EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Evolutionary Federated Learning Approach to Diagnose Alzheimer’s Disease Under Uncertainty

Nanziba Basnin iD, Tanjim Mahmud iD, Raihan Ul Islam iD, Karl Andersson iD

Diagnostics · 01.01.2025 · 15 (1) · 80

DOI: 10.3390/diagnostics15010080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 01.01.2025. Verfasst von Nanziba Basnin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Cybersecurity Laboratory, Luleå University of Technology, 97187 Luleå, Sweden. Die Arbeit wurde bisher 49-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Alzheimer’s disease (AD) leads to severe cognitive impairment and functional decline in patients, and its exact cause remains unknown. Early diagnosis of AD is imperative to enable timely interventions that can slow the progression of the disease. This research tackles the complexity and uncertainty of AD by employing a multimodal approach that integrates medical imaging and demographic data.

Methods

To scale this system to larger environments, such as hospital settings, and to ensure the sustainability, security, and privacy of sensitive data, this research employs both deep learning and federated learning frameworks. MRI images are pre-processed and fed into a convolutional neural network (CNN), which generates a prediction file. This prediction file is then combined with demographic data and distributed among clients for local training. Training is conducted both locally and globally using a belief rule base (BRB), which effectively integrates various data sources into a comprehensive diagnostic model.

Results

The aggregated data values from local training are collected on a central server. Various aggregation methods are evaluated to assess the performance of the federated learning model, with results indicating that FedAvg outperforms other methods, achieving a global accuracy of 99.9%.

Conclusions

The BRB effectively manages the uncertainty associated with AD data, providing a robust framework for integrating and analyzing diverse information. This research not only advances AD diagnostics by integrating multimodal data but also underscores the potential of federated learning for scalable, privacy-preserving healthcare solutions.

Schlagwörter

Stichwörter der Autor:innen

Alzheimer’s diseaseFedAvgFedProxbelief rule baseconvolutional neural network (CNN)federated learninggenetic algorithm

Autor:innen und Institutionen

  • Cybersecurity Laboratory, Luleå University of Technology, 97187 Luleå, Sweden.
  • Department of Computer Science and Engineering, Rangamati Science and Technology University, Rangamati 4500, Bangladesh.
  • Department of Computer Science and Engineering, East West University, Dhaka 1212, Bangladesh.

ORCID-Profile: Nanziba Basnin, Tanjim Mahmud, Raihan Ul Islam, Karl Andersson

Zitieren

APA

Basnin, N., Mahmud, T., Islam, R. U., & Andersson, K. (2025). An Evolutionary Federated Learning Approach to Diagnose Alzheimer’s Disease Under Uncertainty. Diagnostics, 15(1), 80. https://doi.org/10.3390/diagnostics15010080

Vancouver

Basnin N, Mahmud T, Islam RU, Andersson K. An Evolutionary Federated Learning Approach to Diagnose Alzheimer’s Disease Under Uncertainty. Diagnostics. 2025;15(1):80. doi:10.3390/diagnostics15010080

BibTeX
@article{Basnin2025,
  author = {Basnin, Nanziba and Mahmud, Tanjim and Islam, Raihan Ul and Andersson, Karl},
  title = {An Evolutionary Federated Learning Approach to Diagnose Alzheimer’s Disease Under Uncertainty},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {1},
  pages = {80},
  doi = {10.3390/diagnostics15010080}
}
Kostenlos starten →