Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 18, 2025Frontiers in Aging NeuroscienceOpen Access

Accurate and robust prediction of Amyloid-β brain deposition from plasma biomarkers and clinical information using machine learning

View Full Paper
Ask AI
Bookmark
Share

Authors

JXJiayuan XuADAndrew J. DoigSMSofia Michopoulou

Discussion

Loading...

Member takes

Overview

Machine learning predicts amyloid-β status in Alzheimer's patients, suggesting a cost-effective alternative to PET imaging.

Key Points

  • The system achieved an AUC of 0.95 using the ADNI dataset, indicating high predictive accuracy for amyloid-β status.
  • Using just five features, the model still reached an AUC of 0.87, demonstrating effectiveness in streamlined approaches.
  • Machine learning methods like random forest and support vector machine were utilized to analyze clinical data and plasma biomarkers.
  • This technique generalizes well to external datasets, offering a low-cost alternative to traditional PET neuroimaging.

Cite This Study

Xu et al. (2025) studied this question.

synapsesocial.com/papers/68af2edecf1dd9ea359e6556https://doi.org/10.3389/fnagi.2025.1559459
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Optimizing timing and cost-effective use of plasma biomarkers in Alzheimer’s disease2025
  2. 2Development of Plasma Protein Classification Models for Alzheimer’s Disease Using Multiple Machine Learning Approaches2025
  3. 3Integrating MRI Volume and Plasma p-Tau217 for Amyloid Risk Stratification in Early-Stage Alzheimer Disease2025
  4. 4Prediction of continuous amyloid positron emission tomography with fluid measures of phosphorylated tau and β-amyloid2025
  5. 5AI-driven fusion of multimodal data for Alzheimer’s disease biomarker assessment2025 · 45 citations