CoChat
Sign Up
Cited by 363Dementia and Cognitive Impairment ResearchArtificial Intelligence in HealthcareExplainable Artificial Intelligence (XAI)

The DOI matches its Crossref record; 109 of the 109 references it cites were found in a registry or an index.

A multilayer multimodal detection and prediction model based on explainable artificial intelligence for Alzheimer’s disease

Open access
El-Sappagh, Shaker, Alonso, Jose M., Islam, S. M. Riazul, Sultan, Ahmad M., Kwak, Kyung Sup·2021·Scientific Reports
DOI 10.1038/s41598-021-82098-3PMC PMC7846613
Open this paper in CoChat — free accountOpen PDF

Abstract

Alzheimer’s disease (AD) is the most common type of dementia. Its diagnosis and progression detection have been intensively studied. Nevertheless, research studies often have little effect on clinical practice mainly due to the following reasons: (1) Most studies depend mainly on a single modality, especially neuroimaging; (2) diagnosis and progression detection are usually studied separately as two independent problems; and (3) current studies concentrate mainly on optimizing the performance of complex machine learning models, while disregarding their explainability. As a result, physicians struggle to interpret these models, and feel it is hard to trust them. In this paper, we carefully develop an accurate and interpretable AD diagnosis and progression detection model. This model provides physicians with accurate decisions along with a set of explanations for every decision. Specifically, the model integrates 11 modalities of 1048 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) real-world dataset: 294 cognitively normal, 254 stable mild cognitive impairment (MCI), 232 progressive MCI, and 268 AD. It is actually a two-layer model with random forest (RF) as classifier algorithm. In the first layer, the model carries out a multi-class classification for the early diagnosis of AD patients. In the second layer, the model applies binary classification to detect possible MCI-to-AD progression within three years from a baseline diagnosis. The performance of the model is optimized with key markers selected from a large set of biological and clinical measures. Regarding explainability, we provide, for each layer, global and instance-based explanations of the RF classifier by using the SHapley Additive exPlanations (SHAP) feature attribution framework. In addition, we implement 22 explainers based on decision trees and fuzzy rule-based systems to provide complementary justifications for every RF decision in each layer. Furthermore, these explanations are represented in natural language form to help physicians understand the predictions. The designed model achieves a cross-validation accuracy of 93.95% and an F1-score of 93.94% in the first layer, while it achieves a cross-validation accuracy of 87.08% and an F1-Score of 87.09% in the second layer. The resulting system is not only accurate, but also trustworthy, accountable, and medically applicable, thanks to the provided explanations which are broadly consistent with each other and with the AD medical literature. The proposed system can help to enhance the clinical understanding of AD diagnosis and progression processes by providing detailed insights into the effect of different modalities on the disease risk.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-021-82098-3

Cites

109 of 109 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Selected features for both layers based on three different techniques of SVM, RF, and GB. The first row is for the first layer, and the second row is for the second layer.
Figure 1 Selected features for both layers based on three different techniques of SVM, RF, and GB. The first row is for the first layer, and the second row is for the second layer.CC BY · PubMed Central
Figure 2 SHAP summary plots for the first layer. The upper left figure represents the CN class, the upper right figure represents the MCI class, and the second row represents the AD class.
Figure 2 SHAP summary plots for the first layer. The upper left figure represents the CN class, the upper right figure represents the MCI class, and the second row represents the AD class.CC BY · PubMed Central
Figure 3 SHAP summary plots for the second layer. The left figure shows the pMCI class, and the right figure shows the sMCI class.
Figure 3 SHAP summary plots for the second layer. The left figure shows the pMCI class, and the right figure shows the sMCI class.CC BY · PubMed Central
Figure 4 First layer example predictions for AD (A), CN (B), and MCI (C) and SHAP supervised clustering in model behavior for all cases in each class. Red indicates attributions that push the score higher, while blue indicates contributions that push the score lower. A few of the noticeable subgroups are annotated with the features that define them.
Figure 4 First layer example predictions for AD (A), CN (B), and MCI (C) and SHAP supervised clustering in model behavior for all cases in each class. Red indicates attributions that push the score higher, while blue indicates contributions that push the score lower. A few of the noticeable subgroups are annotated with the features that define them.CC BY · PubMed Central
Figure 5 Development process for the oracle model in each layer.
Figure 5 Development process for the oracle model in each layer.CC BY · PubMed Central
Figure 6 The proposed XAI framework. A variety of data modalities are used to build the predictive model. In addition, a variety of explanations are built for the entire RF behavior and for each prediction. The FreeSurfer version 6.0 is used (https://surfer.nmr.mgh.harvard.edu/).
Figure 6 The proposed XAI framework. A variety of data modalities are used to build the predictive model. In addition, a variety of explanations are built for the entire RF behavior and for each prediction. The FreeSurfer version 6.0 is used (https://surfer.nmr.mgh.harvard.edu/).CC BY · PubMed Central
Figure 7 Multimodal fusion strategies: (a) late fusion, (b) early fusion.
Figure 7 Multimodal fusion strategies: (a) late fusion, (b) early fusion.CC BY · PubMed Central
Figure 8 Roles of explainers to enhance RF interpretability.
Figure 8 Roles of explainers to enhance RF interpretability.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 108 references

Research works printed but not linked: 2

  1. Fernandez-Delgado, M., Cernadas, E., Barro, S. & Amorim, D. Do we need hundreds of classifiers to solve real world classification problems. J. Mach. Learn. Res. 15, 3133–3181 (2014).
  2. Elisseeff, A. & Pontil, M. Leave-one-out error and stability of learning algorithms with applications. In NATO science series sub series iii computer and systems sciences 111–130 (ISO Press, 2003).

Cited by

Sorted by citations

Items 201–300 of 363

Related

See all

Metadata

Authors
El-Sappagh, S., Alonso, J. M., Islam, S. M. R., Sultan, A. M., & Kwak, K. S.
Affiliations
  • Sejong University (KR)
  • Inha University (KR)
Corresponding author
Kwak, Kyung Sup
ORCID
Venue
Scientific Reports
Publisher
Springer Science and Business Media LLC
Published
2021-01-29
Volume
11
Issue
1
Pages
2660-2660
ISSN
2045-2322 (ISSN-L)
DOI
10.1038/s41598-021-82098-3
PMC
PMC7846613
OpenAlex
W3125069671
Cited by
363
References
108
Citations by year
2026: 62 · 2025: 96 · 2024: 80 · 2023: 58 · 2022: 56 · 2021: 11
FWCI
36.77
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Aberdeen University Research Archive (Aberdeen University) (submittedVersion)
  • LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Hispana (submittedVersion, cc-by)
  • Repositorio institucional da Universidade de Santiago de Compostela (University of Santiago de Compostela) (submittedVersion, other-oa)
  • Greater South Information System
Funders
National Research Foundation of Korea-Grant funded by the Korean Government (NRF-2017R1A2B2012337)
Topics
  • Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
Keywords
Alzheimer's disease, Alzheimer's disease diagnosis, multimodal fusion, explainable AI, SHAP feature attribution, random forest, fuzzy rule-based systems, natural language explanations, clinical decision support, Alzheimer's Disease Neuroimaging Initiative, biomarker selection, model interpretability
MeSH terms
Aged, Aged, 80 and over, Alzheimer Disease, Artificial Intelligence, Brain, Female, Follow-Up Studies, Humans, Magnetic Resonance Imaging, Male, Middle Aged, Models, Neurological, Databases, Factual, Neuroimaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review