Clinical data-based modeling of IVF live birth outcome and its application

Abstract

Background: The low live birth rate and difficult decision-making of the in vitro fertilization (IVF) treatment regimen bring great trouble to patients and clinicians. Based on the retrospective clinical data of patients undergoing the IVF cycle, this study aims to establish classification models for predicting live birth outcome (LBO) with machine learning methods.

Methods: The historical data of a total of 1405 patients undergoing IVF cycle were first collected and then analyzed by univariate and multivariate analysis. The statistically significant factors were identified and taken as input to build the artificial neural network (ANN) model and supporting vector machine (SVM) model for predicting the LBO. By comparing the model performance, the one with better results was selected as the final prediction model and applied in real clinical applications.

Results: Univariate and multivariate analysis shows that 7 factors were closely related to the LBO (with P < 0.05): Age, ovarian sensitivity index (OSI), controlled ovarian stimulation (COS) treatment regimen, Gn starting dose, endometrial thickness on human chorionic gonadotrophin (HCG) day, Progesterone (P) value on HCG day, and embryo transfer strategy. By taking the 7 factors as input, the ANN-based and SVM-based LBO models were established, yielding good prediction performance. Compared with the ANN model, the SVM model performs much better and was selected as the final model for the LBO prediction. In real clinical applications, the proposed ANN-based LBO model can predict the LBO with good performance and recommend the embryo transfer strategy of potential good LBO.

Conclusions: The proposed model involving all essential IVF treatment factors can accurately predict LBO. It can provide objective and scientific assistance to clinicians for customizing the IVF treatment strategy like the embryo transfer strategy.

Keywords: Embryo transfer strategy, clinical decision support; IVF; Live birth outcome; Machine learning.

Fig. 1

Overview of the proposed research. (1)~(2) Collect data of patients and find the factors related to the LBO; (3) Conduct univariate analysis to determine the significant influencing factors of LBO initially; (4) Conduct multivariate analysis to determine the influencing factors of LBO further; (5) Based on machine learning method, the ANN-based LBO model and SVM-based LBO model are built; (6) The prediction performance of the two models are compared, and the one, i.e., the SVM-based LBO model, that has better modeling performance is selected. (7) 81 new patients were involved in the clinical application of the proposed model to verify the prediction performance and the function of recommendation of the embryo transfer strategy

Fig. 2

Prototype software - Decision Support System of IVF – Embryo transfer strategy determination. For each patient, the user manually inputs the values of 7 influencing factors on the left side of the software and clicks the “Predict the LBO” button on the right to call the SVM-based LBO model embedded in the software. The predicted result will show in the dialog box of “LBO”. By clicking the “Recommend embryo transfer strategy” button, the strategy that has good LBO will be recommended in the dialog box. The information displayed on the software interface in Fig. 3 is the clinical information of Patient # 48 and its corresponding predicted LBO, for which the predicted LBO is “Non-live birth” and the recommended strategy is “2 embryos at cleavage stage”

Fig. 3

ROC curves of ANN-based LBO model. (A) the training set; (B) the validation set; (C) the test set

Fig. 4

ROC curves of SVM-based LBO model. (A) the training set; (B) the test set

Fig. 5

ROC of the proposed model on the clinical application sample

Fig. 6

(A) Calibration plot of the proposed model; (B) DCA curve of the proposed model

Fig. 7

Comparison between model-based recommended strategy and clinician-based strategy (In the figure, the horizontal axis represents the patient ID., and the vertical axis represents the embryo transfer strategy)