TY - JOUR
T1 - Quantitative Brain MRI Metrics Distinguish Four Different ALS Phenotypes
T2 - A Machine Learning Based Study
AU - Rajagopalan, Venkateswaran
AU - Chaitanya, Krishna G.
AU - Pioro, Erik P.
N1 - Funding Information:
The authors do not report any conflict of interest relevant to the present study. E.P.P has received clinical trial and/or research funding from the ALS Association, Biogen, Inc., Biohaven Pharmaceuticals, NIH/CDC, and the Samuel J. and Connie M. Frankino Charitable Foundation. He has received consulting fees from Argenx, Amylyx, Avanir Pharmaceuticals, Inc., Biohaven Pharmaceuticals, Cytokinetics, Inc., ITF Pharma, Inc., MT Pharma America, Inc., Neurotherapia, Inc., and Otsuka America, Inc.
Publisher Copyright:
© 2023 by the authors.
PY - 2023/5
Y1 - 2023/5
N2 - Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease whose diagnosis depends on the presence of combined lower motor neuron (LMN) and upper motor neuron (UMN) degeneration. LMN degeneration assessment is aided by electromyography, whereas no equivalent exists to assess UMN dysfunction. Magnetic resonance imaging (MRI) is primarily used to exclude conditions that mimic ALS. We have identified four different clinical/radiological phenotypes of ALS patients. We hypothesize that these ALS phenotypes arise from distinct pathologic processes that result in unique MRI signatures. To our knowledge, no machine learning (ML)-based data analyses have been performed to stratify different ALS phenotypes using MRI measures. During routine clinical evaluation, we obtained T1-, T2-, PD-weighted, diffusion tensor (DT) brain MRI of 15 neurological controls and 91 ALS patients (UMN-predominant ALS with corticospinal tract CST) hyperintensity, n = 21; UMN-predominant ALS without CST hyperintensity, n = 26; classic ALS, n = 23; and ALS patients with frontotemporal dementia, n = 21). From these images, we obtained 101 white matter (WM) attributes (including DT measures, graph theory measures from DT and fractal dimension (FD) measures using T1-weighted), 10 grey matter (GM) attributes (including FD based measures from T1-weighted), and 10 non-imaging attributes (2 demographic and 8 clinical measures of ALS). We employed classification and regression tree, Random Forest (RF) and also artificial neural network for the classifications. RF algorithm provided the best accuracy (70–94%) in classifying four different phenotypes of ALS patients. WM metrics played a dominant role in classifying different phenotypes when compared to GM or clinical measures. Although WM measures from both right and left hemispheres need to be considered to identify ALS phenotypes, they appear to be differentially affected by the degenerative process. Longitudinal studies can confirm and extend our findings.
AB - Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease whose diagnosis depends on the presence of combined lower motor neuron (LMN) and upper motor neuron (UMN) degeneration. LMN degeneration assessment is aided by electromyography, whereas no equivalent exists to assess UMN dysfunction. Magnetic resonance imaging (MRI) is primarily used to exclude conditions that mimic ALS. We have identified four different clinical/radiological phenotypes of ALS patients. We hypothesize that these ALS phenotypes arise from distinct pathologic processes that result in unique MRI signatures. To our knowledge, no machine learning (ML)-based data analyses have been performed to stratify different ALS phenotypes using MRI measures. During routine clinical evaluation, we obtained T1-, T2-, PD-weighted, diffusion tensor (DT) brain MRI of 15 neurological controls and 91 ALS patients (UMN-predominant ALS with corticospinal tract CST) hyperintensity, n = 21; UMN-predominant ALS without CST hyperintensity, n = 26; classic ALS, n = 23; and ALS patients with frontotemporal dementia, n = 21). From these images, we obtained 101 white matter (WM) attributes (including DT measures, graph theory measures from DT and fractal dimension (FD) measures using T1-weighted), 10 grey matter (GM) attributes (including FD based measures from T1-weighted), and 10 non-imaging attributes (2 demographic and 8 clinical measures of ALS). We employed classification and regression tree, Random Forest (RF) and also artificial neural network for the classifications. RF algorithm provided the best accuracy (70–94%) in classifying four different phenotypes of ALS patients. WM metrics played a dominant role in classifying different phenotypes when compared to GM or clinical measures. Although WM measures from both right and left hemispheres need to be considered to identify ALS phenotypes, they appear to be differentially affected by the degenerative process. Longitudinal studies can confirm and extend our findings.
KW - ALS phenotypes
KW - MRI
KW - Random Forest
KW - machine learning
KW - neural network
UR - http://www.scopus.com/inward/record.url?scp=85159206324&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85159206324&partnerID=8YFLogxK
U2 - 10.3390/diagnostics13091521
DO - 10.3390/diagnostics13091521
M3 - Article
C2 - 37174914
AN - SCOPUS:85159206324
SN - 2075-4418
VL - 13
JO - Diagnostics
JF - Diagnostics
IS - 9
M1 - 1521
ER -