Construction and Analysis of a Joint Diagnosis Model of Random Forest and Artificial Neural Network for Obesity

Yu, Jian; Xie, Xiulan; Zhang, Yun; Jiang, Feng; Wu, Chuyan

doi:10.3389/fmed.2022.906001

Cited by 6 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thanks to the rapid development of high-throughput sequencing technology and gene chip technology, more and more researchers are actively pursuing molecular markers using data mining and analysis of sequencing data or gene chips to the diagnosis and treatment of disease ( 19 , 43 , 44 ). In our study, we analyzed gene expression profiles of NASH patients and normal controls from five independent GEO data sets.…”

Section: Discussionmentioning

confidence: 99%

Integrative network-based analysis on multiple Gene Expression Omnibus datasets identifies novel immune molecular markers implicated in non-alcoholic steatohepatitis

Zhang

Shen²,

Chen³

et al. 2023

Front. Endocrinol.

View full text Add to dashboard Cite

IntroductionNon-alcoholic steatohepatitis (NASH), an advanced subtype of non-alcoholic fatty liver disease (NAFLD), has becoming the most important aetiology for end-stage liver disease, such as cirrhosis and hepatocellular carcinoma. This study were designed to explore novel genes associated with NASH.MethodsHere, five independent Gene Expression Omnibus (GEO) datasets were combined into a single cohort and analyzed using network biology approaches.Results11 modules identified by weighted gene co-expression network analysis (WGCNA) showed significant association with the status of NASH. Further characterization of four gene modules of interest demonstrated that molecular pathology of NASH involves the upregulation of hub genes related to immune response, cholesterol and lipid metabolic process, extracellular matrix organization, and the downregulation of hub genes related to cellular amino acid catabolic, respectively. After DEGs enrichment analysis and module preservation analysis, the Turquoise module associated with immune response displayed a remarkably correlation with NASH status. Hub genes with high degree of connectivity in the module, including CD53, LCP1, LAPTM5, NCKAP1L, C3AR1, PLEK, FCER1G, HLA-DRA and SRGN were further verified in clinical samples and mouse model of NASH. Moreover, single-cell RNA-seq analysis showed that those key genes were expressed by distinct immune cells such as microphages, natural killer, dendritic, T and B cells. Finally, the potential transcription factors of Turquoise module were characterized, including NFKB1, STAT3, RFX5, ILF3, ELF1, SPI1, ETS1 and CEBPA, the expression of which increased with NASH progression.DiscussionIn conclusion, our integrative analysis will contribute to the understanding of NASH and may enable the development of potential biomarkers for NASH therapy.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrative network-based analysis on multiple Gene Expression Omnibus datasets identifies novel immune molecular markers implicated in non-alcoholic steatohepatitis

Zhang

Shen²,

Chen³

et al. 2023

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…We used R packet “randomforest” to classify IVDD-Mito_Genes. The random forest model calculated the average error rate of IVDD-Mito_Genes to determine the optimal number of variables ( Xie et al, 2022 ; Yu et al, 2022 ). We then calculate the error rate for each tree and determine the optimal number of trees based on the lowest error rate.…”

Section: Methodsmentioning

confidence: 99%

Identification of mitochondria-related key gene and association with immune cells infiltration in intervertebral disc degeneration

Guo

Mu²,

et al. 2023

Front. Genet.

View full text Add to dashboard Cite

Intervertebral disc (IVD) degeneration and its inflammatory microenvironment can result in discogenic pain, which has been shown to stem from the nucleus pulposus (NP). Increasing evidence suggests that mitochondrial related genes are strictly connected to cell functionality and, importantly, it can regulate cell immune activity in response to damaged associated signals. Therefore, identification of mitochondria related genes might offer new diagnostic markers and therapeutic targets for IVD degeneration. In this study, we identified key genes involved in NP tissue immune cell infiltration during IVD degeneration by bioinformatic analysis. The key modules were screened by weighted gene co-expression network analysis (WCGNA). Characteristic genes were identified by random forest analysis. Then gene set enrichment analysis (GSEA) was used to explore the signaling pathways associated with the signature genes. Subsequently, CIBERSORT was used to classify the infiltration of immune cells. Function of the hub gene was confirmed by PCR, Western blotting and ELISA. Finally, we identified MFN2 as a crucial molecule in the process of NP cell pyroptosis and NLRP3 inflammasome activation. We speculate that the increased MFN2 expression in NP tissue along with the infiltration of CD8+ T cells, NK cell and neutrophils play important roles in the pathogenesis of IVD degeneration.

show abstract

“…The former two are statistical models while the latter three are machine learning or artificial intelligence (AI) models. We use machine learning models instead of only statistical models alone because there has been an increasing interest in using AI models for health studies [51][52][53]. AI models are often based on mechanisms quite different from statistical models, such as neurons and decision trees.…”

Section: Statistical and Machine Learning Modelsmentioning

confidence: 99%

Deriving neighborhood-level diet and physical activity measurements from anonymized mobile phone location data for enhancing obesity estimation

Zhou

Tirabassi

et al. 2022

Int J Health Geogr

View full text Add to dashboard Cite

Background Obesity is a serious public health problem. Existing research has shown a strong association between obesity and an individual’s diet and physical activity. If we extend such an association to the neighborhood level, information about the diet and physical activity of the residents of a neighborhood may improve the estimate of neighborhood-level obesity prevalence and help identify the neighborhoods that are more likely to suffer from obesity. However, it is challenging to measure neighborhood-level diet and physical activity through surveys and interviews, especially for a large geographic area. Methods We propose a method for deriving neighborhood-level diet and physical activity measurements from anonymized mobile phone location data, and examine the extent to which the derived measurements can enhance obesity estimation, in addition to the socioeconomic and demographic variables typically used in the literature. We conduct case studies in three different U.S. cities, which are New York City, Los Angeles, and Buffalo, using anonymized mobile phone location data from the company SafeGraph. We employ five different statistical and machine learning models to test the potential enhancement brought by the derived measurements for obesity estimation. Results We find that it is feasible to derive neighborhood-level diet and physical activity measurements from anonymized mobile phone location data. The derived measurements provide only a small enhancement for obesity estimation, compared with using a comprehensive set of socioeconomic and demographic variables. However, using these derived measurements alone can achieve a moderate accuracy for obesity estimation, and they may provide a stronger enhancement when comprehensive socioeconomic and demographic data are not available (e.g., in some developing countries). From a methodological perspective, spatially explicit models overall perform better than non-spatial models for neighborhood-level obesity estimation. Conclusions Our proposed method can be used for deriving neighborhood-level diet and physical activity measurements from anonymized mobile phone data. The derived measurements can enhance obesity estimation, and can be especially useful when comprehensive socioeconomic and demographic data are not available. In addition, these derived measurements can be used to study obesity-related health behaviors, such as visit frequency of neighborhood residents to fast-food restaurants, and to identify primary places contributing to obesity-related issues.

show abstract

Construction and Analysis of a Joint Diagnosis Model of Random Forest and Artificial Neural Network for Obesity

Cited by 6 publications

References 33 publications

Integrative network-based analysis on multiple Gene Expression Omnibus datasets identifies novel immune molecular markers implicated in non-alcoholic steatohepatitis

Integrative network-based analysis on multiple Gene Expression Omnibus datasets identifies novel immune molecular markers implicated in non-alcoholic steatohepatitis

Identification of mitochondria-related key gene and association with immune cells infiltration in intervertebral disc degeneration

Deriving neighborhood-level diet and physical activity measurements from anonymized mobile phone location data for enhancing obesity estimation

Contact Info

Product

Resources

About