To determine whether the embryo cleavage pattern and the rate of blastocyst formation differs between normal weight and obese women undergoing in vitro fertilization (IVF) with ICSI (intracytoplasmic sperm injection). This is a retrospective cohort study performed from January 2016 to May 2020 in IVIRMA-Valencia. A total of 3,316 ICSI cycles from 2,822 women were included, with 1,251 cycles belonging to the Preimplantation Genetic Testing (PGT) program. Patients were grouped according to their body mass index (BMI).Underweight was defined as a BMI < 18.5 kg/m2 (n = 173 cycles from 140 women), normal weight as a BMI of 18.5–24.9 kg/m2 (n= 2,339 cycles from 1,989 women), overweight as a BMI of 25–29.9 kg/m2(n = 643 cycles from 548 women) and obesity as a BMI of >30 kg/m2 (n =161 cycles from 145 women).All embryos were grown in vitro until the fifth or sixth day in a time-lapse system - EmbryoScope, EmbryoScope Plus (Vitrolife) and Geri Plus (GeneaBiomedx) - and its development was assessed on an external computer with a specific software for the purpose. There were no differences in sperm parameters or male age among the four BMI groups. Underweight women were l year or less younger than the other three groups. The percentage of women with polycystic ovary syndrome was higher but not significantly different in the obese group. Indications for PGT do not differ among groups .The number of oocytes retrieved or mature oocytes microinjected was significantly higher in the obese group than in the normal weight group. However, fertilization rates and number of embryos transferred were similar in the four BMI groups. A higher percentage of surplus embryos for freezing was observed in the underweight group when compared to normal weight women. All the embryos were transferred or frozen in blastocyst stage. Despite an initial slower pattern of embryo development, the final blastocyst formation rate in day 5 or in day 5 plus day 6 did not differ in obese women when compared to the other BMI groups. Moreover, embryo quality, based on the evaluation of inner cell mass and trophectoderm in both days of blastocyst development was similar across BMI groups. The same was observed with respect to the pattern of development and arrest up to blastocyst formation and the different categories of full, expanded and hatching blastocysts. Blastocyst formation is not affected by female BMI.

To quantify the potential of non-invasive analysis of the oxidative status of the spent media as a viability biomarker in embryo cohorts subjected to group culture in a time-lapse system. We collected 479 samples of spent culture media from 356 ICSI treatments in which embryos were cultured in shared media in two time-lapse incubators: EmbryoScope+® (ESD+, Vitrolife, n=245) and Geri® (Genea Biomedx, n=111). Aliquots of 14μl were analyzed in the Fertissimo Analyzer (Carmel Diagnostics, Israel), which measures the oxidative status of the sample by thermochemiluminescence (TCL) technology: counting the photon emission per second (cps) after heating. TCL parameters express cps amplitude after 55s (H1), 155s (H2) and 255s (H3), the ratio between the Hs, their normalized variants (sm), and a summary mean value (TCL Score). Correlation between the oxidation level of the media and the number and quality of the embryos cultured in the drops was assessed by Pearson correlation coefficient (PCC). The mean oxidation level was found to be significantly different between samples coming from each incubator: TCL Score (ESD+)= 81.04 ± 16.98 vs TCL Score (Geri)= 95.1 ± 14.45, P<0.001. This result might be derived from the different media volume and number of embryos in the dishes (two 180μl pools of 8 embryos in ESD+ and a single 80μl pool of up to 16 embryos in Geri). In samples from ESD+ a significant direct correlation was found between TCL parameters and the number of MII (PCC= 0.122, P=0.02 for H3; 0.096, P=0.067 for TCL Score) and number of blastocysts in the pool (PCC (H3)= 0.139, P=0.008; PCC (TCL Score)= 0.126, P=0.016). A significant direct correlation was also found between H1 and the blastocyst rate (PCC= 0.108, P=0.038) and between H2 and the proportion of those classified as A or B by ASEBIR morphological criteria (PCC= 0.135, P=0.011) in ESD+ samples. A similar association was not found in Geri samples. A significant correlation was found between H2 and the viable (transferred/frozen) embryo rates for both incubators (PCC (ESD+)= 0.105, P=0.045; PCC (Geri)= 0.201, P=0.033). In Geri samples from PGT-A treatments, the TCL Ratio resulted directly correlated to the euploidy rate of the analyzed embryos (PCC= 0.412, P=0.007). Our results show that higher levels of oxidative stress in the spent media are not marker of negative prognostics, but a natural reflection of embryo oxidative metabolism in a closed optimized environment, and directly related with the number of embryos cultured in the media. The lack of said correlation in samples from Geri incubator might be related to the lower volume/embryo ratio, which may cause a faster saturation of the free radicals in the media. Additionally, embryos classified as top morphological quality and euploid embryos, expected to have higher viability, have an increased contribution to the oxidation of the media.

