Clinical validation of an automatic classification algorithm applied on cleavage stage embryos: analysis for blastulation, euploidy, implantation, and live-birth potential.

Is a commercially available embryo assessment algorithm for early embryo evaluation based on the automatic annotation of morphokinetic timings a useful tool for embryo selection in IVF cycles? The classification provided by the algorithm was shown to be significantly predictive, especially when combined with conventional morphological evaluation, for development to blastocyst, implantation, and live birth, but not for euploidy. The gold standard for embryo selection is still morphological evaluation conducted by embryologists. Since the introduction of time-lapse technology to embryo culture, many algorithms for embryo selection have been developed based on embryo morphokinetics, providing complementary information to morphological evaluation. However, manual annotations of developmental events and application of algorithms can be time-consuming and subjective processes. The introduction of automation to morphokinetic annotations is a promising approach that can potentially reduce subjectivity in the embryo selection process and improve the workflow in IVF laboratories. This observational, retrospective cohort study was performed in a single IVF clinic between 2018 and 2021 and included 3736 embryos from oocyte donation cycles (423 cycles) and 1291 embryos from autologous cycles with preimplantation genetic testing for aneuploidies (PGT-A, 185 cycles). Embryos were classified on Day 3 with a score from 1 (best) to 5 (worst) by the automatic embryo assessment algorithm. The performance of the embryo classification model for blastocyst development, implantation, live birth, and euploidy prediction was assessed. All embryos were monitored by a time-lapse system with an automatic cell-tracking and embryo assessment software during culture. The embryo assessment algorithm was applied on Day 3, resulting in embryo classification from 1 to 5 (from highest to lowest developmental potential) depending on four parameters: P2 (t3-t2), P3 (t4-t3), oocyte age, and number of cells. There were 959 embryos selected for transfer on Day 5 or 6 based on conventional morphological evaluation. The blastocyst development, implantation, live birth, and euploidy rates (for embryos subjected to PGT-A) were compared between the different scores. The correlation of the algorithm scoring with the occurrence of those outcomes was quantified by generalized estimating equations (GEEs). Finally, the performance of the GEE model using the embryo assessment algorithm as the predictor was compared to that using conventional morphological evaluation, as well as to a model using a combination of both classification systems. The blastocyst rate was higher with lower the scores generated by the embryo assessment algorithm. A GEE model confirmed the positive association between lower embryo score and higher odds of blastulation (odds ratio (OR) (1 vs 5 score) = 15.849; P < 0.001). This association was consistent in both oocyte donation and autologous embryos subjected to PGT-A. The automatic embryo classification results were also statistically associated with implantation and live birth. The OR of Score 1 vs 5 was 2.920 (95% CI 1.440-5.925; P = 0.003; E = 2.81) for implantation and 3.317 (95% CI 1.615-6.814; P = 0.001; E = 3.04) for live birth. However, this association was not found in embryos subjected to PGT-A. The highest performance was achieved when combining the automatic embryo scoring and traditional morphological classification (AUC for implantation potential = 0.629; AUC for live-birth potential = 0.636). Again, no association was found between the embryo classification and euploidy status in embryos subjected to PGT-A (OR (1 vs 5) = 0.755 (95% CI 0.255-0.981); P = 0.489; E = 1.57). The retrospective nature of this study may be a reason for caution, although the large sample size reinforced the ability of the model for embryo selection. Time-lapse technology with automated embryo assessment can be used together with conventional morphological evaluation to increase the accuracy of embryo selection process and improve the success rates of assisted reproduction cycles. To our knowledge, this is the largest embryo dataset analysed with this embryo assessment algorithm. This research was supported by Agencia Valenciana de Innovació and European Social Fund (ACIF/2019/264 and CIBEFP/2021/13). In the last 5 years, M.M. received speaker fees from Vitrolife, Merck, Ferring, Gideon Richter, Angelini, and Theramex, and B.A.-R. received speaker fees from Merck. The remaining authors have no competing interests to declare. N/A.

