{"title":"Development of a machine learning-based prediction model for clinical pregnancy of intrauterine insemination in a large Chinese population.","authors":"Jialin Wu, Tingting Li, Linan Xu, Lina Chen, Xiaoyan Liang, Aihua Lin, Wangjian Zhang, Rui Huang","doi":"10.1007/s10815-024-03153-2","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>This study aimed to evaluate the effectiveness of a random forest (RF) model in predicting clinical pregnancy outcomes from intrauterine insemination (IUI) and identifying significant factors affecting IUI pregnancy in a large Chinese population.</p><p><strong>Methods: </strong>RESULTS: A total of 11 variables, including eight from female (age, body mass index, duration of infertility, prior miscarriage, and spontaneous abortion), hormone levels (anti-Müllerian hormone, follicle-stimulating hormone, luteinizing hormone), and three from male (smoking, semen volume, and sperm concentration), were identified as the significant variables associated with IUI clinical pregnancy in our Chinese dataset. The RF-based prediction model presents an area under the receiver operating characteristic curve (AUC) of 0.716 (95% confidence interval, 0.6914-0.7406), an accuracy rate of 0.6081, a sensitivity rate of 0.7113, and a specificity rate of 0.505. Importance analysis indicated that semen volume was the most vital variable in predicting IUI clinical pregnancy.</p><p><strong>Conclusions: </strong>The machine learning-based IUI clinical pregnancy prediction model showed a promising predictive efficacy that could provide a potent tool to guide selecting targeted infertile couples beneficial from IUI treatment, and also identify which parameters are most relevant in IUI clinical pregnancy.</p>","PeriodicalId":15246,"journal":{"name":"Journal of Assisted Reproduction and Genetics","volume":null,"pages":null},"PeriodicalIF":3.2000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11339014/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Assisted Reproduction and Genetics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10815-024-03153-2","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/5/31 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"GENETICS & HEREDITY","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose: This study aimed to evaluate the effectiveness of a random forest (RF) model in predicting clinical pregnancy outcomes from intrauterine insemination (IUI) and identifying significant factors affecting IUI pregnancy in a large Chinese population.
Methods: RESULTS: A total of 11 variables, including eight from female (age, body mass index, duration of infertility, prior miscarriage, and spontaneous abortion), hormone levels (anti-Müllerian hormone, follicle-stimulating hormone, luteinizing hormone), and three from male (smoking, semen volume, and sperm concentration), were identified as the significant variables associated with IUI clinical pregnancy in our Chinese dataset. The RF-based prediction model presents an area under the receiver operating characteristic curve (AUC) of 0.716 (95% confidence interval, 0.6914-0.7406), an accuracy rate of 0.6081, a sensitivity rate of 0.7113, and a specificity rate of 0.505. Importance analysis indicated that semen volume was the most vital variable in predicting IUI clinical pregnancy.
Conclusions: The machine learning-based IUI clinical pregnancy prediction model showed a promising predictive efficacy that could provide a potent tool to guide selecting targeted infertile couples beneficial from IUI treatment, and also identify which parameters are most relevant in IUI clinical pregnancy.
期刊介绍:
The Journal of Assisted Reproduction and Genetics publishes cellular, molecular, genetic, and epigenetic discoveries advancing our understanding of the biology and underlying mechanisms from gametogenesis to offspring health. Special emphasis is placed on the practice and evolution of assisted reproduction technologies (ARTs) with reference to the diagnosis and management of diseases affecting fertility. Our goal is to educate our readership in the translation of basic and clinical discoveries made from human or relevant animal models to the safe and efficacious practice of human ARTs. The scientific rigor and ethical standards embraced by the JARG editorial team ensures a broad international base of expertise guiding the marriage of contemporary clinical research paradigms with basic science discovery. JARG publishes original papers, minireviews, case reports, and opinion pieces often combined into special topic issues that will educate clinicians and scientists with interests in the mechanisms of human development that bear on the treatment of infertility and emerging innovations in human ARTs. The guiding principles of male and female reproductive health impacting pre- and post-conceptional viability and developmental potential are emphasized within the purview of human reproductive health in current and future generations of our species.
The journal is published in cooperation with the American Society for Reproductive Medicine, an organization of more than 8,000 physicians, researchers, nurses, technicians and other professionals dedicated to advancing knowledge and expertise in reproductive biology.