Individualized Embryo Selection Strategy Developed by Stacking Machine Learning Model for Better In Vitro Fertilization Outcomes: An Application Study.

Individualized Embryo Selection Strategy Developed by Stacking Machine Learning Model for Better In Vitro Fertilization Outcomes: An Application Study. | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Individualized Embryo Selection Strategy Developed by Stacking Machine Learning Model for Better In Vitro Fertilization Outcomes: An Application Study. Qingsong XI, Qiyu YANG, Meng WANG, Bo HUANG, Bo ZHANG, Zhou LI, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-140383/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 05 Apr, 2021 Read the published version in Reproductive Biology and Endocrinology → Version 1 posted 8 You are reading this latest preprint version Abstract Background: To minimize the rate of in vitro fertilization (IVF)- associated multiple-embryo gestation, significant efforts have been made. Previous studies related to machine learning in IVF mainly focused on selecting the top-quality embryos to improve outcomes, however, in patients with sub-optimal prognosis or with medium- or inferior-quality embryos, the selection between SET and DET could be perplexing. Methods: This was an application study including 7887 patients with 8585 embryos treated during 2016 to 2018, in Tongji Hospital, Wuhan, China. A hierarchical model was established using the machine learning system XGBoost, to learn embryo implantation potential and the impact of double embryos transfer (DET) simultaneously. The performance of the model was evaluated with the AUC of the ROC curve. Multiple regression analyses were also conducted on the 19 selected features to demonstrate the differences between feature importance for prediction and statistical relationship with outcomes. Results: For a single embryo transfer (SET) pregnancy, the following variables remained significant: age, attempts at IVF, estradiol level on hCG day, and endometrial thickness. For DET pregnancy, age, attempts at IVF, endometrial thickness, and the newly added P1+P2 remained significant. For DET twin risk, age, attempts at IVF, 2PN/ MII, and P1×P2 remained significant. The algorithm was repeated 30 times, and averaged AUC of 0.7945, 0.8385, and 0.7229 were achieved for SET pregnancy, DET pregnancy, and DET twin risk, respectively. The trend of predictive and observed rates both in pregnancy and twin risk was basically identical. XGBoost outperformed the other two algorithms: logistic regression and classification and regression tree. Conclusion : Artificial intelligence based on determinant-weighting analysis could offer an individualized embryo selection strategy for any given patient, and predict clinical pregnancy rate and twin risk, therefore optimizing clinical outcomes. Endocrinology & Metabolism Artificial intelligence embryo selection machine learning in vitro fertilization in vitro fertilization prediction Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Introduction For decades, discussions about how to improve the clinical outcomes of in vitro fertilization (IVF) treatment have persisted. Multiple-embryo transfer was suggested to increase the possibility of successful implantation but inevitably elevated the risk of multiple-embryo gestation. IVF-associated multiple pregnancies exhibit significant financial, social, and medical implications [ 1 , 2 ]. Even though the transfer of embryos has been limited to no more than two in recent years, the overall twin rate worldwide after assisted reproduction has still varied from 15–30% [ 3 ]. The incidences of premature birth, low birth weight, cerebral palsy, neurological complications, and perinatal mortality of twin pregnancy markedly increased compared with singleton pregnancy [ 4 ]. To minimize the rate of multiple-embryo gestation, significant efforts, including individualized service provision and single embryo transfer (SET) enhancement, have been made in the course of these decades. Embryo morphological analysis is the routine method for selecting the highest-quality embryos to transfer. It is commonly suggested to perform SET on prognostically good patients with a top-quality embryo and to perform double embryo transfer (DET) in prognostically poor patients because no good-quality embryos are available in the IVF lab. In a large proportion of IVF patients with sub-optimal prognosis or with medium- or inferior-quality embryos, the selection between SET and DET could be perplexing. Because many features have been shown to influence embryo implantation potential positively or negatively in IVF [ 5 – 8 ], developing an optimal embryo selection plan to balance maximum clinical pregnancy rate and minimum twin risk is complicated for IVF clinicians. Therefore, a more precise, quantified, stable embryo selection model based on all possible influencing determinants needs to be constructed. This will potentially offer evidence-based patient counseling and predictable successful chances for any given patient. Artificial intelligence (AI) represents the combination of machine learning, and a moderation and self-adapting prediction model. Previous studies related to machine learning in IVF mainly focused on selecting the top-quality embryos to improve IVF outcomes [ 9 – 13 ]. Developing a flexible, individualized embryo selection approach based on available embryos of various qualities and different twin rate threshold settings is another promising issue. The purpose of our study is to construct an individualized embryo selection strategy and pregnancy prediction model, developed by stacking machine learning, to identify features correlated with embryo implantation potential and to evaluate available embryos’ implantation chances quantitatively. We aim to balance maximal clinical pregnancy and minimal acceptable twin risk in IVF with this model and validate its clinical effectiveness and practicability in subsequent cycles.. Materials And Methods Study design and participants IVF patients in Tongji Hospital between January 2016 and December 2018, with one or two embryo transfers in the fresh cycle, were enrolled in our study. Exclusion criteria included patients with (1) blastocyst transfer in fresh cycle; (2) oocyte donation cycles; (3) vitrified/warmed oocytes; (4) oocytes partially cryopreserved in fresh cycle; (5) combined vitrified/warmed embryo transfers. In total, 4926 patients, between January 2016 and March 2018 were included as the training set to construct our model. Thirty-eight features were analyzed in our study, and their baselines on training and validation sets were exhibited, among which 21 main variables were selected and listed in Table 1 , including patient features, embryo morphology features, and embryo scores. After model construction, the developed embryo selection strategy was applied to guide the selection of SET or DET in 2961 individual cases between April and December 2018 as the validation set. Table 1 Baseline characteristics of the variables included in the training and validation data sets. Features Training set (n = 4926) Validation set (n = 2961) Patient composition SET 4489 2700 DET 437 261 Age*, y 30.46 ± 4.20 30.70 ± 3.94 Attempt times of IVF* 0.95 ± 0.43 0.78 ± 0.54 Antral follicle count* 13.64 ± 6.13 13.37 ± 6.36 Follicle stimulating hormone*, IU/L 7.59 ± 2.35 7.68 ± 2.79 Luteinizing hormone*, IU/L 4.71 ± 3.26 4.95 ± 6.08 E2 per mature oocyte, pmol/L 309.60 ± 141.26 265.68 ± 133.16 E2 on HCG day*, pmol/L 2810.88 ± 1424.43 2174.64 ± 1046.56 Endometrial Thickness*, mm 11.79 ± 2.40 11.98 ± 2.55 MetaphaseⅡ(M II)* 9.86 ± 4.14 9.25 ± 4.02 2pronucleus(PN)* 6.79 ± 3.35 6.31 ± 3.22 Oocyte Number a * 11.03 ± 4.45 10.64 ± 4.49 2PN/MⅡ* 0.70 ± 0.19 0.69 ± 0.20 Frozen Sperm 6.0% 6.3% Male Factor b Oligospermia 9.2% 10.3% Asthenospermia 12.8% 20.0% Azoospermia 7.1% 9.1% Female Factor b Endometriosis 3.0% 4.4% Ovulation Disorder 5.9% 7.8% Unknown 5.2% 12.3% Sperm Retrieval Ejaculation 95.2% 95.2% MESA 0.3% 0.7% TESA 1.0% 1.3% PESA 3.5% 2.8% Stimulation Protocol b Agonist Protocol* 71.4% 70.8% Antagonist Protocol 22.8% 28.5% Endometrial Type b A* 83.3% 85.0% B 2.0% 0.4% C* 21.4% 19.7% Infertility c Primary 64.9% 70.4% Secondary* 35.1% 29.6% Fertilization Method b IVF 72.5% 57.9% ICSI* 24.5% 34.8% Embryo Features Number of Blastomere* 7.93 ± 0.89 8.06 ± 0.93 Fragment d * 0.37 ± 0.50 0.32 ± 0.48 Equality e * 0.91 ± 0.95 0.87 ± 0.91 *The selected features after performing feature selection are marked by asterisks. SET, single-embryo transfer; DET, double-embryo transfer; IVF, in vitro fertilization; ICSI, intracytoplasmic sperm injection; E2: estradiol; hCG, human chorionic gonadotropin; MESA, microscopic epididymal sperm aspiration; TESA, testicular sperm aspiration; PESA, percutaneous epididymal sperm aspiration. (a) Number of oocytes retrieved; (b) for multi-category features, the sum of the proportion for each category may not equal 100% because the missing value exists or another small proportion of category features is not included; (c) infertility is encoded by 0 or 1 if the patient is primary or secondary, respectively; (d) the fragment is encoded by three values: 1 to 3 representing no fragment, 5%-15% fragment, and > 15% fragment, respectively; (e) the equality is encoded by five values, 0 to 4, and represent equal, sort of equal, unequal, sort very unequal, and very unequal, respectively. Controlled Ovarian Hyperstimulation, Embryo Culture, And Pregnancy Ascertain IVF patients were treated with controlled ovarian hyperstimulation (COH) by gonadotropin-releasing hormone (GnRH) agonist or GnRH antagonist, as previously described [ 14 , 15 ]. When two dominant follicles reached 17–18 mm in diameter, oocytes were retrieved transvaginally 36–38 hours after a human chorionic gonadotropin (hCG) trigger. Embryos were cultured in G1 medium (Vitrolife, Sweden) after fertilization and transferred on day 3. Subsequently, biochemical pregnancy was ascertained by a positive serum hCG two weeks after embryo transfer with serial elevation. Clinical pregnancy was defined as a gestational sac and active fetal heartbeat on ultrasound demonstration eight weeks after embryo transfer. Model Construction, Feature Selection, And Validation According to previous studies, the outcome of DET is not a simple binomial distribution with respect to two transferred embryos [ 16 ]. Therefore, a hierarchical model with two levels was established to learn single embryo implantation potential and the impact of double embryos transferred simultaneously. In the first level, patient and embryo features were applied to predict the implantation chance for single embryo, from which the output value was directly treated as the predicted pregnancy chance. For DET, another two features, namely P1 + P2 and P1 × P2, were generated, using the P1 and P2 values predicted by the first level for two embryos, followed by the combination of generated features and patient features as the input for second level. Two models were developed in the second level, one to predict the DET pregnancy chance and the other to predict the DET twin risk. The overall flowchart of our model is shown in Fig. 1 . The first-level model was trained by all data except DET with only one embryo implantation, whereas the second-level models were trained by all DET data. The machine learning system applied here was XGBoost [ 17 ]. XGBoost is a scalable machine learning system for tree boosting, which uses the boosting technique to train multiple trees. In other words, XGBoost is an ensemble of multiple decision trees. Unlike random forest, which generates trees by randomly selecting a subset of training sets and features, XGBoost generates decision trees one by one, based on the performance of the previous generated trees. And comparing to single decision tree algorithm such as C4.5 or CART, ensemble of trees can achieve better performance. Moreover, this system can automatically deal with missing values and assign the importance score for each feature, which was applied for feature selection. Nineteen features were selected and are marked by asterisks in Table 1 . As the training procedure was completed, the performance of the model was evaluated with the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Multiple regression analyses were also conducted on the 19 selected features, with the glm function in R to demonstrate the differences between feature importance for prediction and statistical relationship with outcomes. Embryo Selection Strategy Development Subsequently, an embryo selection strategy to maximize the pregnancy chance with a controlled twin rate threshold setting was developed. As shown in Fig. 2 , for any given acceptable twin rate threshold, the pregnancy and twin rate could be predicted for every possible embryo selection strategy, including one or two best embryos to transfer or the combination of one best embryo and one medium-quality embryo. Moreover, if the transfer failed in the fresh cycle, the plan would be redeveloped with the remaining embryos, following the same protocol until all embryos were transferred or a new cycle was started. With this selection strategy, the prediction model could effectively increase the percentages of elective SET patients and provide plausible plans for DET patients in IVF. Statistical analysis Continuous variables were presented as mean ± standard deviation. Categorical variables were presented as percentage encoded by one-hot encoding for analysis. For XGBoost algorithm, we used the implementation from scikit-learn ( https://xgboost.readthedocs.io/en/latest/python/ python_api.html) using Python. The parameters were as follows: max_depth = 5, min_child_weight = 1, learning_rate = 0.1, n_estimators = 100, gamma = 0, subsample = 0.8, colsample_bytree = 0.8. Other parameters were set by default. Results Variable analysis using training data (January 2016 to March 2018) The results of multiple regression analyses are shown in Table 2 . For a SET pregnancy, the following variables remained significant: age, attempts at IVF, estradiol level on hCG day, and endometrial thickness. For DET pregnancy, age, attempts at IVF, endometrial thickness, and the newly added P1 + P2 remained significant. For DET twin risk, age, attempts at IVF, 2 pronucleus (PN)/ metaphase II (M II), and P1 × P2 remained significant. Table 2 Multivariate analysis results of the selected features for SET pregnancy, DET pregnancy and twin risk prediction. Selected features P value SET DET Pregnancy Pregnancy Twin Risk Age 0.0222* < 0.0001* < 0.0001* Attempt times of IVF < 0.001* < 0.0001* < 0.0001* Antral follicle count 0.3332 0.4016 0.4121 Follicle stimulating hormone 0.7307 0.8141 0.4633 Luteinizing hormone 0.3501 0.7230 0.4616 E2 on HCG day 0.0053* 0.9040 0.7684 Endometrial Thickness 0.0046* < 0.0001* 0.2080 MⅡ 0.9455 0.9444 0.0546 2PN 0.1041 0.9068 0.1021 Oocyte Number 0.7510 0.8897 0.6324 2PN/MⅡ 0.5038 0.7772 0.0148* Stimulation Protocol Agonist Protocol 0.3692 0.2019 0.4961 Endometrial Type A 0.8531 0.5324 0.4914 C 0.7138 0.0887 0.4614 Secondary Infertility 0.0816 0.2445 0.6809 Fertilization Method ICSI 0.2365 0.5069 0.8492 Embryo Features Blastomere Number 0.5422 NU a NU Fragment 0.1585 NU NU Equality 0.5399 NU NU Embryo Scores P1 + P2 NU < 0.001* 0.1344 P1 × P2 NU 0.2040 0.007* *P < 0.05; a NU means this feature was not used in the corresponding level. Feature Importance Of The Hierarchical Model In the XGBoost algorithm, the feature importance means the number of times that a feature is used to split the data across all trees. A higher feature importance score represents greater value for prediction. Figure 3 shows the feature importance in the hierarchical model for a SET pregnancy, a DET pregnancy, and DET twin risk. Some features are not shown in Fig. 3 because the corresponding importance was zero, which means these features were not used for prediction. For SET, as shown in Table 2 , the luteinizing hormone (LH) level and follicle-stimulating hormone (FSH) level were not statistically significant, yet they were the third- and sixth-important features for the first-level model. The same phenomenon was observed for FSH, LH, and antral follicle count (AFC) in DET pregnancy and DET twin risk prediction. Although P1 × P2 was significantly correlated with DET twin risk, it was hardly used by either level model. Model Validation Results The algorithm was repeated 30 times to eliminate the interference of random factors, and averaged AUCs of 0.7945, 0.8385, and 0.7229 were achieved for SET pregnancy, DET pregnancy, and DET twin risk, respectively. The ROC curve in one single run is shown in Fig. 4 . To validate the effectiveness of the developed embryo selection strategy, the consistency between the predicted chance and the observed actual outcomes was analyzed, as shown in Fig. 5 . The trend of predictive and observed rates both in pregnancy and twin risk was basically identical, although with a slight elevation in predictive rates. To validate the prediction performance among XGBoost and other algorithms such as logistic regression (LR) and classification and regression tree (CART), we also performed a non-parametric multiple comparison test using Dunn’s procedure [ 18 ], with a p-value correction using the False Discovery Rate method [ 19 ]. The results are shown in Fig. 6 , where the significant ones (p < 0.05) are marked in asterisk. In general, XGBoost outperformed the other two algorithms with obvious prediction power in SET pregnancy prediction and DET twin risk prediction and similar performance in DET pregnancy prediction task. Discussion One of the most overwhelming challenges in contemporary assisted reproductive technology (ART) is how to narrow the gap in perinatal and neonatal outcomes between spontaneous pregnancy and assisted pregnancy, usually caused by multiple-embryo transfer and implantation [ 20 ]. In recent decades, SET has been advocated in IVF to prevent multiple pregnancies while led to the concerns of decreased IVF success [ 3 , 21 , 22 ]. Therefore, precise embryo selection for SET and twin risk warning for DET are particularly necessary. In this paper, a novel hierarchical model was constructed and validated to optimize embryo selection strategies and successfully predict pregnancy for both SET and DET, as well as predict the twin risk of DET for each individual. Subsequently, we validated our model on 2961 patients, and the results showed that our model had achieved an acceptable performance on embryo selection and twin risk prediction for each individual, as shown in Fig. 4 and Fig. 5 . It is generally accepted that embryos with similar morphology present variable implantation probability, depending on other assessed features such as patient characteristics and cycle demographics. Many features, including age, FSH level, anti-Mullerian hormone (AMH) and embryo quality, have been reported as independent impact factors on oocyte variability and embryo implantation potential [ 5 , 23 – 26 ]. Machine learning is considered a powerful mathematical tool for correlation analysis when huge data is involved; therefore, AI has been introduced in embryo variability prediction in many articles [ 27 , 28 ]. By increasing the information of the input features, the predictive power of the proposed model may be improved. Similarly, 19 features from the initial data sets were considered in the current study to construct the predictive power in our model. It is noteworthy that although previous models may have helped predict the implantation potential of a specific embryo, they did not offer a reasonable and optimal guidance to the embryo selection determination in clinical practice. Minaretzis et al . [ 29 ] once presented an embryo selection strategy of transferring one additional good-quality embryo for each five years of incremental increase in maternal age to improve IVF outcome by multivariate analysis of factors predictive of successful live birth. Because maternal age was the only influencing factor to be considered, the recommended strategy was not so accurate or comprehensive. Kaufmann et al . [ 30 ] reported a neural networks predicting model in IVF, where four input parameters were included and the overall accuracy was 59%. Uyar et al . [ 31 ] proposed a Support Vector Machine (SVM) method in embryo implantation prediction in terms of Area Under ROC curve (0.712 ± 0.032), when 12 features were included. Vaegter et al. [ 16 ] also constructed a predictive model for an embryo transfer strategy, in which only one embryo was transferred if the predictive risk of twin implantation was above 15%, using the two highest scored embryos. While validating this predictive model, the actual twin rate was 3.8%, which was far lower than the expected 15% setting, accompanied by a decreased live birth rate. Unlike previous studies, a novel strategy in embryo selection based on an accurate embryo potential prediction and twin risk assessment was developed in our model. The model not only guides a determination of the number of embryos for transfer and the specific embryo selection, but also presents a relatively accurate prediction of the pregnancy rate and twin risk of the corresponding selection scheme. Because SET was not arbitrarily implemented in all IVF patients, twin pregnancy was inevitable. However, the acceptable twin rate threshold varied among different countries, even among different IVF centers. The greatest strength of our model was that the embryo selection strategy we developed varied correspondingly to patients’ characteristics and embryo morphology parameters as long as different twin rate thresholds were set. Therefore, the selection strategy model is applicable to any IVF center in any country. In such a situation, embryologists can input their accepted twin rate setting on the model to generate their guided embryo selection strategies and present a predictable pregnancy possibility and twin rate assessment. More important, the predictive twin risk indicated that the transferred two embryos were neither a simplified embryo implantation nor an implantation of two independent samples. This principle was previously discussed in an embryo-uterus modeling framework [ 32 – 34 ]. A higher twin rate than expected would be achieved if the implantation chances of the embryos transferred together were completely independent of one another [ 16 ]. Considering the variability of confounding factors, a two-level algorithm was introduced in our model for DET prediction to achieve a satisfying predictive model. Furthermore, unlike previous researches, which only considered significant influencing factors in model construction [ 35 – 37 ], concomitant investigation in our DET model provided a novel insight: that even if one variable were not statistically significant, it might still be important for machine learning models to predict final outcomes. To minimize twin risk, some researchers also constructed a predictable model and validated it in subsequent IVF cycles, and the results showed a significantly reduced twin rate (from 25.2–3.8%) [ 16 ]. However, the proportion of SETs was greatly increased (11.3–75.5%), and surplus embryos would be preserved for future use, resulting in a reduced live birth rate in fresh cycle (29.0–25.1%). Even though the cumulative live birth rate (CLBR) was not affected, patients had to pay more fees and spend more time for a successful pregnancy in subsequent frozen-thawed cycles. Luke et al . [ 38 ] also reported a similar conclusion of comparative CLBR and decreased multiple births in SETs over two cycles, compared to DET in one cycle. In our algorithm, conversely, the pregnancy rate and twin risk were assessed and predicted simultaneously in the fresh cycle, and further validation showed that it effectively reduced twin risk without compromising clinical pregnancy in the fresh cycle. The recommended embryo selection strategy in our model provides decision support to embryologists with higher accuracy and efficiency. For a large proportion of IVF patients with suboptimal prognosis, which plan to choose was a dilemma to embryologists, because prediction judgment was based on their clinical experience instead of on the analysis of thousands of embryos and patient records prior to each embryo transfer [ 39 , 40 ]. Besides, it may also act as a counseling tool for clinicians to evaluate the chance of pregnancy before the transfer procedure. Previous research to establish similar predictive models were problematic due to the limited number of involved features or dramatic distinction between the predicted value and the actual situation [ 16 , 29 ]. The model in the current study guides a determination of the number of embryos for transfer and the specific embryo selection, based on the analysis of a large number of features. In addition, the predicted pregnancy rate and twin risk of the corresponding selection scheme were relatively more accurate. More significantly, our model provides a flexible strategy, with individualized embryo selection for any given patient and varied operations corresponding with any setting acceptable twin rate threshold. One shortcoming of our predictive model was that the predicted mean value was slightly elevated compared to the actual observed rate for both pregnancy and twin rates in validation, although a modest discrimination was also reported in the