Construction and verification analysis of risk prediction model for re-pregnancy failure in patients with unexplained recurrent spontaneous abortion based on LASSO regression analysis
10.3969/j.issn.1671-8348.2024.24.011
- VernacularTitle:基于LASSO回归分析构建不明原因复发性流产患者再次妊娠失败的风险预测模型与验证分析
- Author:
Wei ZHANG
1
;
Xuejuan JIANG
;
Yi ZHU
;
Pian YING
Author Information
1. 杭州市红十字会医院生殖医学科,杭州 310003
- Keywords:
unexplained recurrent spontaneous abortion;
re-pregnancy failure;
minimum absolute shrinkage and selection operator regression;
prediction model;
risk factor
- From:
Chongqing Medicine
2024;53(24):3744-3751
- CountryChina
- Language:Chinese
-
Abstract:
Objective To construct the related factors of re-pregnant failure in the patients with unex-plained recurrent spontaneous abortion(URSA)based on the least absolute shrinkage and selection operator(LASSO)regression analysis,and to construct the prediction model and conduct the verification.Methods The prospective study was adopted to select 420 URSA patients admitted and treated in Hangzhou Municipal Red Cross Hospital from February 2021 to February 2024 as the research subjects.They were divid-ed into modeling group and verification group by simple random sampling method with a ratio of 7∶3.All URSA patients were followed up until termination of pregnancy.They were divided into the pregnancy success group and pregnancy failure group based on the pregnancy outcome.The baseline data of the patients conduc-ted the statistics.LASSO regression was used to screen the risk factors that might affect the re-pregnancy fail-ure of URSA patients for conducting the binary logistic regression analysis,and the nomogram model was con-structed according to the relevant factors and a nomogram model was constructed according to the regression results.The Bootstrap internal verification method was used to verify the nomogram model,and the verifica-tion group data were used to conduct the external verification on the nomogram model.Results The optimal penalty term coefficient λ was determined by the three-fold cross-validation of the LASSO regression model.Nine potential related factors were screened at λ±s(x),which were the age,number of abortions,autoimmune factors,impaired fasting glucose,DFI,number of high-quality embryos,human chorionic gonadotropin(HCG),progesterone(P)and estradiol(E2).The results of binary logistic regression analysis showed that elder,more abortions,abnormal autoimmune factors,impaired fasting glucose and high DFI were the risk fac-tors for re-pregnancy failure in URSA patients(OR=1.286,4.574,3.114,3.204,1.234,P＜0.05).The large number of high-quality embryos and high expression of serum HCG,P and E2 were the protective factors for the re-pregnancy failure in URSA patients(OR=0.547,0.826,0.948,0.995,P＜0.05).The Bootstrap inter-nal validation method was used to verify the nomogram model of the modeling group and validation group.The consistency index(C-index)values were 0.959 and 0.968,respectively.The calibration curves of the two groups were well fitted with the ideal curve.The results of drawing the receiver operating characteristic(ROC)curve showed that the area under the curve(AUC)of the modeling group was 0.959(95％CI:0.937-0.981,P＜0.001),the sensitivity was 86.6％,the specificity was 95.7％and the Youden index was 0.823.AUC of the validation group was 0.968(95％CI:0.949-0.988,P＜0.001),the sensitivity was 88.5％,the specificity was 97.4％and the Youden index was 0.859.Conclusion The age,number of abor-tions,autoimmune factors,impaired fasting glucose,DFI,number of high-quality embryos,HCG,P and E2 are closely correlated to the failure of re-pregnancy in URSA patients.At the same time,the constructed nomo-gram model based on the above factors has a good predictive efficiency on the pregnant failure of the patients.