Valera MA ，Aparicio-Ruiz B ，Pérez-Albalá S ，Romany L ，Remohí J ，Meseguer M ... -  《-》

The higher the score, the better the clinical outcome: retrospective evaluation of automatic embryo grading as a support tool for embryo selection in IVF laboratories.

Is the automatic embryo grading function of specific time-lapse systems clinically useful as a decision support tool for IVF laboratories? Blastocyst grading according to the automatic scoring system is directly associated with the likelihood of implantation and live birth, at least in treatments without preimplantation genetic testing for aneuploidy (PGT-A). Several embryo selection algorithms have been described since the introduction of time-lapse technology in IVF laboratories, but no one algorithm has yet been sufficiently consolidated for universal use. Multicentric models based on automated grading systems offer promise for standardization of embryo selection. A retrospective cohort study was performed including 1678 patients who underwent IVF treatments between 2018 and 2020 and whose embryos (n = 12 468) were cultured in time-lapse systems. After obtaining the required parameters (division time to 2, 3, 4 and 5 cells; time of blastocyst formation; inner cell mass quality; and trophectoderm quality), the automatic embryo score was calculated using the software included in the appropriate workstation. First, embryo score was compared with conventional morphological quality and the subsequent clinical outcomes of 1952 single blastocyst transfers. Second, we quantified the contribution of the automatic embryo score and conventional morphological grade to implantation and live birth outcome with multivariate logistic regression analysis in different patient populations. A higher embryo score was associated with a better clinical outcome of IVF treatment. The mean of the automatic embryo score varied significantly (P < 0.001) among embryos with different morphological categories, between euploid and aneuploid embryos, between embryos resulting in positive versus negative pregnancy, between implanted and non-implanted embryos, and between embryos resulting in positive and negative live birth. Embryo score was related to the odds of implantation and live birth in the oocyte donation program (odds ratio (OR)=1.29; 95% CI [1.19-1.39]; P < 0.001 for implantation and OR = 1.26; 95% CI [1.16-1.36]; P < 0.001 for live birth) and in conventional treatments with autologous oocytes (OR = 1.38; 95% CI [1.24-1.54]; P < 0.001 for implantation and OR = 1.47; 95% CI [1.30-1.65]; P < 0.001 for live birth). There was no significant association of embryo score with implantation or live birth in treatments involving PGT-A. This study is limited by its retrospective nature. Further prospective randomized trials are required to confirm the clinical impact of these findings. The single-center design should be taken into account when considering the universal application of the model. Evidence of the clinical efficiency of automated embryo scoring for ranking embryos with different morphological grade and potential in order to achieve higher implantation and live birth rates may make it a decision support tool for embryologists when selecting blastocysts for embryo transfer. This research has been funded by a grant from the Ministry of Science, Innovation and Universities FIS (PI21/00283) awarded to M.M. There are no competing interests to declare. N/A.

Bori L ，Meseguer F ，Valera MA ，Galan A ，Remohi J ，Meseguer M ... -  《-》

Development of an artificial intelligence model for predicting the likelihood of human embryo euploidy based on blastocyst images from multiple imaging systems during IVF.

