Search

Your search keyword '"Cyprien Gilet"' showing total 19 results
Start Over Author "Cyprien Gilet"
19 results on '"Cyprien Gilet"'

1. Reduced serum levels of pro-inflammatory chemokines in fragile X syndrome

Author

Anke Van Dijck, Susana Barbosa, Patricia Bermudez-Martin, Olfa Khalfallah, Cyprien Gilet, Emanuela Martinuzzi, Ellen Elinck, R. Frank Kooy, Nicolas Glaichenhaus, and Laetitia Davidovic

Subjects
Fragile X syndrome, Cytokines, Chemokines, Biomarkers, Clustering, Autism spectrum disorders, Neurology. Diseases of the nervous system, RC346-429
Abstract

Abstract Background Fragile X syndrome (FXS) is the most frequent cause of inherited intellectual disability and the most commonly identified monogenic cause of autism. Recent studies have shown that long-term pathological consequences of FXS are not solely confined to the central nervous system (CNS) but rather extend to other physiological dysfunctions in peripheral organs. To gain insights into possible immune dysfunctions in FXS, we profiled a large panel of immune-related biomarkers in the serum of FXS patients and healthy controls. Methods We have used a sensitive and robust Electro Chemi Luminescence (ECL)-based immunoassay to measure the levels of 52 cytokines in the serum of n = 25 FXS patients and n = 29 healthy controls. We then used univariate statistics and multivariate analysis, as well as an advanced unsupervised clustering method, to identify combinations of immune-related biomarkers that could discriminate FXS patients from healthy individuals. Results While the majority of the tested cytokines were present at similar levels in FXS patients and healthy individuals, nine chemokines, CCL2, CCL3, CCL4, CCL11, CCL13, CCL17, CCL22, CCL26 and CXCL10, were present at much lower levels in FXS patients. Using robust regression, we show that six of these biomarkers (CCL2, CCL3, CCL11, CCL22, CCL26 and CXCL10) were negatively associated with FXS diagnosis. Finally, applying the K-sparse unsupervised clustering method to the biomarker dataset allowed for the identification of two subsets of individuals, which essentially matched the FXS and healthy control categories. Conclusions Our data show that FXS patients exhibit reduced serum levels of several chemokines and may therefore exhibit impaired immune responses. The present study also highlights the power of unsupervised clustering methods to identify combinations of biomarkers for diagnosis and prognosis in medicine.

Published
2020
Full Text
View/download PDF

9. Box-constrained optimization for minimax supervised learning***

Author

Lionel Fillatre, Susana Barbosa, and Cyprien Gilet

Subjects
Mathematical optimization, T57-57.97, Simplex, Applied mathematics. Quantitative methods, Discretization, Computer science, Supervised learning, Probabilistic logic, Constrained optimization, MathematicsofComputing_NUMERICALANALYSIS, Function (mathematics), Minimax, QA1-939, Subgradient method, Mathematics
Abstract

In this paper, we present the optimization procedure for computing the discrete boxconstrained minimax classifier introduced in [1, 2]. Our approach processes discrete or beforehand discretized features. A box-constrained region defines some bounds for each class proportion independently. The box-constrained minimax classifier is obtained from the computation of the least favorable prior which maximizes the minimum empirical risk of error over the box-constrained region. After studying the discrete empirical Bayes risk over the probabilistic simplex, we consider a projected subgradient algorithm which computes the prior maximizing this concave multivariate piecewise affine function over a polyhedral domain. The convergence of our algorithm is established.

Published
2021

11. Réseaux de Neurones Convolutifs avec Apprentissage Minimax pour des Proportions par classe incertaines et déséquilibrées

Author

Marie Guyomard, Cyprien Gilet, Susana Barbosa, Lionel Fillatre, Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Institut de pharmacologie moléculaire et cellulaire (IPMC), Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA), and Centre National de la Recherche Scientifique [CNRS]

Subjects
Bases de données déséquilibrées, Classifieur Minimax, Changement de probabilités a priori, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Réseau de Neurones Convolutifs, [INFO]Computer Science [cs]
Abstract

International audience; Ce papier propose une nouvelle approche ajustant les réseaux de neurones convolutifs appliqués sur des jeux de données déséquilibrés dont les proportions par classes sont incertaines. La règle de décision constitutant la sortie du réseau de neurones est remplacée par le classifieur Minimax dont la particularité est de chercher à égaliser les risques conditionnels. De ce fait, le réseau de neurones devient robuste au déséquilibre des bases de données ainsi qu’au changement de probabilités a priori. Des expériences numériques sur des images médicales mettent en évidence la pertinence de notre approche quand il est nécessaire de classifier correctement les classes les moins représentées. Les résultats obtenus sur la base de données CIFAR100 démontre l’extensibilité de notre méthode en présence d’un grand nombre de classes.

