Open Access

Machine learning identifies potential diagnostic biomarkers associated with ferroptosis in obstructive sleep apnea

  • Authors:
    • Bowen Chen
    • Liping Dong
    • Weiwei Chi
    • Dongmei Song
  • View Affiliations

  • Published online on: March 13, 2025     https://doi.org/10.3892/etm.2025.12845
  • Article Number: 95
  • Copyright: © Chen et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )
Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )


Abstract

Obstructive sleep apnea (OSA) is the most common sleep apnea‑related disorder, with a high prevalence and a range of associated complications. Ferroptosis is a new mode of cell death that is involved in the development of OSA, but the mechanism has remained elusive. In the present study, ferroptosis‑related genes in OSA were assessed and their potential clinical value was discussed. Data were downloaded and merged, and screened for differentially expressed genes (DEGs) through the Gene Expression Omnibus database. The OSA ferroptosis‑related genes were obtained after intersecting with the downloaded ferroptosis‑related genes. Subsequently, key ferroptosis‑associated differential genes were obtained using two machine learning methods (the least absolute shrinkage and selection operators and random forest). The immune infiltration in the samples and the correlation between key differential genes and immune infiltrating cells were then analyzed. A competing endogenous (ce)RNA visualization network was constructed to find possible therapeutic targets. Finally, the expression levels of key DEGs were verified by reverse transcription‑quantitative (RT‑q)PCR. In this study, 3 key ferroptosis‑related differential genes were identified: TXN, EGR1 and CDKN1A. Functional enrichment analysis showed that the three key differential genes in OSA can influence the development of OSA by affecting metabolism, immune response and other processes. RT‑qPCR experiments verified the expression of these key genes, further confirming the findings. A persistent state of immune activation may promote the progression of OSA, with marked infiltration of T cells and natural killer cells in OSA tissues. Genipin is a possible targeted therapeutic agent for OSA. Meanwhile, ceRNA network analysis identified several long non‑coding RNAs that can regulate OSA disease progression. A total of 3 key ferroptosis‑related markers were identified (TXN, EGR1 and CDKN1A) that are closely associated with metabolic disorders and immune responses, and which may be targets for early diagnosis and treatment of OSA.
View Figures
View References

Related Articles

Journal Cover

May-2025
Volume 29 Issue 5

Print ISSN: 1792-0981
Online ISSN:1792-1015

Sign up for eToc alerts

Recommend to Library

Copy and paste a formatted citation
x
Spandidos Publications style
Chen B, Dong L, Chi W and Song D: Machine learning identifies potential diagnostic biomarkers associated with ferroptosis in obstructive sleep apnea. Exp Ther Med 29: 95, 2025.
APA
Chen, B., Dong, L., Chi, W., & Song, D. (2025). Machine learning identifies potential diagnostic biomarkers associated with ferroptosis in obstructive sleep apnea. Experimental and Therapeutic Medicine, 29, 95. https://doi.org/10.3892/etm.2025.12845
MLA
Chen, B., Dong, L., Chi, W., Song, D."Machine learning identifies potential diagnostic biomarkers associated with ferroptosis in obstructive sleep apnea". Experimental and Therapeutic Medicine 29.5 (2025): 95.
Chicago
Chen, B., Dong, L., Chi, W., Song, D."Machine learning identifies potential diagnostic biomarkers associated with ferroptosis in obstructive sleep apnea". Experimental and Therapeutic Medicine 29, no. 5 (2025): 95. https://doi.org/10.3892/etm.2025.12845