Classification of MRI and psychological testing data based on support vector machine.

Area of Science:

• Neuroscience
• Medical Imaging
• Biomedical Engineering

Background:

• Alzheimer's disease (AD) is a neurodegenerative disorder causing progressive cognitive decline.
• Mild cognitive impairment (MCI) is often considered a prodromal stage of AD.
• Accurate early detection of AD and MCI is crucial for timely intervention.

Purpose of the Study:

• To develop and validate a novel multimodal method for distinguishing AD and MCI subjects from healthy elderly controls.
• To compare the diagnostic performance of the multimodal method with clinical assessments alone.

Main Methods:

• Utilized a multimodal approach combining independent components from MRI measures and clinical assessments.
• Analyzed data from 70 AD subjects, 98 MCI subjects, and 150 healthy controls (HC).
• Employed a support vector machine (SVM)-based classifier after pre-processing, component estimation, and feature extraction.

Main Results:

• Achieved high accuracy in classifying AD from HC (97.7%) and MCI from HC (87.8%).
• Demonstrated superior performance compared to clinical measurements alone (AD vs HC: 79.5% accuracy; MCI vs HC: not specified but implied lower).
• Identified gray matter loss in both AD and MCI, with less volume in MCI, supporting its prodromal role.

Conclusions:

• The proposed multimodal method significantly enhances the accuracy of diagnosing AD and MCI.
• Combining MRI-derived gray matter features with clinical assessments offers improved diagnostic power.
• The findings support the classification of MCI as a precursor stage to Alzheimer's disease.