previous prediction model in ART [ 41 – 43 ]. The model should be adjusted and improved to make the predictive value more closely agree with the actual virtue in the future verification. Besides, the model was developed and validated using data from a single center. As future work, we will need to be much more rigorous with additional data sets demonstrating the predictive value, using the same parameters, as well as applying them in different centers. Conclusions In our study, we constructed and validated an individualized embryo selection strategy and pregnancy prediction model developed by stacking machine learning. This prediction model could provide an accurate and individualized embryo selection strategy for any given patient as well as in any twin risk threshold setting and balance a delicate correlation between clinical pregnancy and twin risk rate; it therefore promises a better IVF outcome without compromising pregnancy success and controlled twin risk. Abbreviations In vitro fertilization (IVF) Single embryo transfer (SET) Double embryo transfer (DET) Artificial intelligence (AI) Controlled ovarian hyperstimulation (COH) Gonadotropin-releasing hormone (GnRH) Human chorionic gonadotropin (hCG) Area under the curve (AUC) Receiver operating characteristic (ROC) Follicle-stimulating hormone (FSH) Luteinizing hormone (LH) Antral follicle count (AFC) Logistic regression (LR) Classification and regression tree (CART) Assisted reproductive technology (ART) Anti-Mullerian hormone (AMH) Cumulative live birth rate (CLBR) Declarations Ethics approval and consent to participate The study was approved by the medical ethics committee of Tongji Medical College of Huazhong University of Science and Technology and written informed consent was obtained from all patients before they were included. All methods were performed in accordance with the relevant guidelines and regulations. Consent for publication Not applicable. Availability of data and materials All data generated or analysed during this study are included in this published article. Competing interests The authors declare that they have no competing interests. Funding This work was supported by research grants from the National Key Research and Development Project (grant number: 2018YFC1002103) and the Chinese Medical Association (grant number: 16020520668) as well as the Natural Science Foundation of Hubei Province (grant number:2017CFB752). Authors' contributions Q.X., M.W., B.Z., Z.L., and B.H.conducted the experiment; Q.Y., L.Y., and S.L. analyzed the data, Q.X. and Q.Y. composed the manuscript, and L.Z. and L.J. were responsible for the concept and study design. All authors contributed to the interpretation, discussion and editing of the manuscript. All authors approved the last version. Acknowledgements Not applicable. References Sunderam S, Kissin DM, Crawford SB, Folger SG, Jamieson DJ, Warner L, et al. Assisted reproductive technology surveillance-United States, 2014. MMWR Surveill Summ. 2017;66(6):1. Chambers GM, Ledger W. The economic implications of multiple pregnancy following ART. Semin Fetal Neonatal Med. 2014;19(4):254–61. Meldrum DR, Adashi EY, Garzo VG, Gleicher N, Parinaud J, Pinborg A, et al. Prevention of in vitro fertilization twins should focus on maximizing single embryo transfer versus twins are an acceptable complication of in vitro fertilization. Fertil Steril. 2018;109(2):223–29. Bergh T, Ericson A, Hillensjö T, Nygren KG, Wennerholm UB. Deliveries and children born after in-vitro fertilisation in Sweden 1982-95: a retrospective cohort study. Lancet. 1999;354(9190):1579–85. Van Loendersloot L, Van Wely M, Limpens J, Bossuyt PM, Repping S, van der Veen F. Predictive factors in in vitro fertilization (IVF): A systematic review and meta-analysis. Hum Reprod Update. 2010;16(6):577–89. Rienzi L, Vajta G, Ubaldi F. Predictive value of oocyte morphology in human IVF: A systematic review of the literature. Hum Reprod Update. 2010;17(1):34–45. Iliodromiti S, Kelsey TW, Wu O, Anderson RA, Nelson SM. The predictive accuracy of Anti-Müllerian hormone for live birth after assisted conception: A systematic review and meta-analysis of the literature. Hum Reprod Update. 2014;20(4):560–70. Fang T, Su Z, Wang L, Yuan P, Li R, Ouyang N, et al. Predictive value of age-specific FSH levels for IVF-ET outcome in women with normal ovarian function. Reprod Biol Endocrinol. 2015;13(1):63. Corani G, Magli C, Giusti A, Gianaroli L, Gambardella LM. A Bayesian network model for predicting pregnancy after in vitro fertilization. Comput Biol Med. 2013;43(11):1783–92. Debón A, Molina I, Cabrera S. Mathematical methodology to obtain and compare different embryo scores. Math Comput Model. 2013;57(5–6):1380–94. Guerif F, Le Gouge A, Giraudeau B, Poindron J, Bidault R, Gasnier O, et al. Limited value of morphological assessment at days 1 and 2 to predict blastocyst development potential: A prospective study based on 4042 embryos. Hum Reprod. 2007;22(7):1973–81. Morales DA, Bengoetxea E, Larrañaga P. Selection of human embryos for transfer by Bayesian classifiers. Comput Biol Med. 2008;38(11–12):1177–86. Roberts SA. Models for assisted conception data with embryo-specific covariates. Stat Med. 2007;26(1):156–70. Zhu L, Xi Q, Zhang H, Li Y, Ai J, Jin L. Blastocyst culture and cryopreservation to optimize clinical outcomes of warming cycles. Reprod Biomed Online. 2013;27(2):154–60. Zhu L, Xi Q, Nie R, Chen W, Zhang H, Li Y. Rescue intracytoplasmic sperm injection: A prospective randomized study. J Reprod Med. 2011;56(9–10):410–14. Vaegter KK, Berglund L, Tilly J, Hadziosmanovic N, Brodin T, Holte J. Construction and validation of a prediction model to minimize twin rates at preserved high live birth rates after IVF. Reprod Biomed Online. 2019;38(1):22–9. Chen T, Guestrin C. XGBoost: A scalable tree boosting system. Proc Int’l Conf on Knowledge Discovery and Data Mining 2016 Aug; San Francisco, CA. Dunn OJ. Multiple comparisons using rank sums. Technometrics. 1964;6:214–52. Benjamini Y, Hochberg Y. Controlling the false discovery rate: A practical and powerful approach to multiple testing. J R Stat Soc Series B Stat Methodol. 1995;57:289–300. Helmerhorst FM, Perquin DA, Donker D, Keirse MJ. Perinatal outcome of singletons and twins after assisted conception: a systematic review of controlled studies. BMJ. 2004;328(7434):261. Drakopoulos P, Blockeel C, Stoop D, Camus M, de Vos M, Tournaye H, et al. Conventional ovarian stimulation and single embryo transfer for IVF/ICSI. How many oocytes do we need to maximize cumulative live birth rates after utilization of all fresh and frozen embryos? Hum Reprod. 2016;31(2):370–76. Van Voorhis B, Mejia RB. Single-embryo transfer point-it is the way forward. Fertil Steril. 2017;108(5):757. Cai Q, Wan F, Appleby D, Hu L, Zhang H. Quality of embryos transferred and progesterone levels are the most important predictors of live birth after fresh embryo transfer: A retrospective cohort study. J Assist Reprod Genet. 2014;31(2):185–94. Lee TH, Chen CD, Tsai YY, Chang LJ, Ho HN, Yang YS. Embryo quality is more important for younger women whereas age is more important for older women with regard to in vitro fertilization outcome and multiple pregnancy. Fertil Steril. 2006;86(1):64–9. Leijdekkers J, Eijkemans M, Van Tilborg T, Oudshoorn SC, McLernon DJ, Bhattacharya S, et al. Predicting the cumulative chance of live birth over multiple complete cycles of in vitro fertilization: An external validation study. Hum Reprod. 2018;33(9):1684–95. Yanez LZ, Han J, Behr BB, Pera RAR, Camarillo DB. Human oocyte developmental potential is predicted by mechanical properties within hours after fertilization. Nat Commun. 2016;7:10809. Vaegter KK, Lakic TG, Olovsson M, Berglund L, Brodin T, Holte J. Which factors are most predictive for live birth after in vitro fertilization and intracytoplasmic sperm injection (IVF/ICSI) treatments? Analysis of 100 prospectively recorded variables in 8,400 IVF/ICSI single-embryo transfers. Fertil Steril. 2017;107(3):641–48. e2. Siristatidis C, Pouliakis A, Chrelias C, Kassanos D. Artificial intelligence in IVF: a need. Syst Biol Reprod Med. 2011;57(4):179–85. Minaretzis D, Harris D, Alper MM, Mortola JF, Berger MJ, Power D. Multivariate analysis of factors predictive of successful live births in in vitro fertilization (IVF) suggests strategies to improve IVF outcome. J Assist Reprod Genet. 1998;15(6):365–71. Kaufmann SJ, Eastaugh JL, Snowden S, Smye SW, Sharma V. The application of neural networks in predicting the outcome of in-vitro fertilization. Hum Reprod. 1997;12:1454–7. Uyar A, Bener A, Ciray H, Bahceci M. A frequency based encoding technique for transformation of categorical variables in mixed IVF dataset. Conf Proc IEEE Eng Med Biol Soc. 2009; 2009: 6214–6217. Hunault CC, Eijkemans MJ, Pieters MH, te Velde ER, Habbema JD, Fauser BC, et al. A prediction model for selecting patients undergoing in vitro fertilization for elective single embryo transfer. Fertil Steril. 2002;77(4):725–32. Roberts S, Hirst W, Brison D, Vail A, towardSET collaboration. Embryo and uterine influences on IVF outcomes: An analysis of a UK multi-centre cohort. Hum Reprod. 2010;25(11):2792 – 802. Roberts SA, McGowan L, Mark Hirst W, Vail A, Rutherford A, Lieberman BA, et al. Reducing the incidence of twins from IVF treatments: Predictive modelling from a retrospective cohort. Hum Reprod. 2010;26(3):569–75. Luke B, Brown MB, Wantman E, Stern JE, Baker VL, Widra E, et al. A prediction model for live birth and multiple births within the first three cycles of assisted reproductive technology. Fertil Steril. 2014;102(3):744–52. Rongieres C, Colella C, Lehert P. To what extent does Anti-Mullerian hormone contribute to a better prediction of live birth after IVF? J Assist Reprod Genet. 2015;32(1):37–43. Vogiatzi P, Pouliakis A. An artificial neural network for the prediction of assisted reproduction outcome. J Assist Reprod Genet. 2019;36:1441–8. Luke B, Brown MB, Wantman E, Stern JE, Baker VL, Widra E, et al. Application of a validated prediction model for in vitro fertilization: Comparison of live birth rates and multiple birth rates with 1 embryo transferred over 2 cycles vs 2 embryos in 1 cycle. Am J Obstet Gynecol. 2015;212(5):676. Van Der Steeg J, Steures P, Eijkemans M, Habbema JD, Bossuyt PM, Hompes PG, et al. Do clinical prediction models improve concordance of treatment decisions in reproductive medicine? BJOG. 2006;113(7):825–31. Wiegerinck MA, Bongers MY, Mol BW, Heineman MJ. How concordant are the estimated rates of natural conception and in-vitro fertilization/embryo transfer success? Hum Reprod. 1999;14(3):689–93. Choi B, Bosch E, Lannon BM, Leveille MC, Wong WH, Leader A, et al. Personalized prediction of first-cycle in vitro fertilization success. Fertil Steril. 2013;99(7):1905–11. Leushuis E, van der Steeg JW, Steures P, Bossuyt PM, Eijkemans MJ, van der Veen F, et al. Prediction models in reproductive medicine: A critical appraisal. Hum Reprod Update. 