An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data

Abstract Finding effective and objective biomarkers to inform the diagnosis of schizophrenia is of great importance yet remains challenging. Relatively little work has been conducted on multi-biological data for the diagnosis of schizophrenia. In this cross-sectional study, we extracted multiple fea...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Peng-fei Ke, Dong-sheng Xiong, Jia-hui Li, Zhi-lin Pan, Jing Zhou, Shi-jia Li, Jie Song, Xiao-yi Chen, Gui-xiang Li, Jun Chen, Xiao-bo Li, Yu-ping Ning, Feng-chun Wu, Kai Wu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/cd9b79389a23479cb148f4150335e9d9
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cd9b79389a23479cb148f4150335e9d9
record_format	dspace
spelling	oai:doaj.org-article:cd9b79389a23479cb148f4150335e9d92021-12-02T16:50:23ZAn integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data10.1038/s41598-021-94007-92045-2322https://doaj.org/article/cd9b79389a23479cb148f4150335e9d92021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94007-9https://doaj.org/toc/2045-2322Abstract Finding effective and objective biomarkers to inform the diagnosis of schizophrenia is of great importance yet remains challenging. Relatively little work has been conducted on multi-biological data for the diagnosis of schizophrenia. In this cross-sectional study, we extracted multiple features from three types of biological data, including gut microbiota data, blood data, and electroencephalogram data. Then, an integrated framework of machine learning consisting of five classifiers, three feature selection algorithms, and four cross validation methods was used to discriminate patients with schizophrenia from healthy controls. Our results show that the support vector machine classifier without feature selection using the input features of multi-biological data achieved the best performance, with an accuracy of 91.7% and an AUC of 96.5% (p < 0.05). These results indicate that multi-biological data showed better discriminative capacity for patients with schizophrenia than single biological data. The top 5% discriminative features selected from the optimal model include the gut microbiota features (Lactobacillus, Haemophilus, and Prevotella), the blood features (superoxide dismutase level, monocyte-lymphocyte ratio, and neutrophil count), and the electroencephalogram features (nodal local efficiency, nodal efficiency, and nodal shortest path length in the temporal and frontal-parietal brain areas). The proposed integrated framework may be helpful for understanding the pathophysiology of schizophrenia and developing biomarkers for schizophrenia using multi-biological data.Peng-fei KeDong-sheng XiongJia-hui LiZhi-lin PanJing ZhouShi-jia LiJie SongXiao-yi ChenGui-xiang LiJun ChenXiao-bo LiYu-ping NingFeng-chun WuKai WuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Peng-fei Ke Dong-sheng Xiong Jia-hui Li Zhi-lin Pan Jing Zhou Shi-jia Li Jie Song Xiao-yi Chen Gui-xiang Li Jun Chen Xiao-bo Li Yu-ping Ning Feng-chun Wu Kai Wu An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
description	Abstract Finding effective and objective biomarkers to inform the diagnosis of schizophrenia is of great importance yet remains challenging. Relatively little work has been conducted on multi-biological data for the diagnosis of schizophrenia. In this cross-sectional study, we extracted multiple features from three types of biological data, including gut microbiota data, blood data, and electroencephalogram data. Then, an integrated framework of machine learning consisting of five classifiers, three feature selection algorithms, and four cross validation methods was used to discriminate patients with schizophrenia from healthy controls. Our results show that the support vector machine classifier without feature selection using the input features of multi-biological data achieved the best performance, with an accuracy of 91.7% and an AUC of 96.5% (p < 0.05). These results indicate that multi-biological data showed better discriminative capacity for patients with schizophrenia than single biological data. The top 5% discriminative features selected from the optimal model include the gut microbiota features (Lactobacillus, Haemophilus, and Prevotella), the blood features (superoxide dismutase level, monocyte-lymphocyte ratio, and neutrophil count), and the electroencephalogram features (nodal local efficiency, nodal efficiency, and nodal shortest path length in the temporal and frontal-parietal brain areas). The proposed integrated framework may be helpful for understanding the pathophysiology of schizophrenia and developing biomarkers for schizophrenia using multi-biological data.
format	article
author	Peng-fei Ke Dong-sheng Xiong Jia-hui Li Zhi-lin Pan Jing Zhou Shi-jia Li Jie Song Xiao-yi Chen Gui-xiang Li Jun Chen Xiao-bo Li Yu-ping Ning Feng-chun Wu Kai Wu
author_facet	Peng-fei Ke Dong-sheng Xiong Jia-hui Li Zhi-lin Pan Jing Zhou Shi-jia Li Jie Song Xiao-yi Chen Gui-xiang Li Jun Chen Xiao-bo Li Yu-ping Ning Feng-chun Wu Kai Wu
author_sort	Peng-fei Ke
title	An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
title_short	An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
title_full	An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
title_fullStr	An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
title_full_unstemmed	An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
title_sort	integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/cd9b79389a23479cb148f4150335e9d9
work_keys_str_mv	AT pengfeike anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT dongshengxiong anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT jiahuili anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT zhilinpan anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT jingzhou anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT shijiali anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT jiesong anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT xiaoyichen anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT guixiangli anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT junchen anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT xiaoboli anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT yupingning anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT fengchunwu anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT kaiwu anintegratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT pengfeike integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT dongshengxiong integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT jiahuili integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT zhilinpan integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT jingzhou integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT shijiali integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT jiesong integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT xiaoyichen integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT guixiangli integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT junchen integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT xiaoboli integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT yupingning integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT fengchunwu integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata AT kaiwu integratedmachinelearningframeworkforadiscriminativeanalysisofschizophreniausingmultibiologicaldata
_version_	1718383066602274816

An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data

Ejemplares similares