Identification of prognostic subtypes and the role of FXYD6 in ovarian cancer through multi-omics clustering

Frontiers in Immunology, Journal Year: 2025, Volume and Issue: 16

Published: March 18, 2025

Ovarian cancer (OC), as a malignant tumor that seriously endangers the lives and health of women, is renowned for its complex heterogeneity. Multi-omics analysis, an effective method distinguishing heterogeneity, can more accurately differentiate prognostic subtypes with differences among patients OC. The aim this study to explore OC analyze molecular characteristics different subtypes. We utilized 10 clustering algorithms multi-omics data from Cancer Genome Atlas (TCGA). After that, we integrated them ten machine-learning methods in order determine high-resolution subgroups generate machine-learning-driven are both resilient consensus-based. Following application clustering, were able identify two (CSs) associated prognosis. Among these, CS2 demonstrated most positive predictive outcome. Subsequently, five genes constitute machine learning (ML)-driven features screened out by ML algorithms, these possess powerful ability function FXYD Domain-Containing Ion Transport Regulator 6 (FXYD6) was analyzed through gene knockdown overexpression, mechanism which it affects functions explored. Through ascertained high-risk score group exhibits poorer prognosis lack response immunotherapy. Moreover, prone display "cold tumor" phenotype, lower likelihood benefiting FXYD6, being crucial differential molecule between subtypes, exerts tumor-promoting effect when knocked down; conversely, overexpression yields opposite Additionally, discovered FXYD6 induce ferroptosis cells, implying low level cells safeguard ferroptosis. Insightful precise categorization be achieved thorough examination data. There significant consequences clinical practice stemming discovery risk scores since they provide useful tool early prediction well screening candidates

Language: Английский

---

AI-Derived Blood Biomarkers for Ovarian Cancer Diagnosis: Systematic Review and Meta-Analysis

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e67922 - e67922

Published: March 24, 2025

Background Emerging evidence underscores the potential application of artificial intelligence (AI) in discovering noninvasive blood biomarkers. However, diagnostic value AI-derived biomarkers for ovarian cancer (OC) remains inconsistent. Objective We aimed to evaluate research quality and validity AI-based OC diagnosis. Methods A systematic search was performed MEDLINE, Embase, IEEE Xplore, PubMed, Web Science, Cochrane Library databases. Studies examining accuracy AI were identified. The risk bias assessed using Quality Assessment Diagnostic Accuracy Studies–AI tool. Pooled sensitivity, specificity, area under curve (AUC) estimated a bivariate model meta-analysis. Results total 40 studies ultimately included. Most (n=31, 78%) included evaluated as low bias. Overall, pooled AUC 85% (95% CI 83%-87%), 91% 90%-92%), 0.95 0.92-0.96), respectively. For contingency tables with highest accuracy, 95% 90%-97%), 97% 95%-98%), 0.99 0.98-1.00), Stratification by algorithms revealed higher sensitivity specificity machine learning (sensitivity=85% specificity=92%) compared those deep (sensitivity=77% specificity=85%). In addition, serum reported substantially (94%) (96%) than plasma (sensitivity=83% specificity=91%). external validation demonstrated significantly (specificity=94%) without (specificity=89%), while reverse observed (74% vs 90%). No publication detected this Conclusions demonstrate satisfactory performance diagnosis are anticipated become an effective modality future, potentially avoiding unnecessary surgeries. Future is warranted incorporate into models, well prioritize adoption methodologies. Trial Registration PROSPERO CRD42023481232; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023481232

Language: Английский

---

Patch-Based Texture Feature Extraction Towards Improved Clinical Task Performance

Bioengineering, Journal Year: 2025, Volume and Issue: 12(4), P. 404 - 404

Published: April 10, 2025

Texture features can capture microstructural patterns and tissue heterogeneity, playing a pivotal role in medical image analysis. Compared to deep learning-based features, texture offer superior interpretability clinical applications. However, as conventional focus strictly on voxel-level statistical information, they fail account for critical spatial heterogeneity between small volumes, which may hold significant importance. To overcome this limitation, we propose novel 3D patch-based develop radiomics analysis framework validate the efficacy of our proposed features. Specifically, multi-scale patches were created construct patch via k-means clustering. The multi-resolution images discretized based labels patterns, then extracted quantify patches. Twenty-five cross-combination models five feature selection methods classifiers constructed. Our methodology was evaluated using two independent MRI datasets. 145 breast cancer patients included axillary lymph node metastasis prediction, 63 cervical enrolled histological subtype prediction. Experimental results demonstrated that achieved an AUC 0.76 prediction task 0.94 outperforming (0.74 0.83, respectively). have successfully captured patch-level representations, could enhance application imaging biomarkers precise cancers personalized therapeutic interventions.

Language: Английский

---

Artificial Intelligence in Ovarian Cancer: A Systematic Review and Meta-Analysis of Predictive AI Models in Genomics, Radiomics, and Immunotherapy

AI, Journal Year: 2025, Volume and Issue: 6(4), P. 84 - 84

Published: April 18, 2025

Background/Objectives: Artificial intelligence (AI) is increasingly influencing oncological research by enabling precision medicine in ovarian cancer through enhanced prediction of therapy response and patient stratification. This systematic review meta-analysis was conducted to assess the performance AI-driven models across three key domains: genomics molecular profiling, radiomics-based imaging analysis, immunotherapy response. Methods: Relevant studies were identified a search multiple databases (2020–2025), adhering PRISMA guidelines. Results: Thirteen met inclusion criteria, involving over 10,000 patients encompassing diverse AI such as machine learning classifiers deep architectures. Pooled AUCs indicated strong predictive for genomics-based (0.78), (0.88), immunotherapy-based (0.77) models. Notably, radiogenomics-based integrating data yielded highest accuracy (AUC = 0.975), highlighting potential multi-modal approaches. Heterogeneity risk bias assessed, evidence certainty graded. Conclusions: Overall, demonstrated promise predicting therapeutic outcomes cancer, with radiomics integrated radiogenomics emerging leading strategies. Future efforts should prioritize explainability, prospective multi-center validation, integration immune spatial transcriptomic support clinical implementation individualized treatment Unlike earlier reviews, this study synthesizes broader range applications provides pooled metrics It examines methodological soundness selected highlights current gaps opportunities translation, offering comprehensive forward-looking perspective field.

Language: Английский

---