the clinical status of AD are studied and the contribution of each feature to the accuracy of the methods is quantified. We provide plausible explanations as to why the methods achieve such accuracy, and we investigate whether the methods use information coherent with clinical knowledge. Finally, we approach these issues through the analysis of SHapley Additive exPlanations (SHAP) values, a technique that has recently attracted increasing attention in the field of explainable artificial intelligence (XAI). Copyright: © 2022 Hernandez et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
000130901 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T64-20R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2019-104358RB-I00
000130901 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000130901 590__ $$a3.7$$b2022
000130901 591__ $$aMULTIDISCIPLINARY SCIENCES$$b26 / 73 = 0.356$$c2022$$dQ2$$eT2
000130901 592__ $$a0.885$$b2022
000130901 593__ $$aMultidisciplinary$$c2022$$dQ1
000130901 594__ $$a6.0$$b2022
000130901 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000130901 700__ $$aRamón-Julvez, Ubaldo$$uUniversidad de Zaragoza
000130901 700__ $$aFerraz, Francisco
000130901 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000130901 773__ $$g17, 5 (2022), [32 pp.]$$pPLoS One$$tPLoS ONE$$x1932-6203
000130901 8564_ $$s4292925$$uhttps://zaguan.unizar.es/record/130901/files/texto_completo.pdf$$yVersión publicada
000130901 8564_ $$s2331559$$uhttps://zaguan.unizar.es/record/130901/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000130901 909CO $$ooai:zaguan.unizar.es:130901$$particulos$$pdriver
000130901 951__ $$a2024-03-18-14:35:57
000130901 980__ $$aARTICLE