Establishment of a corneal ulcer prognostic model based on machine learning

E2F expression profiling-based subtypes in head and neck squamous cell carcinoma: clinical relevance, prognostic implications, and personalized therapy

BACKGROUND

Head and neck squamous cell carcinoma (HNSCC) is a heterogeneous malignancy with poor prognosis. Dysregulation of E2F transcription factors (E2Fs), which control cell proliferation and apoptosis, is implicated in HNSCC pathogenesis. This study explores HNSCC molecular heterogeneity via E2Fs expression, identifies distinct subtypes, and develops a prognostic model that integrates gene expression, immune infiltration, and drug sensitivity.

METHODS

We analyzed the TCGA-HNSC dataset (n = 494) and classified samples based on the expression of eight E2Fs using ConsensusClusterPlus. The optimal number of clusters (k = 2) was determined with the getOptK() function, which assesses cluster stability via internal consistency metrics. Differentially expressed genes between subtypes were identified with limma, and functional annotation was performed using Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses. A prognostic model was constructed using LASSO regression on genes significant in univariate Cox analysis and validated in an independent GSE41613 dataset (n = 97). Immune cell infiltration was estimated using CIBERSORT, and drug sensitivity predicted via pRRophetic. Confounding factors such as HPV and smoking status were not included due to incomplete data.

RESULTS

Two distinct E2F-based subtypes emerged. Cluster 1, characterized by lower E2Fs expression, exhibited poorer overall survival (log-rank, p = 0.035) and was enriched in genes related to epidermal development, keratinocyte differentiation, and IL-17 signaling. In contrast, Cluster 2 showed higher E2Fs expression, better survival, and enrichment in genes associated with DNA replication and repair. Notably, high-risk patients demonstrated increased infiltration of M0 and M2 macrophages (p < 0.05), suggesting an immunosuppressive tumor microenvironment that adversely affects prognosis. Our seven-gene prognostic model (AREG, CXCL14, FAM83E, FDCSP, ARHGAP4, EPHX3, and SPINK6) exhibited robust performance with AUCs of 0.692, 0.673, and 0.679 for 1-, 3-, and 5-year survival, a C-index of 0.66, and good calibration. High-risk patients also showed greater sensitivity to targeted agents such as pazopanib and imatinib.

CONCLUSIONS

These findings reveal two distinct E2F-based molecular subtypes of HNSCC that differ in prognosis, functional pathways, immune infiltration, and drug sensitivity. The prognostic model offers valuable risk stratification and identifies potential biomarkers and therapeutic targets, warranting further experimental and clinical validation.

Artificial intelligence in ophthalmology

PURPOSE OF REVIEW

To review role of artificial intelligence in medicine.

RECENT FINDINGS

Artificial intelligence is continuing to revolutionize access, diagnosis, personalization of medicine, and treatment in healthcare. As a matter of fact, artificial intelligence contributed to the research that resulted in 2024 Nobel Prizes in physics, chemistry, and economics. We are only at the tip of the iceberg in utilizing the abilities of artificial intelligence in medicine to improve accuracy of diagnoses and to enhance patient outcomes. Artificial intelligence has allowed better image analysis, prediction of progression of disease, personalized treatment plans, incorporations of genomics, and improved efficiency in care and follow-up utilizing home monitoring. In ocular health diagnosis and treatment of diabetic retinopathy, macular degeneration, glaucoma, corneal infections, and ectasia are only a few examples of how the power of artificial intelligence has been harnessed. Even though there are still challenges that need more work in the areas of patient privacy, Health Insurance Portability and Accountability Act (HIPAA) compliance, reliability, and development of regulatory frameworks, artificial intelligence has revolutionized and will continue to revolutionize medicine.

SUMMARY

Artificial intelligence is enhancing medical diagnosis and treatment, as well as access and prevention. Ocular imaging, visual outcome, optics, intraocular pressure, and data points will continue to see growth it the field of artificial intelligence.