Published
2021

12. Baseline Levels of C-Reactive Protein and Proinflammatory Cytokines Are Not Associated with Early Response to Amisulpride in Patients with First Episode Psychosis

Author

W. Wolfgang Fleischhacker, René S. Kahn, Robert H. Yolken, El Chérif Ibrahim, Celso Arango, Olfa Khalfallah, Susana Barbosa, Richard Drake, Laetitia Davidovic, Philip McGuire, Shôn Lewis, Inge Winter van Rossum, Dan Rujescu, Cyprien Gilet, Paola Dazzan, Emanuela Martinuzzi, Raoul Belzeaux, Marion Leboyer, Birte Glenthøj, Nicolas Glaichenhaus, Covadonga M. Díaz-Caneja, Stefan Leucht, Iris E. C. Sommer, Institut de pharmacologie moléculaire et cellulaire (IPMC), Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA), Centre Hospitalier Universitaire de Nice (CHU Nice), University Medical Center Groningen [Groningen] (UMCG), University of Bergen (UiB), King‘s College London, Hospital General Universitario 'Gregorio Marañón' [Madrid], Innsbruck Medical University [Austria] (IMU), University of Halle, Partenaires INRAE, Glostrup Hospital, IT University of Copenhagen, University Medical Center [Utrecht], Icahn School of Medicine at Mount Sinai [New York] (MSSM), Johns Hopkins University School of Medicine [Baltimore], University of Manchester [Manchester], Technische Universität Munchen - Université Technique de Munich [Munich, Allemagne] (TUM), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Institut de Neurosciences de la Timone (INT), Aix Marseille Université (AMU)-Centre National de la Recherche Scientifique (CNRS), Fondation FondaMental [Créteil], Département Universitaire de Psychiatrie - [Hôpital Sainte Marguerite - APHM] (Hôpitaux Sud), Hôpital Sainte-Marguerite [CHU - APHM] (Hôpitaux Sud )-Assistance Publique - Hôpitaux de Marseille (APHM)-Aix Marseille Université (AMU), Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), CHU Henri Mondor, Movement Disorder (MD), Clinical Cognitive Neuropsychiatry Research Program (CCNP), Université Nice Sophia Antipolis (1965 - 2019) (UNS), IT University of Copenhagen (ITU), Aix Marseille Université (AMU)-Assistance Publique - Hôpitaux de Marseille (APHM)-Hôpital Sainte-Marguerite [CHU - APHM] (Hôpitaux Sud ), Technische Universität München [München] (TUM), Innsbruck Medical University = Medizinische Universität Innsbruck (IMU), and CHU Henri Mondor [Créteil]

Subjects
0301 basic medicine, Psychosis, medicine.medical_specialty, Proinflammatory cytokine, 03 medical and health sciences, 0302 clinical medicine, remission, Internal medicine, medicine, Amisulpride, psychosis, Adverse effect, Positive and Negative Syndrome Scale, biology, business.industry, C-reactive protein, longitudinal study, medicine.disease, 3. Good health, Clinical trial, Psychiatry and Mental health, 030104 developmental biology, inflammation, [SDV.MHEP.PSM]Life Sciences [q-bio]/Human health and pathology/Psychiatrics and mental health, proinflammatory cytokines, biology.protein, business, 030217 neurology & neurosurgery, medicine.drug, Cohort study
Abstract

