Related Experiment Video
Updated: Oct 31, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
Published on: December 15, 2023
Identifying and characterizing different stages toward Alzheimer's disease using ordered core features and machine
Jinhua Sheng1,2, Bocheng Wang1,2,3, Qiao Zhang4
1College of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, Zhejiang, 310018, China.
This study introduces ordered core features (OCF) to differentiate Alzheimer's disease (AD) and mild cognitive impairment (MCI) stages. OCF accurately classifies disease progression, highlighting differences between early and late MCI.
Area of Science:
- Neuroscience
- Medical Imaging
- Machine Learning
Background:
- Alzheimer's disease (AD) diagnosis and staging are challenging.
- Functional brain connectivity alterations are key indicators of cognitive decline.
- Distinguishing between early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI) is crucial for accurate diagnosis and prognosis.
Purpose of the Study:
- To propose a novel method, ordered core features (OCF), for analyzing functional brain connectivity in Alzheimer's disease progression.
- To evaluate the efficacy of OCF in classifying different stages of cognitive impairment: healthy controls (HC), EMCI, LMCI, and AD.
- To investigate the distinctiveness of EMCI and LMCI based on brain network features.
Main Methods:
- Utilized a joint HCPMMP parcellation method to divide the brain into 360 regions.
- Developed and applied ordered core features (OCF) to identify significant changes in functional brain connectivity across disease cohorts.
- Employed OCF as supervised machine learning classifiers for binary and multi-group classification tasks.
Main Results:
- OCF achieved high accuracy in binary classification (86.0%-95.5%) between any two cohorts, outperforming the use of all network features (70.1%-91.0%).
- Multi-group classification accuracy reached 75%-78% for HC/EMCI/LMCI or EMCI/LMCI/AD, and 53.3% for HC/EMCI/LMCI/AD.
- Classification accuracy decreased when EMCI and LMCI were grouped as mild cognitive impairment (MCI), underscoring their distinct neurological profiles.
Conclusions:
- Ordered core features (OCF) provide a powerful and accurate method for classifying cognitive impairment stages in Alzheimer's disease.
- The findings support the differentiation between EMCI and LMCI, validating current diagnostic criteria.
- OCF effectively highlights key brain regions, particularly in the frontal lobe and insula, associated with cognitive decline.
Related Concept Videos
Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
Alzheimer's Disease: Treatment
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Dementia
The progression of dementia is generally gradual....
Aggregates Classification
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Cognitive Development During Adulthood