To compare a novel capacitation technique based on microfluidics, called Harvester, with density gradient centrifugation (DGC). A pilot prospective study, that included sperm samples of 25 patients was conducted. Fresh ejaculate specimens and capacitated samples of each patient were analyzed according to WHO 2010 criteria with automatic image analysis. Harvester and DGC were used to isolate sperm based on fluid dynamics and cell motility. Fresh sperm samples and sperm resolved by both capacitation techniques were assessed for excessive histone retention indicating defective chromatin compaction and hence DNA maturation using aniline blue staining. Sperm chromatin fragmentation (SCF) of fresh and capacitated sperm samples was assessed by TUNEL on at least 20.000 sperm using flow cytometry. ANOVA test was performed in order to assess statistical differences between result variables. Between March and April, 25 men were recruited (mean age 34,7±8,7 years). Ejaculated sperm were assessed by automatic semen analysis, which yielded an average concentration of 60,1±31,8 x106/mL. After DGC and Harvester, the sperm concentration was 13,2±9,0 and 13,3±10,0 x106/mL, respectively. The motility of fresh sperm sample improved from 42,2±11,8% to 70,7±13,6% after DGC and 74,9±12,7% after Harvester (P<0,0001). Similar trends were obtained when morphology was analyzed. The percentage of normal sperm increased from 1,9±1,1%, for the raw samples, to 3,4±1,5 and 4,1±1,2% for the samples capacitated using DGC and microfluidics, respectively (P<0,0001). Another parameter, which benefited from the capacitation, was DNA maturation. The percentage of sperm DNA maturation increased from 65,3±7,4% to 72,5±7,3% when the samples were processed by DGC and 75,0±7,6% when the harvester was used (P<0,0001). In the same way, the percentage of live sperm increases from 74,0±7,9% and 77,8±8,1% in fresh sperm and after DGC, respectively to 84,2±8,6% after using Harvester (P<0,02). Although there are no significant differences, a decrease in SCF from 17,0±11,9% was observed in capacitated samples using DGC to 12,2±6,2% in raw samples (P>0,05). Nevertheless, after capacitation by Harvester SCF fell to 8,2±7,3%, showing significant differences between both capacitation methods (P<0,006). While the sperm motility, morphology, DNA maturation and vitality improve with the capacitation, no significant differences are observed between Harvester and DGC, except for vitality in which a significant increase in live sperm was observed after using Harvester, due to the preliminary reduced sample size, although values presented better improvement with Harvester. On the contrary, when SCF was analyzed, a significant reduction was observed between the two capacitation techniques, being lower in Harvester.

