AUTHOR=Wang Shoufei , Liu Wenfei , Ye Ziheng , Xia Xiaotian , Guo Minggao 

TITLE=Development of a joint diagnostic model of thyroid papillary carcinoma with artificial neural network and random forest

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.957718

DOI=10.3389/fgene.2022.957718

ISSN=1664-8021

ABSTRACT=Objective: Papillary thyroid carcinoma (PTC) is the most common pathological type of thyroid cancer and the incidence of PTC is increasing rapidly. This study aimed to identify novel and significant biomarkers and perform a early diagnostic model for PTC by using random forest (RF) algorithm and artificial neural network (ANN).
Methods and Results: Through a search of the Gene Expression Omnibus (GEO) database, gene expression datasets (GSE27155, GSE60542 and GSE33630) were downloaded and preprocessed. GSE27155 and GSE60542 were merged as training set, GSE33630 as internal validation set. Differentially expressed genes (DEGs) in training set were identified by R software, followed by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis and immune cell infiltration. Then, RF was used to identify important genes from the DEGs, and an PTC diagnostic model was established by ANN. Finally, the validation set was used to validate the model and the area under the receiver operating characteristic curve (ROC) value was 0.968.
Conclusion: Potential PTC-associated gene biomarkers were identified by RF, and a novel early diagnostic model of PTC was established by ANN. The AUC indicated that the diagnostic model had a highly satisfactory diagnostic performance.