Related Experiment Video
Updated: Feb 10, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Diagnostic Validity of an Automated Probabilistic Tractography in Amnestic Mild Cognitive Impairment
Won Sang Jung1, Yoo Hyun Um2, Dong Woo Kang3
1Department of Radiology, St. Vincent Hospital, Suwon, Korea.
Objective:
Although several prior works showed the white matter (WM) integrity changes in amnestic mild cognitive impairment (aMCI) and Alzheimer's disease, it is still unclear the diagnostic accuracy of the WM integrity measurements using diffusion tensor imaging (DTI) in discriminating aMCI from normal controls. The aim of this study is to explore diagnostic validity of whole brain automated probabilistic tractography in discriminating aMCI from normal controls.
Methods:
One hundred-two subjects (50 aMCI and 52 normal controls) were included and underwent DTI scans. Whole brain WM tracts were reconstructed with automated probabilistic tractography. Fractional anisotropy (FA) and mean diffusivity (MD) values of the memory related WM tracts were measured and compared between the aMCI and the normal control groups. In addition, the diagnostic validities of these WM tracts were evaluated.
Results:
Decreased FA and increased MD values of memory related WM tracts were observed in the aMCI group compared with the control group. Among FA and MD value of each tract, the FA value of left cingulum angular bundle showed the highest area under the curve (AUC) of 0.85 with a sensitivity of 88.2%, a specificity of 76.9% in differentiating MCI patients from control subjects. Furthermore, the combination FA values of WM integrity measures of memory related WM tracts showed AUC value of 0.98, a sensitivity of 96%, a specificity of 94.2%.
Conclusion:
Our results with good diagnostic validity of WM integrity measurements suggest DTI might be promising neuroimaging tool for early detection of aMCI and AD patients.
More Related Videos
Related Concept Videos
Cognitive Dissonance
Reliability and Validity
Data Validation
Key parameters for method validation include:
Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...
Language and Cognition
Cognitive Therapy

