Article (Scientific journals)
A machine learning approach to explore cognitive signatures in patients with temporo-mesial epilepsy.
Roger, E; Torlay, L; Gardette, Jeremy et al.
2020In Neuropsychologia, 142, p. 107455
Peer Reviewed verified by ORBi
 

Files


Full Text
1-s2.0-S0028393220301263-main.pdf
Author postprint (1.77 MB)
Request a copy

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
Epilepsy; Language; Memory; Neuropsychology; Machine Learning; Neuropsychological Tests; Epilepsy, Temporal Lobe/complications; Epilepsy, Temporal Lobe
Abstract :
[en] We aimed to identify cognitive signatures (phenotypes) of patients suffering from mesial temporal lobe epilepsy (mTLE) with respect to their epilepsy lateralization (left or right), through the use of SVM (Support Vector Machine) and XGBoost (eXtreme Gradient Boosting) machine learning (ML) algorithms. Specifically, we explored the ability of the two algorithms to identify the most significant scores (features, in ML terms) that segregate the left from the right mTLE patients. We had two versions of our dataset which consisted of neuropsychological test scores: a "reduced and working" version (n = 46 patients) without any missing data, and another one "original" (n = 57) with missing data but useful for testing the robustness of results obtained with the working dataset. The emphasis was placed on a precautionary machine learning (ML) approach for classification, with reproducible and generalizable results. The effects of several clinical medical variables were also studied. We obtained excellent predictive classification performances (>75%) of left and right mTLE with both versions of the dataset. The most segregating features were four language and memory tests, with a remarkable stability close to 100%. Thus, these cognitive tests appear to be highly relevant for neuropsychological assessment of patients. Moreover, clinical variables such as structural asymmetry between hippocampal gyri, the age of patients and the number of anti-epileptic drugs, influenced the cognitive phenotype. This exploratory study represents an in-depth analysis of cognitive scores and allows observing interesting interactions between language and memory performance. We discuss implications of these findings in terms of clinical and theoretical applications and perspectives in the field of neuropsychology.
Disciplines :
Neurosciences & behavior
Author, co-author :
Roger, E;  Univ. Grenoble Alpes, CNRS LPNC UMR 5105, 38000, Grenoble, France
Torlay, L;  Univ. Grenoble Alpes, CNRS LPNC UMR 5105, 38000, Grenoble, France
Gardette, Jeremy  ;  Univ. Grenoble Alpes, CNRS LPNC UMR 5105, 38000, Grenoble, France
Mosca, C;  Univ. Grenoble Alpes, Grenoble Institute of Neuroscience 'Synchronisation et modulation des réseaux neuronaux dans l'épilepsie' & Neurology Department, 38000, Grenoble, France
Banjac, S;  Univ. Grenoble Alpes, CNRS LPNC UMR 5105, 38000, Grenoble, France
Minotti, L;  Univ. Grenoble Alpes, Grenoble Institute of Neuroscience 'Synchronisation et modulation des réseaux neuronaux dans l'épilepsie' & Neurology Department, 38000, Grenoble, France
Kahane, P;  Univ. Grenoble Alpes, Grenoble Institute of Neuroscience 'Synchronisation et modulation des réseaux neuronaux dans l'épilepsie' & Neurology Department, 38000, Grenoble, France
Baciu, M;  Univ. Grenoble Alpes, CNRS LPNC UMR 5105, 38000, Grenoble, France. Electronic address: monica.baciu@univ-grenoble-alpes.fr
Language :
English
Title :
A machine learning approach to explore cognitive signatures in patients with temporo-mesial epilepsy.
Publication date :
May 2020
Journal title :
Neuropsychologia
ISSN :
0028-3932
eISSN :
1873-3514
Publisher :
Elsevier, England
Volume :
142
Pages :
107455
Peer reviewed :
Peer Reviewed verified by ORBi
Funders :
ANR - Agence Nationale de la Recherche
Funding text :
This work has been funded by the French program \u201CAAP GENERIQUE 2017\u201D run by the \u201C Agence Nationale de la Recherche \u201D, grant \u201CREORG\u201D [grant number ANR-17-CE28-0015-01 ]; and by NeuroCoG IDEX UGA in the framework of the \u201C Investissements d\u2019avenir\u201D program [grant number ANR-15-IDEX-02 ].
Available on ORBi :
since 12 March 2025

Statistics


Number of views
23 (0 by ULiège)
Number of downloads
0 (0 by ULiège)

Scopus citations®
 
24
Scopus citations®
without self-citations
20
OpenCitations
 
15
OpenAlex citations
 
23

Bibliography


Similar publications



Contact ORBi