Trustworthy Explainable Artificial Intelligence for Comprehensive Alzheimer's Disease Diagnosis, Staging, and Progression Prediction Using Multimodal Data

Alzheimer's Disease (AD) is a progressive neurodegenerative condition and requires a suitable diagnosis followed by accurate staging and reliable prediction of disease progression, along with continuous decision support to manage patients effectively.It is obvious that despite the fact that existing approaches utilizing artificial intelligence (AI) technologies have shown great promise in terms of diagnostic capabilities, they are more focused on isolated problems, use only unimodal data, and lack proper explanation capabilities and reliability, which creates a serious hindrance to their applying to the clinical practice.Thus, in order to solve these existing issues, the authors of the article present the concept of a Trustworthy Explainable Artificial Intelligence (TXAI) framework based on multimodal data, which can provide comprehensive diagnostic capabilities for Alzheimer's Disease, its staging, progression prediction, and clinical decision support.The TXAI framework utilizes various input data, particularly structural MRI, PET scans, specific cognitive tests (MMSE, CDR, and ADAS-Cog), demographic data, and important biomarkers connected to particular patients.In relation to the issue of trustworthiness, the authors mention that the TXAI framework includes methods of uncertainty estimation, model calibration, reliability evaluation, and techniques of explainable AI that allow providing accurate predictions accompanied by explanations valid in clinical practice.In addition to that, it is worth mentioning that the TXAI framework deals with disease stage estimation, predictions of progression risk, and calculation of the risk score at the same time.The framework was evaluated using publicly available Alzheimer's Disease datasets, including ADNI, OASIS, and AIBL, under patient-independent stratified cross-validation.Comparative experiments with conventional and deep-learning baselines demonstrate the effectiveness of TXAI for multimodal diagnosis and disease staging, while additional analyses assess progression, trustworthiness, explainability, robustness, and personalized risk assessment.

Authors

Publication Details

Journal
International journal of intelligent engineering and systems
Published
2026-11-17
DOI
https://doi.org/10.22266/ijies2026.1231.27
Primary Topic
Dementia and Cognitive Impairment Research
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Trustworthy Explainable Artificial Intelligence for Comprehensive Alzheimer's Disease Diagnosis, Staging, and Progression Prediction Using Multimodal Data

P. Sumithabhashini, Ramesh Alladi, Pandi Chiranjeevi, Thatikonda Supraja et al.
International journal of intelligent engineering and systems
Dementia and Cognitive Impairment Research
article

Trustworthy Explainable Artificial Intelligence for Comprehensive Alzheimer's Disease Diagnosis, Staging, and Progression Prediction Using Multimodal Data

P. Sumithabhashini, Ramesh Alladi, Pandi Chiranjeevi, Thatikonda Supraja, Ch Vijaya Kumar, P Ashok Kumar
article en

Abstract

Alzheimer's Disease (AD) is a progressive neurodegenerative condition and requires a suitable diagnosis followed by accurate staging and reliable prediction of disease progression, along with continuous decision support to manage patients effectively.It is obvious that despite the fact that existing approaches utilizing artificial intelligence (AI) technologies have shown great promise in terms of diagnostic capabilities, they are more focused on isolated problems, use only unimodal data, and lack proper explanation capabilities and reliability, which creates a serious hindrance to their applying to the clinical practice.Thus, in order to solve these existing issues, the authors of the article present the concept of a Trustworthy Explainable Artificial Intelligence (TXAI) framework based on multimodal data, which can provide comprehensive diagnostic capabilities for Alzheimer's Disease, its staging, progression prediction, and clinical decision support.The TXAI framework utilizes various input data, particularly structural MRI, PET scans, specific cognitive tests (MMSE, CDR, and ADAS-Cog), demographic data, and important biomarkers connected to particular patients.In relation to the issue of trustworthiness, the authors mention that the TXAI framework includes methods of uncertainty estimation, model calibration, reliability evaluation, and techniques of explainable AI that allow providing accurate predictions accompanied by explanations valid in clinical practice.In addition to that, it is worth mentioning that the TXAI framework deals with disease stage estimation, predictions of progression risk, and calculation of the risk score at the same time.The framework was evaluated using publicly available Alzheimer's Disease datasets, including ADNI, OASIS, and AIBL, under patient-independent stratified cross-validation.Comparative experiments with conventional and deep-learning baselines demonstrate the effectiveness of TXAI for multimodal diagnosis and disease staging, while additional analyses assess progression, trustworthiness, explainability, robustness, and personalized risk assessment.

International journal of intelligent engineering and systemsVol. 19(12)
Good health and well-being
Dementia and Cognitive Impairment Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon