Predictive Factors for Recovery Time in Conceived Women Suffering From Moderate to Severe Ovarian Hyperstimulation Syndrome

Huang, Kai; Shi, Ying; Chen, Gezi; Shi, Hao; Zhai, Jing

doi:10.3389/fendo.2022.870008

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a multidisciplinary treatment strategy is an effective approach for PCOS. Many mRNA targets for PCOS have been revealed, such as ALB [6] , LPA [7] , and TNF [8] ; however, the detailed molecular mechanisms underlying PCOS remain unclear.…”

Section: Introductionmentioning

confidence: 99%

Identifying miRNA biomarkers of polycystic ovary syndrome through text mining

Wang¹,

Yuan²,

Zhao

2022

Reproductive and Developmental Medicine

View full text Add to dashboard Cite

Objective: Polycystic ovary syndrome (PCOS) is an endocrine disorder with diverse clinical manifestations that often occurs in women of childbearing age. However, its molecular pathogenesis remains unclear, and this study aimed to identify miRNA targets in PCOS through text mining and database analysis. Methods: First, three different sets of text mining genes (TMGs) associated with “polycystic ovary syndrome”, “obesity/adiposis”, and “anovulation” keywords were retrieved from the GenCLiP3 database, and overlapping genes were selected. Second, Gene ontology annotation and biological pathway enrichment analyses of these overlapping TMGs were performed, followed by protein–protein interaction (PPI) network analysis. Third, genes in the gene module clustered in the PPI were selected to predict potential miRNAs for PCOS via miRNA-mRNA analysis. Results: A total of 4291 TMGs related to three different keywords were obtained through text mining; 72 intersect TMGs were retained among the three gene sets, and 62 TMGs participated in the establishment of the PPI network, of which 18 were aggregated in the gene module. Finally, 11 miRNAs that simultaneously bound to two TMGs (IGF1, ESR1, MAPK1, NAMPT, PIK3CA, and SERPINE1) could be prioritized as targets to study PCOS. Conclusion(s): The discovery of 11 miRNAs (miR-301a-3p, miR-301b-3p, miR-3666, miR-454-3p, miR-130a-3p, miR-130b-3p, miR-4295, miR-190a-3p, miR-5011-5p, miR-548c-3p, and miR-4799-5p) and 6 TMGs, which are associated with the HIF-1 signaling pathway (P = 4.799E-08), could be used as potential targets for PCOS.

show abstract

Section: Introductionmentioning

confidence: 99%

Identifying miRNA biomarkers of polycystic ovary syndrome through text mining

Wang¹,

Yuan²,

Zhao

2022

Reproductive and Developmental Medicine

View full text Add to dashboard Cite

show abstract

A stacked machine learning-based classification model for endometriosis and adenomyosis: a retrospective cohort study utilizing peripheral blood and coagulation markers

Wang,

Zeng,

Yang

2024

Front. Digit. Health

View full text Add to dashboard Cite

IntroductionEndometriosis (EMs) and adenomyosis (AD) are common gynecological diseases that impact women's health, and they share symptoms such as dysmenorrhea, chronic pain, and infertility, which adversely affect women's quality of life. Current diagnostic approaches for EMs and AD involve invasive surgical procedures, and thus, methods of noninvasive differentiation between EMs and AD are needed. This retrospective cohort study introduces a novel, noninvasive classification methodology employing a stacked ensemble machine learning (ML) model that utilizes peripheral blood and coagulation markers to distinguish between EMs and AD.MethodsThe study included a total of 558 patients (329 with EMs and 229 with AD), in whom key hematological and coagulation markers were analyzed to identify distinctive profiles. Feature selection was conducted through ML (logistic regression, support vector machine, and K-nearest neighbors) to determine significant hematological markers.ResultsRed cell distribution width, mean corpuscular hemoglobin concentration, activated partial thromboplastin time, international normalized ratio, and antithrombin III were proved to be the key distinguishing indexes for disease differentiation. Among all the ML classification models developed, the stacked ensemble model demonstrated superior performance (area under the curve = 0.803, 95% credibility interval = 0.701–0.904). Our findings demonstrate the effectiveness of the stacked ensemble ML model for classifying EMs and AD.DiscussionIntegrating biomarkers into this multi-algorithm framework offers a novel approach to noninvasive diagnosis. These results advocate for the application of stacked ensemble ML utilizing cost-effective and readily available peripheral blood and coagulation indicators for the early, rapid, and noninvasive differential diagnosis of EMs and AD, offering a potentially transformative approach for clinical decision-making and personalized treatment strategies.

show abstract

Predictive Factors for Recovery Time in Conceived Women Suffering From Moderate to Severe Ovarian Hyperstimulation Syndrome

Cited by 2 publications

References 34 publications

Identifying miRNA biomarkers of polycystic ovary syndrome through text mining

Identifying miRNA biomarkers of polycystic ovary syndrome through text mining

A stacked machine learning-based classification model for endometriosis and adenomyosis: a retrospective cohort study utilizing peripheral blood and coagulation markers

Contact Info

Product

Resources

About