2009;15(5):537–52. Van Loendersloot L, Repping S, Bossuyt PM, van der Veen F, van Wely M. Prediction models in in vitro fertilization; where are we? A mini review. J Adv Res. 2014;5(3):295–301. Cite Share Download PDF Status: Published Journal Publication published 05 Apr, 2021 Read the published version in Reproductive Biology and Endocrinology → Version 1 posted Editorial decision: Minor revision 31 Jan, 2021 Review # 1 received at journal 24 Jan, 2021 Reviewer # 1 agreed at journal 09 Jan, 2021 Reviewers invited by journal 02 Jan, 2021 First submitted to journal 31 Dec, 2020 Editor assigned by journal 31 Dec, 2020 Submission checks completed at journal 31 Dec, 2020 Editor invited by journal 31 Dec, 2020 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-140383","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research","associatedPublications":[],"authors":[{"id":7463940,"identity":"3669c103-f5b3-4d8d-a062-72dd5f0013b9","order_by":0,"name":"Qingsong XI","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qingsong","middleName":"","lastName":"XI","suffix":""},{"id":7463941,"identity":"3bf44747-1f33-408e-8232-d10821768817","order_by":1,"name":"Qiyu YANG","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qiyu","middleName":"","lastName":"YANG","suffix":""},{"id":7463942,"identity":"e362e5fd-954c-475d-b3e3-9f8b75b94339","order_by":2,"name":"Meng WANG","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Meng","middleName":"","lastName":"WANG","suffix":""},{"id":7463943,"identity":"46479959-9e42-45ce-9451-f2db42bee0d7","order_by":3,"name":"Bo HUANG","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"HUANG","suffix":""},{"id":7463944,"identity":"3725d003-db36-4010-84f2-1cefc4a8b4cd","order_by":4,"name":"Bo ZHANG","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"ZHANG","suffix":""},{"id":7463945,"identity":"e7577461-79ac-4edf-8037-ef5f26138c37","order_by":5,"name":"Zhou LI","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zhou","middleName":"","lastName":"LI","suffix":""},{"id":7463946,"identity":"13305b2a-d19d-4839-8aaa-db8005ca2978","order_by":6,"name":"Shuai LIU","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shuai","middleName":"","lastName":"LIU","suffix":""},{"id":7463947,"identity":"00a1e936-fc64-407d-a67b-28e55c3953c6","order_by":7,"name":"Liu YANG","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Liu","middleName":"","lastName":"YANG","suffix":""},{"id":7463948,"identity":"20078f50-446d-4bb0-8c16-3814e052cb3d","order_by":8,"name":"Lixia ZHU","email":"","orcid":"","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lixia","middleName":"","lastName":"ZHU","suffix":""},{"id":7463949,"identity":"30fde2c8-90cc-43a2-898b-ddaea1ca8c63","order_by":9,"name":"Lei Jin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2ElEQVRIiWNgGAWjYBACPgbGBoMECDvhMEMFEVrYIFoMoFrOEKUFDMBaGJgZ24jRwt7cUPBwxx85c/4FDw8XzrOWbWA/fHQDXi08BxsMEs8YGFvOeJBweOa2dOMGnrS0G3i1SCQCtbQZJG64cSDhMO+2w4kNEjxm+LXIP0TWMocYLRKMUC3nG4BaGojRwgN2mLGxwQ1gIPMcSzduI+QXfvbjzwx/tsnJGZw/k/yZp8Zatp/98DG8WkAWQSJFIieBgdioYX4Ase/4AbCWBiK0jIJRMApGwcgCAJrlT6jQxJazAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-0367-7765","institution":"Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Jin","suffix":""}],"badges":[],"createdAt":"2021-01-04 12:31:00","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-140383/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-140383/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12958-021-00734-z","type":"published","date":"2021-04-05T19:02:19+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":4865078,"identity":"759878d6-ed7b-4738-a339-d34c6b12706a","added_by":"auto","created_at":"2021-01-11 15:42:04","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":79058,"visible":true,"origin":"","legend":"The overall flowchart of the proposed hierarchical model. The first-level model was trained using all data except double embryo transfer (DET), with only one embryo implantation to predict single-embryo implantation outcomes. The second level contains two models, which were trained using DET data to predict both DET implantation outcomes and twin risks.","description":"","filename":"OnlineFig.1.png","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/828d4e4346a01f5ed8158017.png"},{"id":4865189,"identity":"3188fff2-ec03-46d9-ac5a-f2da1b2fca1c","added_by":"auto","created_at":"2021-01-11 15:45:04","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":96872,"visible":true,"origin":"","legend":"Embryo selection strategy developed by the proposed model. For any given acceptable twin rate threshold, the pregnancy and twin rates could be predicted.","description":"","filename":"OnlineFig.2.png","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/9bb1925f922729ba1371d6cc.png"},{"id":4865187,"identity":"af102275-adad-4957-8c59-6413a28d2f46","added_by":"auto","created_at":"2021-01-11 15:45:04","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":89506,"visible":true,"origin":"","legend":"Feature importance in the hierarchical model for SET pregnancy. Feature importance of (A) first-level model for predicting SET pregnancy, (B) second-level model for predicting DET pregnancy, and (C) second-level model for predicting DET twin risk.","description":"","filename":"OnlineFig.3.png","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/ff59dd6e46d4af738d9ccce9.png"},{"id":4865190,"identity":"5d849a2f-e778-4916-8869-8bf8b91fbc2b","added_by":"auto","created_at":"2021-01-11 15:45:05","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":26509,"visible":true,"origin":"","legend":"The ROC curve of a single-embryo transfer (SET) pregnancy, double-embryo transfer (DET) pregnancy, and DET twin risk in our method. The average AUCs for a SET pregnancy, a DET pregnancy, and DET twin risk were 0.7945, 0.8385, and 0.7229, respectively.","description":"","filename":"OnlineFig.4.png","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/c4d8538e38893430414f52dc.png"},{"id":4865083,"identity":"9a9b18e6-b1f6-4ad4-9e34-2df4a81faa3f","added_by":"auto","created_at":"2021-01-11 15:42:05","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":67295,"visible":true,"origin":"","legend":"Validation using the predicted value with the truly observed percentage. (A) Pregnancy prediction in single-embryo transfer (SET) and double-embryo transfer (DET) versus truly observed percentage. (B) Twin risk prediction in DET versus truly observed twin rate.","description":"","filename":"OnlineFig.5.png","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/d3411445e1a691066ec8d235.png"},{"id":4865188,"identity":"aa870ecd-76cb-4c03-9996-cc3ed73eda48","added_by":"auto","created_at":"2021-01-11 15:45:04","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":23928,"visible":true,"origin":"","legend":"AUC performance comparison among XGBoost, CART, and LR on single-embryo transfer (SET) pregnancy, double-embryo transfer (DET) pregnancy, and DET twin risk prediction. ****P\u003c0.0001","description":"","filename":"OnlineFig.6.png","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/ee2a826ab37c95dd57282ce3.png"},{"id":13644303,"identity":"86482c4d-ca7c-47a1-8bb6-72028f87945d","added_by":"auto","created_at":"2021-09-17 09:15:38","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1088896,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-140383/v1/98a9a4ba-cd7e-4058-98b2-79502d40bb3e.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eIndividualized Embryo Selection Strategy Developed by Stacking Machine Learning Model for Better In Vitro Fertilization Outcomes: An Application Study.\u003c/p\u003e","fulltext":[{"header":"Introduction","content":" \u003cp\u003eFor decades, discussions about how to improve the clinical outcomes of in vitro fertilization (IVF) treatment have persisted. Multiple-embryo transfer was suggested to increase the possibility of successful implantation but inevitably elevated the risk of multiple-embryo gestation. IVF-associated multiple pregnancies exhibit significant financial, social, and medical implications [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Even though the transfer of embryos has been limited to no more than two in recent years, the overall twin rate worldwide after assisted reproduction has still varied from 15\u0026ndash;30% [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. The incidences of premature birth, low birth weight, cerebral palsy, neurological complications, and perinatal mortality of twin pregnancy markedly increased compared with singleton pregnancy [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. To minimize the rate of multiple-embryo gestation, significant efforts, including individualized service provision and single embryo transfer (SET) enhancement, have been made in the course of these decades.\u003c/p\u003e \u003cp\u003eEmbryo morphological analysis is the routine method for selecting the highest-quality embryos to transfer. It is commonly suggested to perform SET on prognostically good patients with a top-quality embryo and to perform double embryo transfer (DET) in prognostically poor patients because no good-quality embryos are available in the IVF lab. In a large proportion of IVF patients with sub-optimal prognosis or with medium- or inferior-quality embryos, the selection between SET and DET could be perplexing. Because many features have been shown to influence embryo implantation potential positively or negatively in IVF [\u003cspan additionalcitationids=\"CR6 CR7\" citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e], developing an optimal embryo selection plan to balance maximum clinical pregnancy rate and minimum twin risk is complicated for IVF clinicians. Therefore, a more precise, quantified, stable embryo selection model based on all possible influencing determinants needs to be constructed. This will potentially offer evidence-based patient counseling and predictable successful chances for any given patient.\u003c/p\u003e \u003cp\u003eArtificial intelligence (AI) represents the combination of machine learning, and a moderation and self-adapting prediction model. Previous studies related to machine learning in IVF mainly focused on selecting the top-quality embryos to improve IVF outcomes [\u003cspan additionalcitationids=\"CR10 CR11 CR12\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Developing a flexible, individualized embryo selection approach based on available embryos of various qualities and different twin rate threshold settings is another promising issue.\u003c/p\u003e \u003cp\u003eThe purpose of our study is to construct an individualized embryo selection strategy and pregnancy prediction model, developed by stacking machine learning, to identify features correlated with embryo implantation potential and to evaluate available embryos\u0026rsquo; implantation chances quantitatively. We aim to balance maximal clinical pregnancy and minimal acceptable twin risk in IVF with this model and validate its clinical effectiveness and practicability in subsequent cycles..\u003c/p\u003e "},{"header":"Materials And Methods","content":" \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy design and participants\u003c/h2\u003e \u003cp\u003eIVF patients in Tongji Hospital between January 2016 and December 2018, with one or two embryo transfers in the fresh cycle, were enrolled in our study. Exclusion criteria included patients with (1) blastocyst transfer in fresh cycle; (2) oocyte donation cycles; (3) vitrified/warmed oocytes; (4) oocytes partially cryopreserved in fresh cycle; (5) combined vitrified/warmed embryo transfers. In total, 4926 patients, between January 2016 and March 2018 were included as the training set to construct our model. Thirty-eight features were analyzed in our study, and their baselines on training and validation sets were exhibited, among which 21 main variables were selected and listed in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, including patient features, embryo morphology features, and embryo scores. After model construction, the developed embryo selection strategy was applied to guide the selection of SET or DET in 2961 individual cases between April and December 2018 as the validation set.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003e Baseline characteristics of the variables included in the training and validation data sets.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFeatures\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eTraining set (n\u0026thinsp;=\u0026thinsp;4926)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eValidation set (n\u0026thinsp;=\u0026thinsp;2961)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003ePatient composition\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSET\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4489\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2700\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDET\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e437\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e261\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAge*, y\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30.46\u0026thinsp;\u0026plusmn;\u0026thinsp;4.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e30.70\u0026thinsp;\u0026plusmn;\u0026thinsp;3.94\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAttempt times of IVF*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.95\u0026thinsp;\u0026plusmn;\u0026thinsp;0.43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.78\u0026thinsp;\u0026plusmn;\u0026thinsp;0.54\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAntral follicle count*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13.64\u0026thinsp;\u0026plusmn;\u0026thinsp;6.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e13.37\u0026thinsp;\u0026plusmn;\u0026thinsp;6.36\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFollicle stimulating hormone*, IU/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.59\u0026thinsp;\u0026plusmn;\u0026thinsp;2.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.68\u0026thinsp;\u0026plusmn;\u0026thinsp;2.79\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eLuteinizing hormone*, IU/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.71\u0026thinsp;\u0026plusmn;\u0026thinsp;3.