Can an artificial intelligence (AI) model predict human embryo ploidy status using static images captured by optical light microscopy? Results demonstrated predictive accuracy for embryo euploidy and showed a significant correlation between AI score and euploidy rate, based on assessment of images of blastocysts at Day 5 after IVF. Euploid embryos displaying the normal human chromosomal complement of 46 chromosomes are preferentially selected for transfer over aneuploid embryos (abnormal complement), as they are associated with improved clinical outcomes. Currently, evaluation of embryo genetic status is most commonly performed by preimplantation genetic testing for aneuploidy (PGT-A), which involves embryo biopsy and genetic testing. The potential for embryo damage during biopsy, and the non-uniform nature of aneuploid cells in mosaic embryos, has prompted investigation of additional, non-invasive, whole embryo methods for evaluation of embryo genetic status. A total of 15 192 blastocyst-stage embryo images with associated clinical outcomes were provided by 10 different IVF clinics in the USA, India, Spain and Malaysia. The majority of data were retrospective, with two additional prospectively collected blind datasets provided by IVF clinics using the genetics AI model in clinical practice. Of these images, a total of 5050 images of embryos on Day 5 of in vitro culture were used for the development of the AI model. These Day 5 images were provided for 2438 consecutively treated women who had undergone IVF procedures in the USA between 2011 and 2020. The remaining images were used for evaluation of performance in different settings, or otherwise excluded for not matching the inclusion criteria. The genetics AI model was trained using static 2-dimensional optical light microscope images of Day 5 blastocysts with linked genetic metadata obtained from PGT-A. The endpoint was ploidy status (euploid or aneuploid) based on PGT-A results. Predictive accuracy was determined by evaluating sensitivity (correct prediction of euploid), specificity (correct prediction of aneuploid) and overall accuracy. The Matthew correlation coefficient and receiver-operating characteristic curves and precision-recall curves (including AUC values), were also determined. Performance was also evaluated using correlation analyses and simulated cohort studies to evaluate ranking ability for euploid enrichment. Overall accuracy for the prediction of euploidy on a blind test dataset was 65.3%, with a sensitivity of 74.6%. When the blind test dataset was cleansed of poor quality and mislabeled images, overall accuracy increased to 77.4%. This performance may be relevant to clinical situations where confounding factors, such as variability in PGT-A testing, have been accounted for. There was a significant positive correlation between AI score and the proportion of euploid embryos, with very high scoring embryos (9.0-10.0) twice as likely to be euploid than the lowest-scoring embryos (0.0-2.4). When using the genetics AI model to rank embryos in a cohort, the probability of the top-ranked embryo being euploid was 82.4%, which was 26.4% more effective than using random ranking, and ∼13-19% more effective than using the Gardner score. The probability increased to 97.0% when considering the likelihood of one of the top two ranked embryos being euploid, and the probability of both top two ranked embryos being euploid was 66.4%. Additional analyses showed that the AI model generalized well to different patient demographics and could also be used for the evaluation of Day 6 embryos and for images taken using multiple time-lapse systems. Results suggested that the AI model could potentially be used to differentiate mosaic embryos based on the level of mosaicism. While the current investigation was performed using both retrospectively and prospectively collected data, it will be important to continue to evaluate real-world use of the genetics AI model. The endpoint described was euploidy based on the clinical outcome of PGT-A results only, so predictive accuracy for genetic status in utero or at birth was not evaluated. Rebiopsy studies of embryos using a range of PGT-A methods indicated a degree of variability in PGT-A results, which must be considered when interpreting the performance of the AI model. These findings collectively support the use of this genetics AI model for the evaluation of embryo ploidy status in a clinical setting. Results can be used to aid in prioritizing and enriching for embryos that are likely to be euploid for multiple clinical purposes, including selection for transfer in the absence of alternative genetic testing methods, selection for cryopreservation for future use or selection for further confirmatory PGT-A testing, as required. Life Whisperer Diagnostics is a wholly owned subsidiary of the parent company, Presagen Holdings Pty Ltd. Funding for the study was provided by Presagen with grant funding received from the South Australian Government: Research, Commercialisation, and Startup Fund (RCSF). 'In kind' support and embryology expertise to guide algorithm development were provided by Ovation Fertility. 'In kind' support in terms of computational resources provided through the Amazon Web Services (AWS) Activate Program. J.M.M.H., D.P. and M.P. are co-owners of Life Whisperer and Presagen. S.M.D., M.A.D. and T.V.N. are employees or former employees of Life Whisperer. S.M.D, J.M.M.H, M.A.D, T.V.N., D.P. and M.P. are listed as inventors of patents relating to this work, and also have stock options in the parent company Presagen. M.V. sits on the advisory board for the global distributor of the technology described in this study and also received support for attending meetings. N/A.

Diakiw SM ，Hall JMM ，VerMilyea MD ，Amin J ，Aizpurua J ，Giardini L ，Briones YG ，Lim AYX ，Dakka MA ，Nguyen TV ，Perugini D ，Perugini M ... -  《-》

Development of a generally applicable morphokinetic algorithm capable of predicting the implantation potential of embryos transferred on Day 3.

