logo logo
Multifactor Prediction of Embryo Transfer Outcomes Based on a Machine Learning Algorithm. Liu Ran,Bai Shun,Jiang Xiaohua,Luo Lihua,Tong Xianhong,Zheng Shengxia,Wang Ying,Xu Bo Frontiers in endocrinology fertilization-embryo transfer (IVF-ET) technology make it possible for infertile couples to conceive a baby successfully. Nevertheless, IVF-ET does not guarantee success. Frozen embryo transfer (FET) is an important supplement to IVF-ET. Many factors are correlated with the outcome of FET which is unpredictable. Machine learning is a field of study that predict various outcomes by defining data attributes and using relevant data and calculation algorithms. Machine learning algorithm has been widely used in clinical research. The present study focuses on making predictions of early pregnancy outcomes in FET through clinical characters, including age, body mass index (BMI), endometrial thickness (EMT) on the day of progesterone treatment, good-quality embryo rate (GQR), and type of infertility (primary or secondary), serum estradiol level (E2) on the day of embryo transfer, and serum progesterone level (P) on the day of embryo transfer. We applied four representative machine learning algorithms, including logistic regression (LR), conditional inference tree, random forest (RF) and support vector machine (SVM) to build prediction models and identify the predictive factors. We found no significant difference among the models in the sensitivity, specificity, positive predictive rate, negative predictive rate or accuracy in predicting the pregnancy outcome of FET. For example, the positive/negative predictive rate of the SVM (gamma = 1, cost = 100, 10-fold cross validation) is 0.56 and 0.55. This approach could provide a reference for couples considering FET. The prediction accuracy of the present study is limited, which suggests that there may be some other more effective predictors to be developed in future work. 10.3389/fendo.2021.745039
Factors affecting the outcome of frozen-thawed embryo transfer. Veleva Zdravka,Orava Mauri,Nuojua-Huttunen Sinikka,Tapanainen Juha S,Martikainen Hannu Human reproduction (Oxford, England) STUDY QUESTION:Which clinical and laboratory factors affect live birth rate (LBR) after frozen-thawed embryo transfer (FET)? SUMMARY ANSWER:Top quality embryo characteristics, endometrial preparation protocol, number of embryos transferred and BMI affected independently the LBR in FET. WHAT IS KNOWN ALREADY:FET is an important part of present-day IVF/ICSI treatment. There is limited understanding of the factors affecting success rates after FET. STUDY DESIGN, SIZE, DURATION:This is a two-centre retrospective cohort study. Analysis was carried out on 1972 consecutive FET cycles in 1998-2007, with embryos frozen on Day 2. The primary outcome was LBR per cycle. PARTICIPANTS/MATERIALS, SETTING, METHODS:We assessed the independent effect on LBR of the following variables: female age, female age at embryo freezing, BMI, diagnosis, primary versus secondary infertility, fertilization by IVF versus ICSI, pregnancy in the fresh cycle, type (spontaneous, spontaneous with luteal progesterone and estrogen/progesterone substitution) and rank of the FET cycle, as well as number and presence (yes versus no) of top quality embryo(s) at freezing, thawing and transfer, damaged thawed embryos and overnight culture. MAIN RESULTS AND THE ROLE OF CHANCE:In 78% of the cycles with top quality embryos frozen (n = 1319), at least one embryo still had high-quality morphology after thawing. Top quality embryo morphology observed at any stage of culture improved the outcome even if high-quality characteristics disappeared before transfer. LBRs after the transfer of a top quality embryo were similar in the FET (24.9%) and fresh cycles of the same period (21.9%). The chance of live birth increased significantly if ≥1 top quality embryo was present at freezing (odds ratio (OR) 1.85, 95% confidence interval (CI) 1.10-3.14), at thawing (OR 1.93, CI 1.20-3.11) or at transfer (OR 3.41, CI 2.12-5.48). Compared with spontaneous cycles with luteal support, purely spontaneous cycles (OR 0.58, CI 0.40-0.84) and hormonally substituted FET (OR 0.47, CI 0.32-0.69) diminished the odds of pregnancy. BMI (OR 0.96, CI 0.92-0.99) and transfer of two embryos versus one (OR 1.45, CI 1.08-1.94) were other factors that improved LBR after FET. LIMITATIONS, REASONS FOR CAUTION:The sample sizes available in some subanalyses were small, limiting the power of the study. WIDER IMPLICATIONS OF THE FINDINGS:The presence of ≥1 top quality embryo at any step of the freezing and thawing process increases the chance of pregnancy. The data do not support the freezing of all embryos for transfer in order to improve the outcome. A top quality embryo transferred in FET may even have the same potential as in a fresh cycle. On the contrary, LBR in the group with no top quality embryos frozen was quite low (10.4%), raising the question of whether a re-evaluation of freezing criteria is necessary to avoid costly treatments with a low success rate. 10.1093/humrep/det251