Differential diagnosis of neurodegenerative dementias with the explainable MRI based machine learning algorithm MUQUBIA

Abstract

Biomarker-based differential diagnosis of the most common forms of dementia is becoming increasingly important. Machine learning (ML) may be able to address this challenge. The aim of this study was to develop and interpret a ML algorithm capable of differentiating Alzheimer's dementia, frontotemporal dementia, dementia with Lewy bodies and cognitively normal control subjects based on sociodemographic, clinical, and magnetic resonance imaging (MRI) variables. 506 subjects from 5 databases were included. MRI images were processed with FreeSurfer, LPA, and TRACULA to obtain brain volumes and thicknesses, white matter lesions and diffusion metrics. MRI metrics were used in conjunction with clinical and demographic data to perform differential diagnosis based on a Support Vector Machine model called MUQUBIA (Multimodal Quantification of Brain whIte matter biomArkers). Age, gender, Clinical Dementia Rating (CDR) Dementia Staging Instrument, and 19 imaging features formed the best set of discriminative features. The predictive model performed with an overall Area Under the Curve of 98%, high overall precision (88%), recall (88%), and F1 scores (88%) in the test group, and good Label Ranking Average Precision score (0.95) in a subset of neuropathologically assessed patients. The results of MUQUBIA were explained by the SHapley Additive exPlanations (SHAP) method. The MUQUBIA algorithm successfully classified various dementias with good performance using cost-effective clinical and MRI information, and with independent validation, has the potential to assist physicians in their clinical diagnosis.

Figure 1

Acceptable and non-acceptable outputs of each image analysis pipeline. All images and outputs have been inspected slice by slice. Images of low quality, presenting artifacts or resulting in wrong segmentation or unrealistic reconstruction were discarded.

Figure 2

Steps to create and test MUQUBIA. (a) Images of 506 subjects were processed to obtain the full set of features. (b) Missing values were replaced with median values. (c) The data were split into training set (70% of the subjects) and test set (30%) to avoid any bias in the selection of features and in the classification performance. (d) Values were standardized. (e) The full set of features was pruned to avoid overfitting using a bidirectional sequential feature selection approach. (f) The non-linear SVM model was built and fine-tuned on the training and validation sets, while being tested on the test set left aside. Acronyms: ft, features; MD, Mean Diffusivity; SVM, Support Vector Machine; WM, White Matter.

Figure 3

Representation of brain regions corresponding to imaging features selected by MUQUBIA to distinguish the different diagnostic classes (AD, DLB, FTD, CN). The color of each brain region reflects the ability of the corresponding feature to discriminate among the different classes (averaged mean Shapley value). Acronyms: L, left; R, right.

Figure 4

Contribution of each feature to the classification, represented by the mean Shapley magnitude values. The graph shows the importance of each variable for each diagnostic group. Acronyms: AD, Alzheimer’s Dementia; FTD, Frontotemporal Dementia; DLB, Dementia with Lewy Body; CN, Cognitive Normal; FA, Fractional Anisotropy; MD, Mean Diffusivity; LH, left hemisphere; RH, right hemisphere.

Figure 5

Global interpretability plots for each diagnostic class. Each dot corresponds to a subject in the training set. The position of the dot on the x-axis shows the effect of that feature on the prediction of the model for that subject. If multiple dots land at the same x position, they piled up to show density. The features are ordered by the sum of the Shapley values. Colors are used to display the standardized value of each feature (colder colors represent lower values, warmer colors represent higher values). Acronyms: AD, Alzheimer’s Dementia; FTD, Frontotemporal Dementia; DLB, Dementia with Lewy Body; CN, Cognitive Normal; LH, left hemisphere; RH, right hemisphere; FA, Fractional Anisotropy; MD, Mean Diffusivity.

Figure 6

SHAP partial dependence plots for each diagnostic class (AD, DLB, FTD, CN). Each subplot shows the marginal effect that two features have on the predicted diagnosis. Once the first feature is chosen, the second is selected based on the feature with which the first feature interacts most strongly. The color of a dot indicates the value for the second feature. The color of each plot changes progressively from blue to red (or vice-versa) as you move along the axes. Colder colors represent lower values, warmer colors represent higher values of the second feature. Acronyms: AD, Alzheimer’s Dementia; FTD, Frontotemporal Disease; DLB, Dementia with Lewy Body; CN, Cognitive Normal; LH, left hemisphere; RH, right hemisphere; FA, Fractional Anisotropy; MD, Mean Diffusivity.

Figure 7

Confusion matrix and ROC curves of the test set. The AUC of each ROC curve for each diagnostic class against all others is reported in the legend. Acronyms: AD, Alzheimer’s Dementia; FTD, Frontotemporal Disease; DLB, Dementia with Lewy Body; CN, Cognitive Normal; AUC, Area Under the Curve.