Can a generally applicable morphokinetic algorithm suitable for Day 3 transfers of time-lapse monitored embryos originating from different culture conditions and fertilization methods be developed for the purpose of supporting the embryologist's decision on which embryo to transfer back to the patient in assisted reproduction? The algorithm presented here can be used independently of culture conditions and fertilization method and provides predictive power not surpassed by other published algorithms for ranking embryos according to their blastocyst formation potential. Generally applicable algorithms have so far been developed only for predicting blastocyst formation. A number of clinics have reported validated implantation prediction algorithms, which have been developed based on clinic-specific culture conditions and clinical environment. However, a generally applicable embryo evaluation algorithm based on actual implantation outcome has not yet been reported. Retrospective evaluation of data extracted from a database of known implantation data (KID) originating from 3275 embryos transferred on Day 3 conducted in 24 clinics between 2009 and 2014. The data represented different culture conditions (reduced and ambient oxygen with various culture medium strategies) and fertilization methods (IVF, ICSI). The capability to predict blastocyst formation was evaluated on an independent set of morphokinetic data from 11 218 embryos which had been cultured to Day 5. PARTICIPANTS/MATERIALS, SETTING, The algorithm was developed by applying automated recursive partitioning to a large number of annotation types and derived equations, progressing to a five-fold cross-validation test of the complete data set and a validation test of different incubation conditions and fertilization methods. The results were expressed as receiver operating characteristics curves using the area under the curve (AUC) to establish the predictive strength of the algorithm. By applying the here developed algorithm (KIDScore), which was based on six annotations (the number of pronuclei equals 2 at the 1-cell stage, time from insemination to pronuclei fading at the 1-cell stage, time from insemination to the 2-cell stage, time from insemination to the 3-cell stage, time from insemination to the 5-cell stage and time from insemination to the 8-cell stage) and ranking the embryos in five groups, the implantation potential of the embryos was predicted with an AUC of 0.650. On Day 3 the KIDScore algorithm was capable of predicting blastocyst development with an AUC of 0.745 and blastocyst quality with an AUC of 0.679. In a comparison of blastocyst prediction including six other published algorithms and KIDScore, only KIDScore and one more algorithm surpassed an algorithm constructed on conventional Alpha/ESHRE consensus timings in terms of predictive power. Some morphological assessments were not available and consequently three of the algorithms in the comparison were not used in full and may therefore have been put at a disadvantage. Algorithms based on implantation data from Day 3 embryo transfers require adjustments to be capable of predicting the implantation potential of Day 5 embryo transfers. The current study is restricted by its retrospective nature and absence of live birth information. Prospective Randomized Controlled Trials should be used in future studies to establish the value of time-lapse technology and morphokinetic evaluation. Algorithms applicable to different culture conditions can be developed if based on large data sets of heterogeneous origin. This study was funded by Vitrolife A/S, Denmark and Vitrolife AB, Sweden. B.M.P.'s company BMP Analytics is performing consultancy for Vitrolife A/S. M.B. is employed at Vitrolife A/S. M.M.'s company ilabcomm GmbH received honorarium for consultancy from Vitrolife AB. D.K.G. received research support from Vitrolife AB.

Petersen BM ，Boel M ，Montag M ，Gardner DK ... -  《-》

Leave the past behind: women's reproductive history shows no association with blastocysts' euploidy and limited association with live birth rates after euploid embryo transfers.

