Development and validation of immune-based biomarkers and deep learning models for Alzheimer’s disease

Abstract

Background: Alzheimer’s disease (AD) is the most common form of dementia in old age and poses a severe threat to the health and life of the elderly. However, traditional diagnostic methods and the ATN diagnostic framework have limitations in clinical practice. Developing novel biomarkers and diagnostic models is necessary to complement existing diagnostic procedures.Methods: The AD expression profile dataset GSE63060 was downloaded from the NCBI GEO public database for preprocessing. AD-related differentially expressed genes were screened using a weighted co-expression network and differential expression analysis, and functional enrichment analysis was performed. Subsequently, we screened hub genes by random forest, analyzed the correlation between hub genes and immune cells using ssGSEA, and finally built an AD diagnostic model using an artificial neural network and validated it.Results: Based on the random forest algorithm, we screened a total of seven hub genes from AD-related DEGs, based on which we confirmed that hub genes play an essential role in the immune microenvironment and successfully established a novel diagnostic model for AD using artificial neural networks, and validated its effectiveness in the publicly available datasets GSE63060 and GSE97760.Conclusion: Our study establishes a reliable model for screening and diagnosing AD that provides a theoretical basis for adding diagnostic biomarkers for the AD gene.

Neural Computation-Based Methods for the Early Diagnosis and Prognosis of Alzheimer’s Disease Not Using Neuroimaging Biomarkers: A Systematic Review

“…According to the descriptions and figures with the ANN diagrams in those articles and after checking the documentation of the R package that they used for ML, either those figures were incorrect, or those authors have erroneously used the word “layers” instead of “neurons”. He et al [ 130 ] concluded that, after screening seven hub genes from AD-related differentially expressed genes, hub genes are key in the immune microenvironment. The RF in [ 131 ] was able to screen six important genes, critical for separating AD and normal samples.…”

“…Three articles included in this review utilized a RF for feature selection and an ANN with only 5 hidden neurons for classification [130][131][132]. According to the descriptions and figures with the ANN diagrams in those articles and after checking the documentation of the R package that they used for ML, either those figures were incorrect, or those authors have erroneously used the word "layers" instead of "neurons".…”

Identification of potential immune-related hub genes in Parkinson’s disease based on machine learning and development and validation of a diagnostic classification model

“…Gray modules are used to place genes that are not attributed to any of the modules and are not considered to be of clinical analysis. Correlations between model eigengenes (ME) and clinical characteristics were calculated using Pearson correlation coefficients for each module, including Brown, Red, Purple and Yellow for the four modules at P<0.05 [ 31 ]. We then calculated the relationship between gene expression levels and clinical performance for these four modules using Pearson correlation coefficients.…”

Machine learning models identify ferroptosis-related genes as potential diagnostic biomarkers for Alzheimer’s disease

“…On the basis of some research, ferroptosis has been shown to be involved in the pathological process of AD ( Ayton et al, 2020 ; Sun Y. et al, 2022 ; Wang et al, 2022c ). In the previous studies, to promote the development of diagnosis, researchers have explored candidate factors such as immune-based biomarkers ( He et al, 2022 ), DNA methylation-related biomarkers ( Chen et al, 2022 ) and aging-related biomarkers ( Zhang Q. et al, 2022 ). The diagnostic link between ferroptosis and AD is not well studied.…”