Di Wu

A Machine Learning Approach to Build and Evaluate a Molecular Prognostic Model for Endometrial Cancer Based on Tumour Microenvironment

ABSTRACTEndometrial cancer (EC) incidence and the associated tumour burden have increased globally. To build a molecular expression prognostic model based on the tumour microenvironment to guide personalised treatment using a machine learning approach. Two datasets were reviewed, including a training cohort (n = 698) and a testing cohort (n = 151). All patients underwent hysterectomy ± adnexectomy ± lymph nodes dissection between December 2014 and June 2020 at the PLA General Hospital First Medical Center and received necessary and regular follow‐up. We developed novel models using R software to predict factors that affect survival, such as progression‐free survival and overall survival. Then, the model was optimised by evaluating the prediction efficiency in multiple dimensions. Eight hundred and forty‐nine patients with EC were included in the study. Survival‐related influences on EC patients were identified by univariate analysis and cox regression equations. In addition, a nomogram was visualised in conjunction with demographic characteristics and the above meaningful clinicopathological variables. Ultimately, through a comprehensive assessment, a random forest model (RF16) was developed for complementing the findings of the molecular classification of EC. The RF16 not only specifically characterises tumour molecules, but also enhances the generalizability of the model by replacing gene sequencing with immunohistochemistry. This study showed that the machine learning model (RF16) is low‐cost, efficient, and clinically valuable in guiding treatment for EC patients.

Plastic-related endocrine disrupting chemicals significantly related to the increased risk of estrogen-dependent diseases in women

To evaluate the association between exposure to plastic-related endocrine-disrupting chemicals (EDCs), specifically Bisphenol A (BPA), Phthalates, Cadmium, and Lead, and the risk of estrogen-dependent diseases (EDDs) such as polycystic ovary syndrome (PCOS), endometriosis, or endometrial cancer by conducting a meta-analysis of relevant studies. PubMed, Web of Science, and Cochrane Library databases were used for literature retrieval of articles published until the 21st of April 2023. Literature that evaluated the association between BPA, phthalates, cadmium, and/or lead exposure and the risk of PCOS, endometriosis, or endometrial cancer development or exacerbation were included in our analysis. STATA/MP 17.0 was used for all statistical analyses. Overall, 22 articles were included in our meta-analysis with a total of 83,641 subjects all of whom were females aged between 18 and 83 years old. The overall effect size of each study was as follows: endometriosis risk in relation to BPA exposure ES 1.82 (95% CI; 1.50, 2.20). BPA and PCOS risk ES 1.61 (95% CI; 1.39, 1.85). Phthalate metabolites and endometriosis risk; MBP ES 1.07 (95% CI; 0.86, 1.33), MEP ES 1.05 (95% CI; 0.87, 1.28), MEHP ES 1.15 (95% CI; 0.67, 1.98), MBzP ES 0.97 (95% CI; 0.63, 1.49), MEOHP ES 1.87 (95% CI; 1.21, 2.87), and MEHHP ES 1.98 (95% CI; 1.32, 2.98). Cadmium exposure and endometrial cancer risk ES 1.14 (95% CI; 0.92, 1.41). Cadmium exposure and the risk of endometriosis ES 2.54 (95% CI; 1.71, 3.77). Lead exposure and the risk of endometriosis ES 1.74 (95% CI; 1.13, 2.69). Increased serum, urinary, or dietary concentration of MBzP and MEHP in women is significantly associated with endometriosis risk. Increased cadmium concentration is associated with endometrial cancer risk.