A Machine Learning Approach for the Differential Diagnosis of Alzheimer and Vascular Dementia Fed by MRI Selected Features

0410

Among dementia-like diseases, Alzheimer disease (AD) and vascular dementia (VD) are two of the most frequent. AD and VD may share multiple neurological symptoms that may lead to controversial diagnoses when using conventional clinical and MRI criteria. Therefore, other approaches are needed to overcome this issue. Machine learning (ML) combined with magnetic resonance imaging (MRI) has been shown to improve the diagnostic accuracy of several neurodegenerative diseases, including dementia. To this end, in this study, we investigated,

first, whether different kinds of ML algorithms, combined with advanced MRI features, could be supportive in classifying VD from AD and,

second, whether the developed approach might help in predicting the prevalent disease in subjects with an unclear profile of AD or VD.

Three ML categories of algorithms were tested: artificial neural network (ANN), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS). Multiple regional metrics from resting-state fMRI (rs-fMRI) and diffusion tensor imaging (DTI) of 60 subjects (33 AD, 27 VD) were used as input features to train the algorithms and find the best feature pattern to classify VD from AD.

We then used the identified VD–AD discriminant feature pattern as input for the most performant ML algorithm to predict the disease prevalence in 15 dementia patients with a “mixed VD–AD dementia” (MXD) clinical profile using their baseline MRI data.

ML predictions were compared with the diagnosis evidence from a 3-year clinical follow-up. ANFIS emerged as the most efficient algorithm in discriminating AD from VD, reaching a classification accuracy greater than 84% using a small feature pattern. Moreover, ANFIS showed improved classification accuracy when trained with a multimodal input feature data set (e.g., DTI + rs-fMRI metrics) rather than a unimodal feature data set.

When applying the best discriminant pattern to the MXD group, ANFIS achieved a correct prediction rate of 77.33%.

Overall, results showed that our approach has a high discriminant power to classify AD and VD profiles. Moreover, the same approach also showed potential in predicting earlier the prevalent underlying disease in dementia patients whose clinical profile is uncertain between AD and VD, therefore suggesting its usefulness in supporting physicians’ diagnostic evaluations.

FIGURE 1 | (A) Brain areas from which DTI features (FA, MD) have been extracted; (B) the 116 areas from the AAL atlas used to parcellate the brain and then to calculate the rs-fMRI-derived graph theory (GT) metrics.

FIGURE 2 | Details of the ROC curves and relative AUC (95% IC) values obtained from each run classifier (SVMRBF, SVMMLP, MLP, RBFN, and ANFIS) using input data from the DTI data set (on the left), the GT fMRI data set (in the middle), and the DTI + GT data set (on the right).

FIGURE 3 | Predictions of the prevalent underlying disease (dark gray squares for AD, light gray squares for VD) on the MXD subjects performed by ANFIS using the feature pattern reported in Table 4. ANFIS correctly predicted the class for 11 out of the 15 MXD subjects (77.33% correct prediction rate). A red asterisk highlights
the four subjects for whom ANFIS predicted a class that was in discordance with the clinical evidence at follow-up.

FIGURE 4 | Boxplots representing the summary of the 10 features (WM features on top, GM features on bottom) in AD and VD groups. The ensemble of these features (see also Table 4) formed the discriminant pattern that was also used to predict the prevalent underlying disease in MXD subjects. Each feature has been tested with the Mann–Whitney U test in order to assess significant differences between AD and VD values. An asterisk mark has been added on the top of the boxplot of the features with values significantly (p < 0.05) different between the AD and VD populations.