Background Patients with a First-Episode of Psychosis (FEP) exhibit low-grade inflammation as demonstrated by elevated levels of C reactive protein (CRP) and pro-inflammatory cytokines. Aims The primary goal of this study was to investigate the association between pro-inflammatory biomarkers and clinical outcomes in unmedicated FEP patients. Method We used clinical data and biological samples from 289 FEP patients participating to the Optimization of Treatment and Management of Schizophrenia in Europe (OPTIMISE) clinical trial. Patients were assessed at baseline and 4-5 weeks after treatment with amisulpride. Baseline serum levels of interleukin (IL)-6, IL-8, Tumor Necrosis Factor (TNF)-α and CRP were measured. We first used multivariable regression to investigate the association between each of the four tested biomarkers and the following clinical outcomes: Positive And Negative Syndrome Scale (PANSS), Calgary Depression Score for Schizophrenia (CDSS), remission according to Andreasen’s criteria and Serious Adverse Events (SAEs). As a complementary approach, we used an unsupervised clustering method to stratify patients into an “inflamed” or a “non-inflamed” biotype based on baseline levels of IL-6, IL-8 and TNF-α. We then used linear and logistic regressions to investigate the association between the patient biotype and clinical outcomes. Results After adjusting for covariates and confounders, we did not find any association between IL-6, IL-8, TNF-α, CRP or the patient biotype and clinical outcomes. Implications Our results do not support the existence of an association between baseline levels of CRP and proinflammatory cytokines and early response to amisulpride in unmedicated FEP patients.

Published
2021
Full Text
View/download PDF

13. Discrete Box-Constrained Minimax Classifier for Uncertain and Imbalanced Class Proportions

Author

Lionel Fillatre, Susana Barbosa, Cyprien Gilet, Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Institut de pharmacologie moléculaire et cellulaire (IPMC), Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-Université Côte d'Azur (UCA), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MEDIACODING, Signal, Images et Systèmes (Laboratoire I3S - SIS), COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015 - 2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S)

Subjects
Multivariate statistics, Databases, Factual, Γ-Minimax Classifier, Computer science, Imbalanced datasets, Bayesian Robustness, 02 engineering and technology, Naive Bayes classifier, Bayes' theorem, Minimax Classifier, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Artificial Intelligence, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Prior probability, Discrete Bayes Classifier, 0202 electrical engineering, electronic engineering, information engineering, Cluster Analysis, Cluster analysis, Categorical variable, Subgradient method, business.industry, Applied Mathematics, Pattern recognition, Bayes Theorem, Maximization, Minimax, Histogram Rule, ComputingMethodologies_PATTERNRECOGNITION, Computational Theory and Mathematics, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], business, Prior Probability Shift, Classifier (UML), Software, Algorithms, Uncertain Class Proportions
Abstract

International audience; This paper aims to build a supervised classifier for dealing with imbalanced datasets, uncertain class proportions, dependencies between features, the presence of both numeric and categorical features, and arbitrary loss functions. The Bayes classifier suffers when prior probability shifts occur between the training and testing sets. A solution is to look for an equalizer decision rule whose class-conditional risks are equal. Such a classifier corresponds to a minimax classifier when it maximizes the Bayes risk. We develop a novel box-constrained minimax classifier which takes into account some constraints on the priors to control the risk maximization. We analyze the empirical Bayes risk with respect to the box-constrained priors for discrete inputs. We show that this risk is a concave non-differentiable multivariate piecewise affine function. A projected subgradient algorithm is derived to maximize this empirical Bayes risk over the box-constrained simplex. Its convergence is established and its speed is bounded. The optimization algorithm is scalable when the number of classes is large. The robustness of our classifier is studied on diverse databases. Our classifier, jointly applied with a clustering algorithm to process mixed attributes, tends to balance the class-conditional risks while being not too pessimistic.

Published
2020
Full Text
View/download PDF

14. Anomaly Detection with Discrete Minimax Classifier for Imbalanced dataset or Uncertain Class Proportions

Author

Lionel Fillatre, Cyprien Gilet, Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MEDIACODING, Signal, Images et Systèmes (Laboratoire I3S - SIS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S)

Subjects
Training set, Discretization, business.industry, Computer science, 010102 general mathematics, Condition monitoring, 02 engineering and technology, Decision rule, Minimax, Machine learning, computer.software_genre, 01 natural sciences, ComputingMethodologies_PATTERNRECOGNITION, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Anomaly detection, Artificial intelligence, 0101 mathematics, Decision-making, business, computer, Classifier (UML), ComputingMilieux_MISCELLANEOUS
Abstract

Supervised classification is becoming a useful tool in condition monitoring. For example, from a set of measured features (temperature, vibration, etc.), we might be interested in predicting machine failures. Given some costs of class misclassifications and a set of labeled learning samples, this task aims to fit a decision rule by minimizing the empirical risk of misclassifications. However, learning a classifier when the class proportions of the training set are uncertain, and might differ from the unknown state of nature, may increase the misclassification risk when classifying some test samples. This drawback can also occur when dealing with imbalanced datasets, which is common in condition monitoring. To make a decision rule robust with respect to the class proportions, a solution is to learn a decision rule which minimizes the maximum class-conditional risk. Such a decision rule is called a minimax classifier. This paper studies the minimax classifier for classifying discrete or discretized features between several classes. Our algorithm is applied to a real condition monitoring database.