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.95\u0026thinsp;\u0026plusmn;\u0026thinsp;6.08\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eE2 per mature oocyte, pmol/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e309.60\u0026thinsp;\u0026plusmn;\u0026thinsp;141.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e265.68\u0026thinsp;\u0026plusmn;\u0026thinsp;133.16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eE2 on HCG day*, pmol/L\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2810.88\u0026thinsp;\u0026plusmn;\u0026thinsp;1424.43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2174.64\u0026thinsp;\u0026plusmn;\u0026thinsp;1046.56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEndometrial\u0026nbsp;Thickness*, mm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11.79\u0026thinsp;\u0026plusmn;\u0026thinsp;2.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11.98\u0026thinsp;\u0026plusmn;\u0026thinsp;2.55\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMetaphaseⅡ(M II)*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.86\u0026thinsp;\u0026plusmn;\u0026thinsp;4.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9.25\u0026thinsp;\u0026plusmn;\u0026thinsp;4.02\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e2pronucleus(PN)*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.79\u0026thinsp;\u0026plusmn;\u0026thinsp;3.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.31\u0026thinsp;\u0026plusmn;\u0026thinsp;3.22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eOocyte Number\u003csup\u003ea\u003c/sup\u003e*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e11.03\u0026thinsp;\u0026plusmn;\u0026thinsp;4.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10.64\u0026thinsp;\u0026plusmn;\u0026thinsp;4.49\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e2PN/MⅡ*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.70\u0026thinsp;\u0026plusmn;\u0026thinsp;0.19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.69\u0026thinsp;\u0026plusmn;\u0026thinsp;0.20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFrozen Sperm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.3%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMale Factor\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eOligospermia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e10.3%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAsthenospermia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e20.0%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAzoospermia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.1%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9.1%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFemale Factor\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEndometriosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.4%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eOvulation Disorder\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.8%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eUnknown\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12.3%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSperm Retrieval\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEjaculation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e95.2%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.2%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eMESA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.7%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eTESA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.3%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003ePESA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.8%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eStimulation Protocol\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAgonist Protocol*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e71.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e70.8%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eAntagonist Protocol\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22.8%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e28.5%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEndometrial Type\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eA*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e83.3%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e85.0%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eB\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eC*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21.4%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e19.7%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eInfertility\u003csup\u003ec\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003ePrimary\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e64.9%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e70.4%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eSecondary*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e35.1%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e29.6%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFertilization\u0026nbsp;Method\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eIVF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e72.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e57.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eICSI*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e24.5%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e34.8%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEmbryo Features\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eNumber of Blastomere*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7.93\u0026thinsp;\u0026plusmn;\u0026thinsp;0.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.06\u0026thinsp;\u0026plusmn;\u0026thinsp;0.93\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eFragment\u003csup\u003ed\u003c/sup\u003e*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.37\u0026thinsp;\u0026plusmn;\u0026thinsp;0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.32\u0026thinsp;\u0026plusmn;\u0026thinsp;0.48\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eEquality\u003csup\u003ee\u003c/sup\u003e*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.91\u0026thinsp;\u0026plusmn;\u0026thinsp;0.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.87\u0026thinsp;\u0026plusmn;\u0026thinsp;0.91\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003e*The selected features after performing feature selection are marked by asterisks.\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003eSET, single-embryo transfer; DET, double-embryo transfer; IVF, in vitro fertilization; ICSI, intracytoplasmic sperm injection; E2: estradiol; hCG, human chorionic gonadotropin; MESA, microscopic epididymal sperm aspiration; TESA, testicular sperm aspiration; PESA, percutaneous epididymal sperm aspiration.\u003c/td\u003e\u003c/tr\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003e(a) Number of oocytes retrieved; (b) for multi-category features, the sum of the proportion for each category may not equal 100% because the missing value exists or another small proportion of category features is not included; (c) infertility is encoded by 0 or 1 if the patient is primary or secondary, respectively; (d) the fragment is encoded by three values: 1 to 3 representing no fragment, 5%-15% fragment, and \u0026gt;\u0026thinsp;15% fragment, respectively; (e) the equality is encoded by five values, 0 to 4, and represent equal, sort of equal, unequal, sort very unequal, and very unequal, respectively.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \n\u003ch2\u003eControlled Ovarian Hyperstimulation, Embryo Culture, And Pregnancy Ascertain\u003c/h2\u003e\n \u003cp\u003eIVF patients were treated with controlled ovarian hyperstimulation (COH) by gonadotropin-releasing hormone (GnRH) agonist or GnRH antagonist, as previously described [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. When two dominant follicles reached 17\u0026ndash;18\u0026nbsp;mm in diameter, oocytes were retrieved transvaginally 36\u0026ndash;38 hours after a human chorionic gonadotropin (hCG) trigger. Embryos were cultured in G1 medium (Vitrolife, Sweden) after fertilization and transferred on day 3. Subsequently, biochemical pregnancy was ascertained by a positive serum hCG two weeks after embryo transfer with serial elevation. Clinical pregnancy was defined as a gestational sac and active fetal heartbeat on ultrasound demonstration eight weeks after embryo transfer.\u003c/p\u003e \n\u003ch2\u003eModel Construction, Feature Selection, And Validation\u003c/h2\u003e\n \u003cp\u003eAccording to previous studies, the outcome of DET is not a simple binomial distribution with respect to two transferred embryos [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Therefore, a hierarchical model with two levels was established to learn single embryo implantation potential and the impact of double embryos transferred simultaneously. In the first level, patient and embryo features were applied to predict the implantation chance for single embryo, from which the output value was directly treated as the predicted pregnancy chance. For DET, another two features, namely P1\u0026thinsp;+\u0026thinsp;P2 and P1\u0026thinsp;\u0026times;\u0026thinsp;P2, were generated, using the P1 and P2 values predicted by the first level for two embryos, followed by the combination of generated features and patient features as the input for second level. Two models were developed in the second level, one to predict the DET pregnancy chance and the other to predict the DET twin risk. The overall flowchart of our model is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The first-level model was trained by all data except DET with only one embryo implantation, whereas the second-level models were trained by all DET data.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe machine learning system applied here was XGBoost [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. XGBoost is a scalable machine learning system for tree boosting, which uses the boosting technique to train multiple trees. In other words, XGBoost is an ensemble of multiple decision trees. Unlike random forest, which generates trees by randomly selecting a subset of training sets and features, XGBoost generates decision trees one by one, based on the performance of the previous generated trees. And comparing to single decision tree algorithm such as C4.5 or CART, ensemble of trees can achieve better performance. Moreover, this system can automatically deal with missing values and assign the importance score for each feature, which was applied for feature selection. Nineteen features were selected and are marked by asterisks in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003eAs the training procedure was completed, the performance of the model was evaluated with the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Multiple regression analyses were also conducted on the 19 selected features, with the glm function in R to demonstrate the differences between feature importance for prediction and statistical relationship with outcomes.\u003c/p\u003e \n\u003ch2\u003eEmbryo Selection Strategy Development\u003c/h2\u003e\n \u003cp\u003eSubsequently, an embryo selection strategy to maximize the pregnancy chance with a controlled twin rate threshold setting was developed. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, for any given acceptable twin rate threshold, the pregnancy and twin rate could be predicted for every possible embryo selection strategy, including one or two best embryos to transfer or the combination of one best embryo and one medium-quality embryo. Moreover, if the transfer failed in the fresh cycle, the plan would be redeveloped with the remaining embryos, following the same protocol until all embryos were transferred or a new cycle was started. With this selection strategy, the prediction model could effectively increase the percentages of elective SET patients and provide plausible plans for DET patients in IVF.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eContinuous variables were presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation. Categorical variables were presented as percentage encoded by one-hot encoding for analysis. For XGBoost algorithm, we used the implementation from scikit-learn (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://xgboost.readthedocs.io/en/latest/python/\u003c/span\u003e\u003c/span\u003e python_api.html) using Python. The parameters were as follows: max_depth\u0026thinsp;=\u0026thinsp;5, min_child_weight\u0026thinsp;=\u0026thinsp;1, learning_rate\u0026thinsp;=\u0026thinsp;0.1, n_estimators\u0026thinsp;=\u0026thinsp;100, gamma\u0026thinsp;=\u0026thinsp;0, subsample\u0026thinsp;=\u0026thinsp;0.8, colsample_bytree\u0026thinsp;=\u0026thinsp;0.8. Other parameters were set by default.