Machine-learning Support to Individual Diagnosis of Mild Cognitive Impairment Using Multimodal MRI and Cognitive Assessments. (October 2017)

• Record Type: Journal Article
• Authors: De Marco, Matteo; Beltrachini, Leandro; Biancardi, Alberto; Frangi, Alejandro F.; Venneri, Annalena
• Is Part Of: Alzheimer disease and associated disorders. Volume 31:Number 4(2017)
• Publication Date: 2017-10
• Subjects: machine learning -- magnetic resonance imaging -- semantics -- hippocampus -- resting-state; Alzheimer's disease -- Periodicals; Dementia -- Periodicals; 616.8305
• DOI: 10.1097/WAD.0000000000000208
• Languages: English
• ISSNs: 0893-0341

Abstract

Abstract : Background: Understanding whether the cognitive profile of a patient indicates mild cognitive impairment (MCI) or performance levels within normality is often a clinical challenge. The use of resting-state functional magnetic resonance imaging (RS-fMRI) and machine learning may represent valid aids in clinical settings for the identification of MCI patients. Methods: Machine-learning models were computed to test the classificatory accuracy of cognitive, volumetric [structural magnetic resonance imaging (sMRI)] and blood oxygen level dependent-connectivity (extracted from RS-fMRI) features, in single-modality and mixed classifiers. Results: The best and most significant classifier was the RS-fMRI+Cognitive mixed classifier (94% accuracy), whereas the worst performing was the sMRI classifier (∼80%). The mixed global (sMRI+RS-fMRI+Cognitive) had a slightly lower accuracy (∼90%), although not statistically different from the mixed RS-fMRI+Cognitive classifier. The most important cognitive features were indices of declarative memory and semantic processing. The crucial volumetric feature was the hippocampus. The RS-fMRI features selected by the algorithms were heavily based on the connectivity of mediotemporal, left temporal, and other neocortical regions. Conclusion: Feature selection was profoundly driven by statistical independence. Some features showed no between-group differences, or showed a trend in either direction. This indicates that clinically relevant brain alterations typical of MCI might be subtle and not inferable from group analysis.