Background: Mild cognitive impairment (MCI) is considered a prodromal stage of Alzheimer’s disease, which is the sixth leading cause of death in the United State. Early diagnosis of MCI can allow for treatment to improve cognitive function and reduce modifiable risk factors. Currently, the combination of machine learning and neuroimaging plays a role in identifying and understanding neuropathological diseases. However, some challenges still remain, and these limitations need to be optimized for clinical MCI diagnosis.
Methods: In this study, for stable identification with functional near-infrared spectroscopy (fNIRS) using the minimum resting-state time, nine different measurement durations (i.e., 30, 60, 90, 120, 150, 180, 210, 240, and 270 s) were evaluated based on 30 s intervals using a traditional machine learning approach and graph theory analysis. The machine learning methods were trained using temporal features of the resting-state fNIRS signal and included linear discriminant analysis (LDA), support vector machine, and K-nearest neighbor (KNN) algorithms. To enhance the diagnostic accuracy, feature representation- and classification-based transfer learning (TL) methods were used to detect MCI from the healthy controls through the input of connectivity maps with 30 and 90 s durations.
Results: As in the results of the traditional machine learning and graph theory analysis, there was no significant difference among the different time windows. The accuracy of the conventional machine learning methods ranged from 55.76% (KNN, 120 s) to 67.00% (LDA, 90 s). The feature representation-based TL showed improved accuracy in both the 30 and 90 s cases (i.e., mean accuracy of 30 s: 79.37%, mean accuracy of 30 s: 74.05%). Notably, the classification-based TL method achieved the highest accuracy of 97.01% using the VGG19 pre-trained CNN model trained with the 30 s duration connectivity map.
Conclusion: The results indicate that a 30 s measurement of the resting state with fNIRS could be used to detect MCI. Moreover, the combination of neuroimaging (e.g., functional connectivity maps) and deep learning methods (e.g., CNN and TL) may be considered as novel biomarkers for clinical computer-assisted MCI diagnosis.