\u003c/p\u003e \u003c/div\u003e "},{"header":"Results","content":" \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003eVariable analysis using training data (January 2016 to March 2018)\u003c/h2\u003e \u003cp\u003eThe results of multiple regression analyses are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. For a SET pregnancy, the following variables remained significant: age, attempts at IVF, estradiol level on hCG day, and endometrial thickness. For DET pregnancy, age, attempts at IVF, endometrial thickness, and the newly added P1\u0026thinsp;+\u0026thinsp;P2 remained significant. For DET twin risk, age, attempts at IVF, 2 pronucleus (PN)/ metaphase II (M II), and P1\u0026thinsp;\u0026times;\u0026thinsp;P2 remained significant.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003e Multivariate analysis results of the selected features for SET pregnancy, DET pregnancy and twin risk prediction.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003eSelected features\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003eP value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSET\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e \u003cp\u003eDET\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePregnancy\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePregnancy\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTwin Risk\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.0222*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAttempt times of IVF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAntral follicle count\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.3332\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.4016\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4121\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFollicle stimulating hormone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.7307\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.8141\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4633\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLuteinizing hormone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.3501\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7230\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4616\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eE2 on HCG day\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.0053*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.9040\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.7684\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndometrial\u0026nbsp;Thickness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.0046*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.0001*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.2080\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMⅡ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.9455\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.9444\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.0546\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2PN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.1041\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.9068\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.1021\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOocyte Number\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.7510\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.8897\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.6324\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2PN/MⅡ\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.5038\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.7772\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.0148*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eStimulation Protocol\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAgonist Protocol\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.3692\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4961\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEndometrial Type\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.8531\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.5324\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4914\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.7138\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.0887\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.4614\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSecondary Infertility\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.0816\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.2445\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.6809\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFertilization\u0026nbsp;Method\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICSI\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.2365\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.5069\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.8492\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEmbryo Features\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBlastomere Number\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.5422\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNU\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFragment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.1585\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEquality\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.5399\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEmbryo Scores\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eP1\u0026thinsp;+\u0026thinsp;P2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001*\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.1344\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eP1\u0026thinsp;\u0026times;\u0026thinsp;P2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.2040\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.007*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003ctfoot\u003e \u003ctr\u003e\u003ctd colspan=\"4\"\u003e*P\u0026thinsp;\u0026lt;\u0026thinsp;0.05; \u003csup\u003ea\u003c/sup\u003eNU means this feature was not used in the corresponding level.\u003c/td\u003e\u003c/tr\u003e \u003c/tfoot\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \n\u003ch2\u003eFeature Importance Of The Hierarchical Model\u003c/h2\u003e\n \u003cp\u003eIn the XGBoost algorithm, the feature importance means the number of times that a feature is used to split the data across all trees. A higher feature importance score represents greater value for prediction. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the feature importance in the hierarchical model for a SET pregnancy, a DET pregnancy, and DET twin risk. Some features are not shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e because the corresponding importance was zero, which means these features were not used for prediction.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFor SET, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, the luteinizing hormone (LH) level and follicle-stimulating hormone (FSH) level were not statistically significant, yet they were the third- and sixth-important features for the first-level model. The same phenomenon was observed for FSH, LH, and antral follicle count (AFC) in DET pregnancy and DET twin risk prediction. Although P1\u0026thinsp;\u0026times;\u0026thinsp;P2 was significantly correlated with DET twin risk, it was hardly used by either level model.\u003c/p\u003e \n\u003ch2\u003eModel Validation Results\u003c/h2\u003e\n \u003cp\u003eThe algorithm was repeated 30 times to eliminate the interference of random factors, and averaged AUCs of 0.7945, 0.8385, and 0.7229 were achieved for SET pregnancy, DET pregnancy, and DET twin risk, respectively. The ROC curve in one single run is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eTo validate the effectiveness of the developed embryo selection strategy, the consistency between the predicted chance and the observed actual outcomes was analyzed, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e. The trend of predictive and observed rates both in pregnancy and twin risk was basically identical, although with a slight elevation in predictive rates.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eTo validate the prediction performance among XGBoost and other algorithms such as logistic regression (LR) and classification and regression tree (CART), we also performed a non-parametric multiple comparison test using Dunn\u0026rsquo;s procedure [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e], with a p-value correction using the False Discovery Rate method [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. The results are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e, where the significant ones (p\u0026thinsp;\u0026lt;\u0026thinsp;0.05) are marked in asterisk. In general, XGBoost outperformed the other two algorithms with obvious prediction power in SET pregnancy prediction and DET twin risk prediction and similar performance in DET pregnancy prediction task.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e "},{"header":"Discussion","content":" \u003cp\u003eOne of the most overwhelming challenges in contemporary assisted reproductive technology (ART) is how to narrow the gap in perinatal and neonatal outcomes between spontaneous pregnancy and assisted pregnancy, usually caused by multiple-embryo transfer and implantation [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. In recent decades, SET has been advocated in IVF to prevent multiple pregnancies while led to the concerns of decreased IVF success [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. Therefore, precise embryo selection for SET and twin risk warning for DET are particularly necessary. In this paper, a novel hierarchical model was constructed and validated to optimize embryo selection strategies and successfully predict pregnancy for both SET and DET, as well as predict the twin risk of DET for each individual. Subsequently, we validated our model on 2961 patients, and the results showed that our model had achieved an acceptable performance on embryo selection and twin risk prediction for each individual, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e \u003cp\u003eIt is generally accepted that embryos with similar morphology present variable implantation probability, depending on other assessed features such as patient characteristics and cycle demographics. Many features, including age, FSH level, anti-Mullerian hormone (AMH) and embryo quality, have been reported as independent impact factors on oocyte variability and embryo implantation potential [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e, \u003cspan additionalcitationids=\"CR24 CR25\" citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. Machine learning is considered a powerful mathematical tool for correlation analysis when huge data is involved; therefore, AI has been introduced in embryo variability prediction in many articles [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. By increasing the information of the input features, the predictive power of the proposed model may be improved. Similarly, 19 features from the initial data sets were considered in the current study to construct the predictive power in our model. It is noteworthy that although previous models may have helped predict the implantation potential of a specific embryo, they did not offer a reasonable and optimal guidance to the embryo selection determination in clinical practice.\u003c/p\u003e \u003cp\u003eMinaretzis \u003cem\u003eet al\u003c/em\u003e. [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e] once presented an embryo selection strategy of transferring one additional good-quality embryo for each five years of incremental increase in maternal age to improve IVF outcome by multivariate analysis of factors predictive of successful live birth. Because maternal age was the only influencing factor to be considered, the recommended strategy was not so accurate or comprehensive. Kaufmann \u003cem\u003eet al\u003c/em\u003e. [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e] reported a neural networks predicting model in IVF, where four input parameters were included and the overall accuracy was 59%. Uyar \u003cem\u003eet al\u003c/em\u003e. [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e] proposed a Support Vector Machine (SVM) method in embryo implantation prediction in terms of Area Under ROC curve (0.712\u0026thinsp;\u0026plusmn;\u0026thinsp;0.032), when 12 features were included.