Related Experiment Video
Updated: Jul 12, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Creation of a Rat Takotsubo Syndrome Model and Utilization of Machine Learning Algorithms for Screening Diagnostic
Hongyu Huai1, Junliang Li2, Xiangjie Zhang1
1Key Laboratory of Medical Electrophysiology, Ministry of Education & Medical Electrophysiological Key Laboratory of Sichuan Province, Institute of Cardiovascular Research, Southwest Medical University, Luzhou, People's Republic of China.
Introduction:
Ferroptosis, a crucial type of programmed cell death, is directly linked to various cardiac disorders. However, the contribution of ferroptosis-related genes (FRGs) to Takotsubo syndrome (TTS) has not been completely understood.
Purpose:
The objective of this study was to investigate the relationship between the FRGs and TTS.
Methods:
TTS rat models were established by isoprenaline injection. Heart tissues were subsequently harvested for total RNA extraction and library construction. Transcriptome data wereobtained transcriptome data for TTS and FRGs from our laboratory, and sources such as the Ferroptosis Database (FerrDb) and the Gene Expression Omnibus Database (GEO). 57 differentially expressed FRGs (DE-FRGs) were discovered. The LASSO and SVM-RFE algorithms were employed to identify Enpp2, Pla2g6, Etv4, and Il1b as marker genes, and logistic regression was applied to construct a diagnostic model. The important genes were validated by real time PCR and the external dataset. Finally, the extent of immune infiltration was explored.
Results:
Among the 57 genes, there were 36 up-regulated and 21 down-regulated genes that exhibited distinct expression patterns in the TTS and healthy control samples. Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis indicated that the enriched pathways were primarily associated with pathways of neurodegeneration-multiple disease, while Gene Ontology (GO) analysis revealed that these genes were primarily linked to cellular response to external stimuli, outer membrane functions, and ubiquitin protein ligase binding. After the identification of four marker genes as potentially effective biomarkers for TTS diagnosis, subsequent logistic regression modeling revealed a receiver operating characteristic curve (ROC) with an AUC of 1.0. The examination of immune cell infiltration showed significantly higher prevalence of activated CD4+ T cells, mast cells, etc., in TTS.
Conclusion:
Our findings support the theoretical importance of ferroptosis in TTS, highlighting Enpp2, Pla2g6, Etv4, and Il1b as potential diagnostic and therapeutic biomarkers for TTS.