Published
2019

15. Correction: Stratification and prediction of remission in first-episode psychosis patients: the OPTiMiSE cohort study

Author

Richard Drake, Nicolas Glaichenhaus, Susana Barbosa, Laetitia Davidovic, René S. Kahn, Lionel Fillatre, Marion Leboyer, Dan Rujescu, Shôn Lewis, Stefan Leucht, Celso Arango, Stéphane Jamain, Olfa Khalfallah, Douglas Daoudlarian, Rejane Troudet, Guillaume Fond, Iris E. C. Sommer, Cyprien Gilet, Birte Glenthøj, Robert H. Yolken, Philip McGuire, W. Wolfgang Fleischhacker, Paola Dazzan, Emanuela Martinuzzi, Covadonga M. Díaz-Caneja, Wafa Bel Haj Ali, Inge Winter, Diabète de Type 1 : mécanismes et traitements immunologiques, Université Paris Descartes - Paris 5 (UPD5)-Institut National de la Santé et de la Recherche Médicale (INSERM), Institut de pharmacologie moléculaire et cellulaire (IPMC), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Laboratoire Modélisation et Sûreté des Systèmes (LM2S), Institut Charles Delaunay (ICD), Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS)-Université de Technologie de Troyes (UTT)-Centre National de la Recherche Scientifique (CNRS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS), Institut Mondor de Recherche Biomédicale (IMRB), Institut National de la Santé et de la Recherche Médicale (INSERM)-IFR10-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), Aix Marseille Université (AMU), Assistance Publique - Hôpitaux de Marseille (APHM), Brain Centre Rudolf Magnus [Utrecht], University Medical Center [Utrecht], Psychological Medicine, Dept. of Psychiatry, Adolescent Unit, Hospital General Universitario Gregorio Marañón, Division of Psychiatric Genomics, Icahn School of Medicine at Mount Sinai [New York] (MSSM), Stanley Laboratory of Developmental Neurovirology, Johns Hopkins University Medical Center, COMUE Université Côte d'Azur (2015-2019) (COMUE UCA), Immunologie des Maladies Infectieuses Allergiques et Autoimmunes, COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Institut National de la Santé et de la Recherche Médicale (INSERM), Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA), Université Nice Sophia Antipolis (... - 2019) (UNS), and Assistance Publique-Hôpitaux de Marseille (AP-HM)

Subjects
Pediatrics, medicine.medical_specialty, business.industry, 05 social sciences, Stratification (mathematics), 03 medical and health sciences, Cellular and Molecular Neuroscience, Psychiatry and Mental health, 0302 clinical medicine, First episode psychosis, [SDV.MHEP.PSM]Life Sciences [q-bio]/Human health and pathology/Psychiatrics and mental health, 0502 economics and business, ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, Medicine, 050211 marketing, business, 030217 neurology & neurosurgery, Biological Psychiatry, ComputingMilieux_MISCELLANEOUS, Cohort study
Abstract

The original Article did not feature the list of collaborators. This has now been corrected in the PDF and HTML versions of this Article.

Published
2019
Full Text
View/download PDF

16. Reduced serum levels of pro-inflammatory chemokines in Fragile X Syndrome

Author

Anke Van Dijck, Susana Barbosa, Patricia Bermudez-Martin, Olfa Khalfallah, Cyprien Gilet, Ellen Elinck, R Frank Kooy, Nicolas Glaichenhaus, and Laetitia Davidovic

Subjects
congenital, hereditary, and neonatal diseases and abnormalities
Abstract