\u003c/p\u003e \u003cp\u003eVaegter \u003cem\u003eet al.\u003c/em\u003e [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] also constructed a predictive model for an embryo transfer strategy, in which only one embryo was transferred if the predictive risk of twin implantation was above 15%, using the two highest scored embryos. While validating this predictive model, the actual twin rate was 3.8%, which was far lower than the expected 15% setting, accompanied by a decreased live birth rate. Unlike previous studies, a novel strategy in embryo selection based on an accurate embryo potential prediction and twin risk assessment was developed in our model. The model not only guides a determination of the number of embryos for transfer and the specific embryo selection, but also presents a relatively accurate prediction of the pregnancy rate and twin risk of the corresponding selection scheme.\u003c/p\u003e \u003cp\u003eBecause SET was not arbitrarily implemented in all IVF patients, twin pregnancy was inevitable. However, the acceptable twin rate threshold varied among different countries, even among different IVF centers. The greatest strength of our model was that the embryo selection strategy we developed varied correspondingly to patients\u0026rsquo; characteristics and embryo morphology parameters as long as different twin rate thresholds were set. Therefore, the selection strategy model is applicable to any IVF center in any country. In such a situation, embryologists can input their accepted twin rate setting on the model to generate their guided embryo selection strategies and present a predictable pregnancy possibility and twin rate assessment.\u003c/p\u003e \u003cp\u003eMore important, the predictive twin risk indicated that the transferred two embryos were neither a simplified embryo implantation nor an implantation of two independent samples. This principle was previously discussed in an embryo-uterus modeling framework [\u003cspan additionalcitationids=\"CR33\" citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. A higher twin rate than expected would be achieved if the implantation chances of the embryos transferred together were completely independent of one another [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Considering the variability of confounding factors, a two-level algorithm was introduced in our model for DET prediction to achieve a satisfying predictive model. Furthermore, unlike previous researches, which only considered significant influencing factors in model construction [\u003cspan additionalcitationids=\"CR36\" citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e], concomitant investigation in our DET model provided a novel insight: that even if one variable were not statistically significant, it might still be important for machine learning models to predict final outcomes.\u003c/p\u003e \u003cp\u003eTo minimize twin risk, some researchers also constructed a predictable model and validated it in subsequent IVF cycles, and the results showed a significantly reduced twin rate (from 25.2\u0026ndash;3.8%) [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. However, the proportion of SETs was greatly increased (11.3\u0026ndash;75.5%), and surplus embryos would be preserved for future use, resulting in a reduced live birth rate in fresh cycle (29.0\u0026ndash;25.1%). Even though the cumulative live birth rate (CLBR) was not affected, patients had to pay more fees and spend more time for a successful pregnancy in subsequent frozen-thawed cycles. Luke \u003cem\u003eet al\u003c/em\u003e. [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e] also reported a similar conclusion of comparative CLBR and decreased multiple births in SETs over two cycles, compared to DET in one cycle. In our algorithm, conversely, the pregnancy rate and twin risk were assessed and predicted simultaneously in the fresh cycle, and further validation showed that it effectively reduced twin risk without compromising clinical pregnancy in the fresh cycle.\u003c/p\u003e \u003cp\u003eThe recommended embryo selection strategy in our model provides decision support to embryologists with higher accuracy and efficiency. For a large proportion of IVF patients with suboptimal prognosis, which plan to choose was a dilemma to embryologists, because prediction judgment was based on their clinical experience instead of on the analysis of thousands of embryos and patient records prior to each embryo transfer [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. Besides, it may also act as a counseling tool for clinicians to evaluate the chance of pregnancy before the transfer procedure.\u003c/p\u003e \u003cp\u003ePrevious research to establish similar predictive models were problematic due to the limited number of involved features or dramatic distinction between the predicted value and the actual situation [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. The model in the current study guides a determination of the number of embryos for transfer and the specific embryo selection, based on the analysis of a large number of features. In addition, the predicted pregnancy rate and twin risk of the corresponding selection scheme were relatively more accurate. More significantly, our model provides a flexible strategy, with individualized embryo selection for any given patient and varied operations corresponding with any setting acceptable twin rate threshold.\u003c/p\u003e \u003cp\u003eOne shortcoming of our predictive model was that the predicted mean value was slightly elevated compared to the actual observed rate for both pregnancy and twin rates in validation, although a modest discrimination was also reported in the previous prediction model in ART [\u003cspan additionalcitationids=\"CR42\" citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]. The model should be adjusted and improved to make the predictive value more closely agree with the actual virtue in the future verification. Besides, the model was developed and validated using data from a single center. As future work, we will need to be much more rigorous with additional data sets demonstrating the predictive value, using the same parameters, as well as applying them in different centers.\u003c/p\u003e "},{"header":"Conclusions","content":" \u003cp\u003eIn our study, we constructed and validated an individualized embryo selection strategy and pregnancy prediction model developed by stacking machine learning. This prediction model could provide an accurate and individualized embryo selection strategy for any given patient as well as in any twin risk threshold setting and balance a delicate correlation between clinical pregnancy and twin risk rate; it therefore promises a better IVF outcome without compromising pregnancy success and controlled twin risk.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eIn vitro fertilization (IVF)\u003c/p\u003e \u003cp\u003eSingle embryo transfer (SET)\u003c/p\u003e \u003cp\u003eDouble embryo transfer (DET)\u003c/p\u003e \u003cp\u003eArtificial intelligence (AI)\u003c/p\u003e \u003cp\u003eControlled ovarian hyperstimulation (COH)\u003c/p\u003e \u003cp\u003eGonadotropin-releasing hormone (GnRH)\u003c/p\u003e \u003cp\u003eHuman chorionic gonadotropin (hCG)\u003c/p\u003e \u003cp\u003eArea under the curve (AUC)\u003c/p\u003e \u003cp\u003eReceiver operating characteristic (ROC)\u003c/p\u003e \u003cp\u003eFollicle-stimulating hormone (FSH)\u003c/p\u003e \u003cp\u003eLuteinizing hormone (LH)\u003c/p\u003e \u003cp\u003eAntral follicle count (AFC)\u003c/p\u003e \u003cp\u003eLogistic regression (LR)\u003c/p\u003e \u003cp\u003eClassification and regression tree (CART)\u003c/p\u003e \u003cp\u003eAssisted reproductive technology (ART)\u003c/p\u003e \u003cp\u003eAnti-Mullerian hormone (AMH)\u003c/p\u003e \u003cp\u003eCumulative live birth rate (CLBR)\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the medical ethics committee of Tongji Medical College of Huazhong University of Science and Technology and written informed consent was obtained from all patients before they were included. All methods were performed in accordance with the relevant guidelines and regulations.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAvailability of data and materials\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll data generated or analysed during this study are included in this published article.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by research grants from the National Key Research and Development Project (grant number: 2018YFC1002103) and the Chinese Medical Association (grant number: 16020520668) as well as the Natural Science Foundation of Hubei Province (grant number:2017CFB752).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors' contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eQ.X., M.W., B.Z., Z.L., and B.H.conducted the experiment; Q.Y., L.Y., and S.L. analyzed the data, Q.X. and Q.Y. composed the manuscript, and L.Z. and L.J. were responsible for the concept and study design. All authors contributed to the interpretation, discussion and editing of the manuscript. All authors approved the last version.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e Not applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSunderam S, Kissin DM, Crawford SB, Folger SG, Jamieson DJ, Warner L, et al. Assisted reproductive technology surveillance-United States, 2014. MMWR Surveill Summ. 2017;66(6):1.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChambers GM, Ledger W. The economic implications of multiple pregnancy following ART. Semin Fetal Neonatal Med. 2014;19(4):254\u0026ndash;61.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMeldrum DR, Adashi EY, Garzo VG, Gleicher N, Parinaud J, Pinborg A, et al. Prevention of in vitro fertilization twins should focus on maximizing single embryo transfer versus twins are an acceptable complication of in vitro fertilization. Fertil Steril. 2018;109(2):223\u0026ndash;29.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBergh T, Ericson A, Hillensj\u0026ouml; T, Nygren KG, Wennerholm UB. Deliveries and children born after in-vitro fertilisation in Sweden 1982-95: a retrospective cohort study. Lancet. 1999;354(9190):1579\u0026ndash;85.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Loendersloot L, Van Wely M, Limpens J, Bossuyt PM, Repping S, van der Veen F. Predictive factors in in vitro fertilization (IVF): A systematic review and meta-analysis. Hum Reprod Update. 2010;16(6):577\u0026ndash;89.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRienzi L, Vajta G, Ubaldi F. Predictive value of oocyte morphology in human IVF: A systematic review of the literature. Hum Reprod Update. 2010;17(1):34\u0026ndash;45.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eIliodromiti S, Kelsey TW, Wu O, Anderson RA, Nelson SM. The predictive accuracy of Anti-M\u0026uuml;llerian hormone for live birth after assisted conception: A systematic review and meta-analysis of the literature. Hum Reprod Update. 2014;20(4):560\u0026ndash;70.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFang T, Su Z, Wang L, Yuan P, Li R, Ouyang N, et al. Predictive value of age-specific FSH levels for IVF-ET outcome in women with normal ovarian function. Reprod Biol Endocrinol. 2015;13(1):63.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCorani G, Magli C, Giusti A, Gianaroli L, Gambardella LM. A Bayesian network model for predicting pregnancy after in vitro fertilization. Comput Biol Med. 2013;43(11):1783\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDeb\u0026oacute;n A, Molina I, Cabrera S. Mathematical methodology to obtain and compare different embryo scores. Math Comput Model. 2013;57(5\u0026ndash;6):1380\u0026ndash;94.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuerif F, Le Gouge A, Giraudeau B, Poindron J, Bidault R, Gasnier O, et al. Limited value of morphological assessment at days 1 and 2 to predict blastocyst development potential: A prospective study based on 4042 embryos. Hum Reprod. 2007;22(7):1973\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMorales DA, Bengoetxea E, Larra\u0026ntilde;aga P. Selection of human embryos for transfer by Bayesian classifiers. Comput Biol Med. 2008;38(11\u0026ndash;12):1177\u0026ndash;86.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoberts SA. Models for assisted conception data with embryo-specific covariates. Stat Med. 2007;26(1):156\u0026ndash;70.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu L, Xi Q, Zhang H, Li Y, Ai J, Jin L. Blastocyst culture and cryopreservation to optimize clinical outcomes of warming cycles. Reprod Biomed Online. 2013;27(2):154\u0026ndash;60.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu L, Xi Q, Nie R, Chen W, Zhang H, Li Y. Rescue intracytoplasmic sperm injection: A prospective randomized study. J Reprod Med. 2011;56(9\u0026ndash;10):410\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVaegter KK, Berglund L, Tilly J, Hadziosmanovic N, Brodin T, Holte J. Construction and validation of a prediction model to minimize twin rates at preserved high live birth rates after IVF. Reprod Biomed Online. 2019;38(1):22\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen T, Guestrin C. XGBoost: A scalable tree boosting system. Proc Int\u0026rsquo;l Conf on Knowledge Discovery and Data Mining 2016 Aug; San Francisco, CA.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDunn OJ. Multiple comparisons using rank sums. Technometrics. 1964;6:214\u0026ndash;52.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBenjamini Y, Hochberg Y. Controlling the false discovery rate: A practical and powerful approach to multiple testing. J R Stat Soc Series B Stat Methodol. 1995;57:289\u0026ndash;300.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHelmerhorst FM, Perquin DA, Donker D, Keirse MJ. Perinatal outcome of singletons and twins after assisted conception: a systematic review of controlled studies. BMJ. 2004;328(7434):261.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDrakopoulos P, Blockeel C, Stoop D, Camus M, de Vos M, Tournaye H, et al. Conventional ovarian stimulation and single embryo transfer for IVF/ICSI. How many oocytes do we need to maximize cumulative live birth rates after utilization of all fresh and frozen embryos? Hum Reprod. 2016;31(2):370\u0026ndash;76.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Voorhis B, Mejia RB. Single-embryo transfer point-it is the way forward. Fertil Steril. 2017;108(5):757.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCai Q, Wan F, Appleby D, Hu L, Zhang H. Quality of embryos transferred and progesterone levels are the most important predictors of live birth after fresh embryo transfer: A retrospective cohort study. J Assist Reprod Genet. 2014;31(2):185\u0026ndash;94.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee TH, Chen CD, Tsai YY, Chang LJ, Ho HN, Yang YS. Embryo quality is more important for younger women whereas age is more important for older women with regard to in vitro fertilization outcome and multiple pregnancy. Fertil Steril. 2006;86(1):64\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLeijdekkers J, Eijkemans M, Van Tilborg T, Oudshoorn SC, McLernon DJ, Bhattacharya S, et al. Predicting the cumulative chance of live birth over multiple complete cycles of in vitro fertilization: An external validation study. Hum Reprod. 2018;33(9):1684\u0026ndash;95.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYanez LZ, Han J, Behr BB, Pera RAR, Camarillo DB. Human oocyte developmental potential is predicted by mechanical properties within hours after fertilization. Nat Commun. 2016;7:10809.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVaegter KK, Lakic TG, Olovsson M, Berglund L, Brodin T, Holte J. Which factors are most predictive for live birth after in vitro fertilization and intracytoplasmic sperm injection (IVF/ICSI) treatments? Analysis of 100 prospectively recorded variables in 8,400 IVF/ICSI single-embryo transfers. Fertil Steril. 2017;107(3):641\u0026ndash;48. e2.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSiristatidis C, Pouliakis A, Chrelias C, Kassanos D. Artificial intelligence in IVF: a need. Syst Biol Reprod Med. 2011;57(4):179\u0026ndash;85.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMinaretzis D, Harris D, Alper MM, Mortola JF, Berger MJ, Power D. Multivariate analysis of factors predictive of successful live births in in vitro fertilization (IVF) suggests strategies to improve IVF outcome. J Assist Reprod Genet. 1998;15(6):365\u0026ndash;71.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKaufmann SJ, Eastaugh JL, Snowden S, Smye SW, Sharma V. The application of neural networks in predicting the outcome of in-vitro fertilization. Hum Reprod. 1997;12:1454\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUyar A, Bener A, Ciray H, Bahceci M. A frequency based encoding technique for transformation of categorical variables in mixed IVF dataset. Conf Proc IEEE Eng Med Biol Soc. 2009; 2009: 6214\u0026ndash;6217.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHunault CC, Eijkemans MJ, Pieters MH, te Velde ER, Habbema JD, Fauser BC, et al. A prediction model for selecting patients undergoing in vitro fertilization for elective single embryo transfer. Fertil Steril. 2002;77(4):725\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoberts S, Hirst W, Brison D, Vail A, towardSET collaboration. Embryo and uterine influences on IVF outcomes: An analysis of a UK multi-centre cohort. Hum Reprod. 2010;25(11):2792 \u0026ndash; 802.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoberts SA, McGowan L, Mark Hirst W, Vail A, Rutherford A, Lieberman BA, et al. Reducing the incidence of twins from IVF treatments: Predictive modelling from a retrospective cohort. Hum Reprod. 2010;26(3):569\u0026ndash;75.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLuke B, Brown MB, Wantman E, Stern JE, Baker VL, Widra E, et al. A prediction model for live birth and multiple births within the first three cycles of assisted reproductive technology. Fertil Steril. 2014;102(3):744\u0026ndash;52.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRongieres C, Colella C, Lehert P. To what extent does Anti-Mullerian hormone contribute to a better prediction of live birth after IVF? J Assist Reprod Genet. 2015;32(1):37\u0026ndash;43.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVogiatzi P, Pouliakis A. An artificial neural network for the prediction of assisted reproduction outcome. J Assist Reprod Genet. 2019;36:1441\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLuke B, Brown MB, Wantman E, Stern JE, Baker VL, Widra E, et al. Application of a validated prediction model for in vitro fertilization: Comparison of live birth rates and multiple birth rates with 1 embryo transferred over 2 cycles vs 2 embryos in 1 cycle. Am J Obstet Gynecol. 2015;212(5):676.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Der Steeg J, Steures P, Eijkemans M, Habbema JD, Bossuyt PM, Hompes PG, et al. Do clinical prediction models improve concordance of treatment decisions in reproductive medicine? BJOG. 2006;113(7):825\u0026ndash;31.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWiegerinck MA, Bongers MY, Mol BW, Heineman MJ. How concordant are the estimated rates of natural conception and in-vitro fertilization/embryo transfer success? Hum Reprod. 1999;14(3):689\u0026ndash;93.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChoi B, Bosch E, Lannon BM, Leveille MC, Wong WH, Leader A, et al. Personalized prediction of first-cycle in vitro fertilization success. Fertil Steril. 2013;99(7):1905\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLeushuis E, van der Steeg JW, Steures P, Bossuyt PM, Eijkemans MJ, van der Veen F, et al. Prediction models in reproductive medicine: A critical appraisal. Hum Reprod Update. 2009;15(5):537\u0026ndash;52.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVan Loendersloot L, Repping S, Bossuyt PM, van der Veen F, van Wely M. Prediction models in in vitro fertilization; where are we? A mini review. J Adv Res. 2014;5(3):295\u0026ndash;301.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"reproductive-biology-and-endocrinology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rbej","sideBox":"Learn more about [Reproductive Biology and Endocrinology](http://rbej.biomedcentral.com)","snPcode":"12958","submissionUrl":"https://submission.nature.com/new-submission/12958/3","title":"Reproductive Biology and Endocrinology","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Artificial intelligence, embryo selection, machine learning, in vitro fertilization, in vitro fertilization prediction","lastPublishedDoi":"10.21203/rs.3.rs-140383/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-140383/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground: \u003c/strong\u003eTo minimize the rate of in vitro fertilization (IVF)- associated multiple-embryo gestation, significant efforts have been made. Previous studies related to machine learning in IVF mainly focused on selecting the top-quality embryos to improve outcomes, however, in patients with sub-optimal prognosis or with medium- or inferior-quality embryos, the selection between SET and DET could be perplexing. \u003c/p\u003e\u003cp\u003e\u003cstrong\u003eMethods: \u003c/strong\u003eThis was an application study including 7887 patients with 8585 embryos treated during 2016 to 2018, in Tongji Hospital, Wuhan, China. A hierarchical model was established using the machine learning system XGBoost, to learn embryo implantation potential and the impact of double embryos transfer (DET) simultaneously. The performance of the model was evaluated with the AUC of the ROC curve. Multiple regression analyses were also conducted on the 19 selected features to demonstrate the differences between feature importance for prediction and statistical relationship with outcomes.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eResults: \u003c/strong\u003eFor a single embryo transfer (SET) pregnancy, the following variables remained significant: age, attempts at IVF, estradiol level on hCG day, and endometrial thickness. For DET pregnancy, age, attempts at IVF, endometrial thickness, and the newly added P1+P2 remained significant. For DET twin risk, age, attempts at IVF, 2PN/ MII, and P1×P2 remained significant. The algorithm was repeated 30 times, and averaged AUC of 0.7945, 0.8385, and 0.7229 were achieved for SET pregnancy, DET pregnancy, and DET twin risk, respectively. The trend of predictive and observed rates both in pregnancy and twin risk was basically identical. XGBoost outperformed the other two algorithms: logistic regression and classification and regression tree. \u003c/p\u003e\u003cp\u003e\u003cstrong\u003eConclusion\u003c/strong\u003e: Artificial intelligence based on determinant-weighting analysis could offer an individualized embryo selection strategy for any given patient, and predict clinical pregnancy rate and twin risk, therefore optimizing clinical outcomes.\u003c/p\u003e","manuscriptTitle":"Individualized Embryo Selection Strategy Developed by Stacking Machine Learning Model for Better In Vitro Fertilization Outcomes: An Application Study.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-01-11 15:42:02","doi":"10.21203/rs.3.rs-140383/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Minor revision","date":"2021-02-01T00:00:00+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2021-01-25T00:00:00+00:00","index":1,"fulltext":"Recommendation: Reviewer's comments unavailable due to the journal's policy.\n"},{"type":"reviewerAgreed","content":"","date":"2021-01-10T00:00:00+00:00","index":1,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2021-01-03T00:00:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"","date":"2021-01-01T00:00:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2021-01-01T00:00:00+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2020-12-31T23:00:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2020-12-31T23:00:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"reproductive-biology-and-endocrinology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"rbej","sideBox":"Learn more about [Reproductive Biology and Endocrinology](http://rbej.biomedcentral.com)","snPcode":"12958","submissionUrl":"https://submission.nature.com/new-submission/12958/3","title":"Reproductive Biology and Endocrinology","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"5a255557-cbd3-4fa3-95cf-a3a6c064ad1d","owner":[],"postedDate":"January 11th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":1737087,"name":"Endocrinology \u0026 Metabolism"}],"tags":[],"updatedAt":"2021-08-18T19:13:29+00:00","versionOfRecord":{"articleIdentity":"rs-140383","link":"https://doi.org/10.1186/s12958-021-00734-z","journal":{"identity":"reproductive-biology-and-endocrinology","isVorOnly":false,"title":"Reproductive Biology and Endocrinology"},"publishedOn":"2021-04-05 19:02:19","publishedOnDateReadable":"April 5th, 2021"},"versionCreatedAt":"2021-01-11 15:42:02","video":"","vorDoi":"10.1186/s12958-021-00734-z","vorDoiUrl":"https://doi.org/10.1186/s12958-021-00734-z","workflowStages":[]},"version":"v1","identity":"rs-140383","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-140383","identity":"rs-140383","version":["v1"]},"buildId":"rHA-KDH7Qsr4HCuvH75dn","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}