Resting-state whole-brain functional connectivity networks for MCI classification using L2-regularized logistic...

Area of Science:

• Neuroimaging
• Neurology
• Machine Learning

Background:

• Mild cognitive impairment (MCI) is a precursor to Alzheimer's disease (AD), necessitating early diagnosis for timely intervention.
• Resting-state functional Magnetic Resonance Imaging (rs-fMRI) offers insights into whole-brain connectivity but faces challenges in identifying discriminative features for classification.
• Effective classification of MCI is crucial for developing treatments to delay or prevent AD progression.

Purpose of the Study:

• To develop and validate a novel feature extraction method from rs-fMRI data for improved classification of mild cognitive impairment.
• To identify the most discriminative functional connectivity patterns associated with MCI.
• To assess the diagnostic performance of a machine learning classifier trained on these novel features.

Main Methods:

• rs-fMRI data was analyzed to compute Pearson's correlation coefficients for whole-brain functional connectivity.
• A Two Sample T-Test was applied to the correlation matrix to identify novel, discriminative features.
• A L2-regularized Logistic Regression classifier was trained using the five identified features and evaluated with leave-one-out and 10-fold cross-validation.

Main Results:

• The proposed method achieved a classification accuracy of 87.5% for mild cognitive impairment.
• The area under the receiver operating characteristic (ROC) curve reached 0.929, indicating high diagnostic performance.
• Statistical validation confirmed the method's significant superiority over three other algorithms.

Conclusions:

• The novel feature extraction technique based on rs-fMRI connectivity is effective for classifying mild cognitive impairment.
• This method demonstrates potential as a valuable tool to assist physicians in real-world diagnostic scenarios.
• Accurate and early diagnosis of MCI can facilitate interventions to delay or prevent the onset of Alzheimer's disease.