Dataset Information

A Predictive Model for Guillain-Barre Syndrome Based on Ensemble Methods.

ABSTRACT: Nowadays, Machine Learning methods have proven to be highly effective on the identification of various types of diseases, in the form of predictive models. Guillain-Barré syndrome (GBS) is a potentially fatal autoimmune neurological disorder that has barely been studied with computational techniques and few predictive models have been proposed. In a previous study, single classifiers were successfully used to build a predictive model. We believe that a predictive model is imperative to carry out adequate treatment in patients promptly. We designed three classification experiments: (1) using all four GBS subtypes, (2) One versus All (OVA), and (3) One versus One (OVO). These experiments use a real-world dataset with 129 instances and 16 relevant features. Besides, we compare five state-of-the-art ensemble methods against 15 single classifiers with 30 independent runs. Standard performance measures were used to obtain the best classifier in each experiment. Derived from the experiments, we conclude that Random Forest showed the best results in four GBS subtypes classification, no ensemble method stood out over the rest in OVA classification, and single classifiers outperformed ensemble methods in most cases in OVO classification. This study presents a novel predictive model for classification of four subtypes of Guillain-Barré syndrome. Our model identifies the best method for each classification case. We expect that our model could assist specialized physicians as a support tool and also could serve as a basis to improved models in the future.

SUBMITTER: Canul-Reich J

PROVIDER: S-EPMC6247730 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Predictive Model for Guillain-Barré Syndrome Based on Ensemble Methods.

Canul-Reich Juana J Hernández-Torruco José J Chávez-Bosquez Oscar O Hernández-Ocaña Betania B

Computational intelligence and neuroscience 20181105

Nowadays, Machine Learning methods have proven to be highly effective on the identification of various types of diseases, in the form of predictive models. Guillain-Barré syndrome (GBS) is a potentially fatal autoimmune neurological disorder that has barely been studied with computational techniques and few predictive models have been proposed. In a previous study, single classifiers were successfully used to build a predictive model. We believe that a predictive model is imperative to carry out ...[more]

PMID: 30532769

Similar Datasets

Project description:BackgroundGuillain-Barré syndrome (GBS) is an acute inflammatory neuropathy with a heterogeneous presentation. Although some evidences support the role of autoantibodies in its pathogenesis, the target antigens remain unknown in a substantial proportion of GBS patients. The objective of this study is to screen for autoantibodies targeting peripheral nerve components in Guillain-Barré syndrome.MethodsAutoantibody screening was performed in serum samples from all GBS patients included in the International GBS Outcome study by 11 different Spanish centres. The screening included testing for anti-ganglioside antibodies, anti-nodo/paranodal antibodies, immunocytochemistry on neuroblastoma-derived human motor neurons and murine dorsal root ganglia (DRG) neurons, and immunohistochemistry on monkey peripheral nerve sections. We analysed the staining patterns of patients and controls. The prognostic value of anti-ganglioside antibodies was also analysed.ResultsNone of the GBS patients (n = 100) reacted against the nodo/paranodal proteins tested, and 61 (61%) were positive for, at least, one anti-ganglioside antibody. GBS sera reacted strongly against DRG neurons more frequently than controls both with IgG (6% vs 0%; p = 0.03) and IgM (11% vs 2.2%; p = 0.02) immunodetection. No differences were observed in the proportion of patients reacting against neuroblastoma-derived human motor neurons. Reactivity against monkey nerve tissue was frequently detected both in patients and controls, but specific patterns were only detected in GBS patients: IgG from 13 (13%) patients reacted strongly against Schwann cells. Finally, we confirmed that IgG anti-GM1 antibodies are associated with poorer outcomes independently of other known prognostic factors.ConclusionOur study confirms that (1) GBS patients display a heterogeneous repertoire of autoantibodies targeting nerve cells and structures; (2) gangliosides are the most frequent antigens in GBS patients and have a prognostic value; (3) further antigen-discovery experiments may elucidate other potential antigens in GBS.

Dataset Information

A Predictive Model for Guillain-Barre Syndrome Based on Ensemble Methods.

Publications

A Predictive Model for Guillain-Barré Syndrome Based on Ensemble Methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets