Prediction of the information processing speed performance in multiple sclerosis using a machine learning approach in a large multicenter magnetic resonance imaging data set. Issue 1 (18th October 2022)

• Record Type: Journal Article
• Authors: Marzi, Chiara; d'Ambrosio, Alessandro; Diciotti, Stefano; Bisecco, Alvino; Altieri, Manuela; Filippi, Massimo; Rocca, Maria Assunta; Storelli, Loredana; Pantano, Patrizia; Tommasin, Silvia; Cortese, Rosa; De Stefano, Nicola; Tedeschi, Gioacchino; Gallo, Antonio
• Is Part Of: Human brain mapping. Volume 44:Issue 1(2023)
• Page Start: 186
• Page End: 202
• Publication Date: 2022-10-18
• Subjects: artificial intelligence -- cognitive performance -- information processing speed -- machine learning -- MRI -- multiple sclerosis -- symbol digit modalities test; Brain mapping -- Periodicals; 611.81
• DOI: 10.1002/hbm.26106
• Languages: English
• ISSNs: 1065-9471

Abstract

Abstract: Many patients with multiple sclerosis (MS) experience information processing speed (IPS) deficits, and the Symbol Digit Modalities Test (SDMT) has been recommended as a valid screening test. Magnetic resonance imaging (MRI) has markedly improved the understanding of the mechanisms associated with cognitive deficits in MS. However, which structural MRI markers are the most closely related to cognitive performance is still unclear. We used the multicenter 3T‐MRI data set of the Italian Neuroimaging Network Initiative to extract multimodal data (i.e., demographic, clinical, neuropsychological, and structural MRIs) of 540 MS patients. We aimed to assess, through machine learning techniques, the contribution of brain MRI structural volumes in the prediction of IPS deficits when combined with demographic and clinical features. We trained and tested the eXtreme Gradient Boosting (XGBoost) model following a rigorous validation scheme to obtain reliable generalization performance. We carried out a classification and a regression task based on SDMT scores feeding each model with different combinations of features. For the classification task, the model trained with thalamus, cortical gray matter, hippocampus, and lesions volumes achieved an area under the receiver operating characteristic curve of 0.74. For the regression task, the model trained with cortical gray matter and thalamus volumes, EDSS, nucleus accumbens, lesions, and putamen volumes, and age reached a mean absolute error of 0.95. In conclusion, our results confirmed that damage to cortical gray matter and relevant deep and archaic gray matter structures, such as the thalamus and hippocampus, is among the most relevant predictors of cognitive performance in MS. Abstract : We developed an advanced machine learning pipeline to identify brain structural magnetic resonance imaging (MRI) volumes that, along with demographic and clinical data, predict information processing speed (IPS) performance, assessed with the Symbol Digit Modalities Test (SDMT), of patients with multiple sclerosis (MS). In this study, we used a multicenter 3T‐MRI data set of 540 MS patients. We confirmed that damage of cortical gray matter and relevant deep and archaic gray matter structures, such as the thalamus and hippocampus, is among the most relevant predictors of cognitive performance in MS.