Is there an association between patients' reproductive history and the mean euploidy rates per biopsied blastocysts (m-ER) or the live birth rates (LBRs) per first single vitrified-warmed euploid blastocyst transfers? Patients' reproductive history (as annotated during counselling) showed no association with the m-ER, but a lower LBR was reported after euploid blastocyst transfer in women with a history of repeated implantation failure (RIF). Several studies have investigated the association between the m-ER and (i) patients' basal characteristics, (ii) ovarian stimulation strategy and dosage, (iii) culture media and conditions, and (iv) embryo morphology and day of full blastocyst development. Conversely, the expected m-ER due to women's reproductive history (previous live births (LBs), miscarriages, failed IVF cycles and transfers, and lack of euploid blastocysts among prior cohorts of biopsied embryos) still needs investigations. Yet, this information is critical to counsel new patients about a first cycle with preimplantation genetic testing for aneuploidy (PGT-A), but even more so after former adverse outcomes to prevent treatment drop-out. This observational study included all patients undergoing a comprehensive chromosome testing (CCT)-based PGT-A cycle with at least one biopsied blastocyst in the period April 2013-December 2019 at a private IVF clinic (n = 2676 patients undergoing 2676 treatments and producing and 8151 blastocysts). m-ER were investigated according to women's reproductive history of LBs: no/≥1, miscarriages: no/1/>1; failed IVF cycles: no/1/2/>2, and implantation failures after previous transfers: no/1/2/>2. Among the 2676 patients included in this study, 440 (16%) had already undergone PGT-A before the study period; the data from these patients were further clustered according to the presence or absence of euploid embryo(s) in their previous cohort of biopsied blastocysts. The clinical outcomes per first single vitrified-warmed euploid blastocyst transfers (n =1580) were investigated according to the number of patients' previous miscarriages and implantation failures. The procedures involved in this study included ICSI, blastocyst culture, trophectoderm biopsy without hatching in Day 3, CCT-based PGT-A without reporting segmental and/or putative mitotic (or mosaic) aneuploidies and single vitrified-warmed euploid blastocyst transfer. For statistical analysis, Mann-Whitney U or Kruskal-Wallis tests, as well as linear regressions and generalised linear models among ranges of maternal age at oocyte retrieval were performed to identify significant differences for continuous variables. Fisher's exact tests and multivariate logistic regression analyses were instead used for categorical variables. Maternal age at oocyte retrieval was the only variable significantly associated with the m-ER. We defined five clusters (<35 years: 66 ± 31%; 35-37 years: 58 ± 33%; 38-40 years: 43 ± 35%; 40-42 years: 28 ± 34%; and >42 years: 17 ± 31%) and all analyses were conducted among them. The m-ER did not show any association with the number of previous LBs, miscarriages, failed IVF cycles or implantation failures. Among patients who had already undergone PGT-A before the study period, the m-ER did not associate with the absence (or presence) of euploid blastocysts in their former cohort of biopsied embryos. Regarding clinical outcomes of the first single vitrified-warmed euploid blastocyst transfer, the implantation rate was 51%, the miscarriage rate was 14% and the LBR was 44%. This LBR was independent of the number of previous miscarriages, but showed a decreasing trend depending on the number of previous implantation failures, reaching statistical significance when comparing patients with >2 failures and patients with no prior failure (36% versus 47%, P < 0.01; multivariate-OR adjusted for embryo quality and day of full blastocyst development: 0.64, 95% CI 0.48-0.86, P < 0.01). No such differences were shown for previous miscarriage rates. The sample size for treatments following a former completed PGT-A cycle should be larger in future studies. The data should be confirmed from a multicentre perspective. The analysis should be performed also in non-PGT cycles and/or including patients who did not produce blastocysts, in order to investigate a putative association between women's reproductive history with outcomes other than euploidy and LBRs. These data are critical to counsel infertile couples before, during and after a PGT-A cycle, especially to prevent treatment discontinuation due to previous adverse reproductive events. Beyond the 'maternal age effect', the causes of idiopathic recurrent pregnancy loss (RPL) and RIF are likely to be endometrial receptivity and selectivity issues; transferring euploid blastocysts might reduce the risk of a further miscarriage, but more information beyond euploidy are required to improve the prognosis in case of RIF. No funding was received and there are no competing interests. N/A.

Cimadomo D ，Capalbo A ，Dovere L ，Tacconi L ，Soscia D ，Giancani A ，Scepi E ，Maggiulli R ，Vaiarelli A ，Rienzi L ，Ubaldi FM ... -  《-》