EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

From Single-Modal to Multi-Modal Artificial Intelligence in Alzheimer’s Disease: A Systematic Review of Databases, Modalities, Diagnostic Performance, and Clinical Translation Challenges

José Menezes iD, Maria Inês Barbosa iD, Pedro Miguel Rodrigues iD

Sensors · 2026

DOI: 10.3390/s26175489 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Sensors, 2026. Verfasst von José Menezes und 2 weiteren Autor:innen. Beteiligte Einrichtung: CBQF-Centro de Biotecnologia e Química Fina, Escola Superior de Biotecnologia, Portuguesa, Universidade Católica Portuguesa, 4169-005 Porto, Portugal. Hauptthemen laut MEDLINE: Alzheimer Disease, Artificial Intelligence. Die Arbeit nennt 633 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação para a Ciência e Tecnologia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Alzheimer’s disease (AD) is the leading cause of dementia and a major cause of death worldwide, making early detection a critical clinical priority. Because pathological changes may begin 15–20 years before symptom onset, artificial intelligence (AI) has emerged as a promising tool for identifying and characterizing AD. In particular, multi-modal approaches that integrate cognitive, biological, and sensor-based data have attracted growing interest. This systematic review compares single- and multi-modal AI strategies for AD detection, covering machine learning and deep learning methods, feature representations, validation strategies, and classification tasks. Searches of major databases identified 568 studies published between 2016 and early 2026; 278 met the inclusion criteria according to PRISMA guidelines. Multi-modal approaches generally achieved higher performance than single-modal strategies, particularly for challenging tasks such as predicting progression between closely related disease stages, although direct comparisons under identical conditions remain scarce. Critically, only about 4% of studies evaluated their models on a genuinely independent external cohort, raising substantial concerns about model generalizability. Overall, current AI systems remain highly dependent on existing datasets and heterogeneous evaluation protocols, which limit generalizability and clinical applicability. Future research should prioritize representative multimodal datasets, rigorous external validation, and clinically interpretable AI systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Alzheimer DiseaseArtificial IntelligenceHumansMachine LearningDatabases, FactualTranslational Research, Biomedical

Stichwörter der Autor:innen

Alzheimer’s diseasebiomarkersdata fusiondeep learningearly diagnosismachine learningmulti-modal artificial intelligenceneuroimaging

Autor:innen und Institutionen

  • CBQF-Centro de Biotecnologia e Química Fina, Escola Superior de Biotecnologia, Portuguesa, Universidade Católica Portuguesa, 4169-005 Porto, Portugal.

ORCID-Profile: José Menezes, Maria Inês Barbosa, Pedro Miguel Rodrigues

Förderung

  • Fundação para a Ciência e Tecnologia

Zitieren

APA

Menezes, J., Barbosa, M. I., & Rodrigues, P. M. (2026). From Single-Modal to Multi-Modal Artificial Intelligence in Alzheimer’s Disease: A Systematic Review of Databases, Modalities, Diagnostic Performance, and Clinical Translation Challenges. Sensors. https://doi.org/10.3390/s26175489

Vancouver

Menezes J, Barbosa MI, Rodrigues PM. From Single-Modal to Multi-Modal Artificial Intelligence in Alzheimer’s Disease: A Systematic Review of Databases, Modalities, Diagnostic Performance, and Clinical Translation Challenges. Sensors. 2026. doi:10.3390/s26175489

BibTeX
@article{Menezes2026,
  author = {Menezes, José and Barbosa, Maria Inês and Rodrigues, Pedro Miguel},
  title = {From Single-Modal to Multi-Modal Artificial Intelligence in Alzheimer’s Disease: A Systematic Review of Databases, Modalities, Diagnostic Performance, and Clinical Translation Challenges},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26175489}
}
Kostenlos starten →