{"title":"Prediction of clinical pregnancy outcome after single fresh blastocyst transfer during in vitro fertilization: an ensemble learning perspective.","authors":"Zhiqiang Liu, Hongzhan Zhang, Feng Xiong, Xin Huang, Shuyi Yu, Qing Sun, Lianghui Diao, Zhenjuan Li, Yulian Wu, Yong Zeng, Chunyu Huang","doi":"10.1080/14647273.2024.2422918","DOIUrl":null,"url":null,"abstract":"<p><p>To establish a predictive model for clinical pregnancy outcomes following the transfer of a single fresh blastocyst in vitro fertilization (IVF). 615 patients (492 in training set and 123 in test set) who underwent the first single and fresh blastocyst transfer in the first IVF or intracytoplasmic sperm injection cycle performed in fertility centre of Shenzhen Zhongshan Obstetrics & Gynecology Hospital from July 2015 to June 2021 were enrolled in this study. Conventional method such as logistic regression (LR), individual machine learning methods including naive bayesian (NB), K-nearest neighbours (K-NN), support vector machine (SVM), decision tree (DT), and ensemble learning methods including random forest (RF), XGBoost, LightGBM, Voting were used to establish the clinical pregnancy outcome prediction model, and the efficacy among different models was compared. Three major types of prediction models, including conventional method: LR (AUC = 0.707), individual machine learning classifiers: NB (AUC = 0.741), K-NN (AUC = 0.719), SVM (AUC = 0.761), DT (AUC = 0.728), ensemble models: RF (AUC = 0.790), XGBoost (AUC = 0.799), LightGBM (AUC = 0.794), Voting (AUC = 0.845) were established. It was found that the performance of the voting model was best. This study revealed that a voting classifier can provide a more accurate estimate of IVF outcome, which can assist clinicians to make individual patient counselling.</p>","PeriodicalId":13006,"journal":{"name":"Human Fertility","volume":"27 1","pages":"2422918"},"PeriodicalIF":2.1000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human Fertility","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/14647273.2024.2422918","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/11/11 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"OBSTETRICS & GYNECOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
To establish a predictive model for clinical pregnancy outcomes following the transfer of a single fresh blastocyst in vitro fertilization (IVF). 615 patients (492 in training set and 123 in test set) who underwent the first single and fresh blastocyst transfer in the first IVF or intracytoplasmic sperm injection cycle performed in fertility centre of Shenzhen Zhongshan Obstetrics & Gynecology Hospital from July 2015 to June 2021 were enrolled in this study. Conventional method such as logistic regression (LR), individual machine learning methods including naive bayesian (NB), K-nearest neighbours (K-NN), support vector machine (SVM), decision tree (DT), and ensemble learning methods including random forest (RF), XGBoost, LightGBM, Voting were used to establish the clinical pregnancy outcome prediction model, and the efficacy among different models was compared. Three major types of prediction models, including conventional method: LR (AUC = 0.707), individual machine learning classifiers: NB (AUC = 0.741), K-NN (AUC = 0.719), SVM (AUC = 0.761), DT (AUC = 0.728), ensemble models: RF (AUC = 0.790), XGBoost (AUC = 0.799), LightGBM (AUC = 0.794), Voting (AUC = 0.845) were established. It was found that the performance of the voting model was best. This study revealed that a voting classifier can provide a more accurate estimate of IVF outcome, which can assist clinicians to make individual patient counselling.
期刊介绍:
Human Fertility is a leading international, multidisciplinary journal dedicated to furthering research and promoting good practice in the areas of human fertility and infertility. Topics included span the range from molecular medicine to healthcare delivery, and contributions are welcomed from professionals and academics from the spectrum of disciplines concerned with human fertility. It is published on behalf of the British Fertility Society.
The journal also provides a forum for the publication of peer-reviewed articles arising out of the activities of the Association of Biomedical Andrologists, the Association of Clinical Embryologists, the Association of Irish Clinical Embryologists, the British Andrology Society, the British Infertility Counselling Association, the Irish Fertility Society and the Royal College of Nursing Fertility Nurses Group.
All submissions are welcome. Articles considered include original papers, reviews, policy statements, commentaries, debates, correspondence, and reports of sessions at meetings. The journal also publishes refereed abstracts from the meetings of the constituent organizations.