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

Подход на основе машинного обучения для дифференциальной диагностики болезни Альцгеймера и сосудистой деменции с использованием признаков, отобранных по данным МРТ
Giovanni Magenes, Daniele Martinelli, Maria Giovanna Cuzzoni, Giuseppe Micieli, Gloria Castellazzi, Egidio Ugo D'Angelo, Alfredo Cardoso Costa, Elena Sinforiani, Sara Bernini, Fulvia Palesi, Claudia A. M. Gandini Wheeler‐Kingshott, Matteo Cotta Ramusino, Federica M. Denaro, Antonio Ricciardi, Paolo Vitali, Nicoletta Anzalone
2020-06-11

Alzheimer diseasediffusion tensor imagingmachine learningresting-state fMRIvascular dementia
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.
1
Among ANN, SVM, and ANFIS models, ANFIS most effectively discriminated Alzheimer disease from vascular dementia, achieving classification accuracy above 84% with a small feature pattern.
2
Applying the best Alzheimer–vascular dementia discriminant pattern to 15 patients with mixed clinical profiles yielded a 77% correct prediction rate, compared with three-year clinical follow-up evidence.
3
Machine-learning models combining advanced MRI features were evaluated for distinguishing Alzheimer disease from vascular dementia and predicting disease prevalence in clinically mixed cases.
4
Multimodal MRI inputs combining DTI and resting-state fMRI metrics improved ANFIS classification accuracy compared with unimodal feature sets.

Alzheimer disease, vascular dementia, and mixed VD-AD dementia patients characterized by MRI-derived features

MRI-feature-based differential classification of Alzheimer disease versus vascular dementia and prediction of disease prevalence in clinically ambiguous mixed cases

Publication Details
Publication Date
2020-06-11
Journal
Publisher
ISSN
Cited by
142
Access Type
Author Information
Authors
Giovanni Magenes
Daniele Martinelli
Maria Giovanna Cuzzoni
Giuseppe Micieli
Gloria Castellazzi
Egidio Ugo D'Angelo
Alfredo Cardoso Costa
Elena Sinforiani
Sara Bernini
Fulvia Palesi
Claudia A. M. Gandini Wheeler‐Kingshott
Matteo Cotta Ramusino
Federica M. Denaro
Antonio Ricciardi
Paolo Vitali
Nicoletta Anzalone
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%