Background: Fragile X syndrome (FXS) is the most frequent cause of inherited intellectual disability and the most commonly identified monogenic cause of autism. Recent studies have shown that long-term pathological consequences of FXS are not solely confined to the central nervous system (CNS) but rather extend to other physiological dysfunctions in peripheral organs. To gain insights into possible immune dysfunctions in FXS, we profiled a large panel of immune-related biomarkers in the serum of FXS patients and healthy controls. Methods: We have used a sensitive and robust ElectroChemiLuminescence (ECL)-based immunoassay to measure the levels of 52 cytokines in the serum of n=25 FXS patients and n=29 healthy controls. We then used univariate statistics and multivariate analysis, as well as an advanced unsupervised clustering method, to identify combinations of immune-related biomarkers that could discriminate FXS patients from healthy individuals. Results: While the majority of the tested cytokines were present at similar levels in FXS patients and healthy individuals, nine chemokines, CCL2, CCL3, CCL4, CCL11, CCL13, CCL17, CCL22, CCL26 and CXCL10, were present at much lower levels in FXS patients. Applying the K-sparse unsupervised clustering method to the biomarker dataset allowed for the identification of two subsets of individuals, which essentially matched the FXS and healthy control categories. Conclusions: Our data suggest that FXS patients exhibit reduced serum levels of several chemokines and may therefore exhibit impaired immune responses. The present study also highlights the power of unsupervised clustering methods to identify combinations of biomarkers for diagnosis and prognosis in medicine.

Published
2019
Full Text
View/download PDF

17. Apprentissage d'un classificateur minimax pour données discrètes

Author

Cyprien Gilet, Susana Barbosa, Lionel Fillatre, Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Institut de pharmacologie moléculaire et cellulaire (IPMC), Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MEDIACODING, Signal, Images et Systèmes (Laboratoire I3S - SIS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S)

Subjects
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML], ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Published
2019

18. 17.4 STRATIFICATION AND PREDICTION OF REMISSION IN FIRST-EPISODE PSYCHOSIS PATIENTS: THE OPTiMISE COHORT STUDY

Author

Stefan Leucht, Stéphane Jamain, W. Wolfgang Fleischhacker, Celso Arango, Richard Drake, Nicolas Glaichenhaus, Iris E. C. Sommer, Emanuella Martinuzzi, Susana Barbosa, René S. Kahn, Covadonga M. Díaz-Caneja, Cyprien Gilet, Shôn Lewis, Dan Rujescu, Davidovic Laetitia, Robert H. Yolken, Philip McGuire, Paola Dazzan, Birte Glenthøj, and Marion Leboyer

Subjects
Plenary/Symposia, Psychiatry and Mental health, Pediatrics, medicine.medical_specialty, business.industry, First episode psychosis, Medicine, business, Stratification (mathematics), Cohort study
Abstract

BACKGROUND: Early response to first-line antipsychotics is associated with positive long-term symptomatic outcome in psychosis. Unfortunately, attempts to identify reliable predictors of treatment response in first-episode psychosis (FEP) patients have not yet been successful. One reason for this could be that FEP patients are heterogeneous in terms of symptoms and underlying disease biological mechanisms, thereby impeding the identification of one-size-fits-all predictors of treatment response. METHODS: We have used a two-step hierarchical clustering approach to stratify 325 FEP patients into four subtypes, termed C1A, C1B, C2A and C2B, based on their symptoms assessed using the Positive and Negative Syndrome Scale. After validating our clustering approach on external measures, we then used a regularized logistic regression method to identify biological and clinical variables associated with increased odds of being non-remitters within each subtype. RESULTS: Compared to those from the other subtypes, C1A patients exhibited higher serum levels of several pro-inflammatory cytokines and were the most at risk of being non-remitters when treated with a second-generation antipsychotic drug. In C1A patients, but not in others, lower serum levels of interleukin-15, higher levels of C-X-C motif chemokine 12, previous exposure to cytomegalovirus, use of recreational drugs and a younger age were all associated with higher odds of being non-remitters 4 weeks after treatment. The predictive value of this model was 73%, and its specificity and sensitivity were 45% and 83% respectively. CONCLUSIONS: Serum levels of two cytokines combined with three clinical variables predict remission in a subtype of FEP patients.

Published
2019

19. Apprentissage d’un classifieur minimax pour données discrètes

Author

Cyprien Gilet, Susana Barbosa, Lionel Fillatre, Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA), Institut de pharmacologie moléculaire et cellulaire (IPMC), Centre National de la Recherche Scientifique (CNRS)-Université Nice Sophia Antipolis (... - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Université Côte d'Azur (UCA), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia-Antipolis (I3S) / Projet MEDIACODING, Signal, Images et Systèmes (Laboratoire I3S - SIS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (... - 2019) (UNS), and COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S)

Subjects
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML], ComputingMilieux_MISCELLANEOUS
Abstract

International audience

Catalog

Books, media, physical & digital resources
See catalog results