Cargando…
Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis
The Alzheimer′s 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, fe...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9075665/ https://www.ncbi.nlm.nih.gov/pubmed/35522653 http://dx.doi.org/10.1371/journal.pone.0264695 |
_version_ | 1784701738606919680 |
---|---|
author | Hernandez, Monica Ramon-Julvez, Ubaldo Ferraz, Francisco |
author_facet | Hernandez, Monica Ramon-Julvez, Ubaldo Ferraz, Francisco |
author_sort | Hernandez, Monica |
collection | PubMed |
description | The Alzheimer′s 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 Alzheimer′s. 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). |
format | Online Article Text |
id | pubmed-9075665 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-90756652022-05-07 Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis Hernandez, Monica Ramon-Julvez, Ubaldo Ferraz, Francisco PLoS One Research Article The Alzheimer′s 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 Alzheimer′s. 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). Public Library of Science 2022-05-06 /pmc/articles/PMC9075665/ /pubmed/35522653 http://dx.doi.org/10.1371/journal.pone.0264695 Text en © 2022 Hernandez et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Hernandez, Monica Ramon-Julvez, Ubaldo Ferraz, Francisco Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis |
title | Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis |
title_full | Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis |
title_fullStr | Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis |
title_full_unstemmed | Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis |
title_short | Explainable AI toward understanding the performance of the top three TADPOLE Challenge methods in the forecast of Alzheimer’s disease diagnosis |
title_sort | explainable ai toward understanding the performance of the top three tadpole challenge methods in the forecast of alzheimer’s disease diagnosis |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9075665/ https://www.ncbi.nlm.nih.gov/pubmed/35522653 http://dx.doi.org/10.1371/journal.pone.0264695 |
work_keys_str_mv | AT hernandezmonica explainableaitowardunderstandingtheperformanceofthetopthreetadpolechallengemethodsintheforecastofalzheimersdiseasediagnosis AT ramonjulvezubaldo explainableaitowardunderstandingtheperformanceofthetopthreetadpolechallengemethodsintheforecastofalzheimersdiseasediagnosis AT ferrazfrancisco explainableaitowardunderstandingtheperformanceofthetopthreetadpolechallengemethodsintheforecastofalzheimersdiseasediagnosis AT explainableaitowardunderstandingtheperformanceofthetopthreetadpolechallengemethodsintheforecastofalzheimersdiseasediagnosis |