STUDY QUESTION: Does the embryo cleavage pattern and rate of blastocyst formation differ between normal weight and obese women undergoing IVF? SUMMARY ANSWER: Embryo morphokinetic development, final blastocyst formation rate and blastocyst morphology do not differ between obese and normal weight women. WHAT IS KNOWN ALREADY: Female obesity has been related to impaired IVF outcomes. Although the mechanisms responsible for this detrimental effect are thought to include impaired oocyte and embryo quality and reduced endometrial receptivity, they are yet to be confirmed. Embryo quality has been commonly assessed using static morphological criteria. Only three studies have analysed the progress of embryos up to the blastocyst stage in women with elevated BMI, but they have used small samples of patients or have obtained contradictory results. STUDY DESIGN, SIZE, DURATION: This retrospective, cohort study, was performed from January 2016 to May 2020. A total of 3316 ICSI cycles from 2822 women were included, of which 1251 cycles were part of a preimplantation genetic testing programme. In total, 17 848 embryos were analysed. PARTICIPANTS/MATERIALS, SETTING, METHODS: This study reports on the IVF cycles of infertile women, with a known BMI, who underwent ICSI and whose embryos were grown until the fifth/sixth day of development in a time-lapse system. Patients were grouped as follows. Underweight was defined as a BMI <18.5 kg/m(2); normal weight was a BMI of 18.5-24.9 kg/m(2); overweight was a BMI of 25-29.9 kg/m(2); and obesity was a BMI of >= 30 kg/m(2). Embryo development was assessed on an external computer with analysis software. MAIN RESULTS AND THE ROLE OF CHANCE: Despite an initial slower pattern of embryo development, the blastocyst formation rate on day 5 or on day 5 plus day 6 did not differ in obese women with respect to the other three BMI groups. Moreover, based on the evaluation of inner cell mass and the trophectoderm on both days of blastocyst development, embryo quality was similar across the BMI groups, as were the pattern of development and arrest up to blastocyst formation and the distribution of the categories of full, expanded and hatching blastocysts. LIMITATIONS, REASONS FOR CAUTION: Limitations include the retrospective analysis of data, the use of BMI as the only parameter to define normal/abnormal female body weight, and the lack of complete information about clinical outcomes. WIDER IMPLICATIONS OF THE FINDINGS: Blastocyst formation and embryo morphokinetics are not affected by female obesity, and the poorer IVF outcomes described for such women are probably due to deficient endometrial receptivity. The role of endometrial progesterone exposure on the day of embryo transfer should be analysed in future studies as a possible determining factor.

It is 40 years since the birth of the first baby conceived through in vitro fertilization (IVF). From then on, remarkable progress has been made in the management of infertility and assisted reproductive technology (ART). The improvements in clinical practice, such as ovarian stimulation protocols, embryo culture conditions, and vitrification protocols, have led to improved success rates globally.

OBJECTIVE:To describe novel embryo features capable of predicting implantation potential as input data for an artificial neural network (ANN) model. DESIGN:Retrospective cohort study. SETTING:University-affiliated private IVF center. PATIENT(S):This study included 637 patients from the oocyte donation program who underwent single-blastocyst transfer during two consecutive years. INTERVENTION(S):None. MAIN OUTCOME MEASURE(S):The research was divided into two phases. Phase 1 consisted of the description and analysis of the following embryo features in implanted and nonimplanted embryos: distance and speed of pronuclear migration, blastocyst expanded diameter, inner cell mass area, and trophectoderm cell cycle length. Phase 2 consisted of the development of an ANN algorithm for implantation prediction. Results were obtained for four models fed with different input data. The predictive power was measured with the use of the area under the receiver operating characteristic curve (AUC). RESULT(S):Out of the five novel described parameters, blastocyst expanded diameter and trophectoderm cell cycle length had statistically different values in implanted and nonimplanted embryos. After the ANN models were trained and validated using fivefold cross-validation, they were capable of predicting implantation on testing data with AUCs of 0.64 for ANN1 (conventional morphokinetics), 0.73 for ANN2 (novel morphodynamics), 0.77 for ANN3 (conventional morphokinetics + novel morphodynamics), and 0.68 for ANN4 (discriminatory variables from statistical test). CONCLUSION(S):The novel proposed embryo features affect the implantation potential, and their combination with conventional morphokinetic parameters is effective as input data for a predictive model based on artificial intelligence.

Blastocyst contraction has been extensively described by Time-Lapse monitoring systems, affecting approximately 20% of the embryos, decreasing their implantation potential to 10% (Scorio et al. 2020). Our objective is to demonstrate whether performing AH for those collapsed blastocysts (CB) may help to restore their implantation potential. To demonstrate our hypothesis we calculated the implantation rate as well as pregnancy rate (PR) of CB with AH comparing these results to those blastocysts with collapse but without AH. Retrospective Cohort Study. We analyzed 208 blastocyst from oocyte donation program during one consecutive year(January 2019-January 2020) that were distributed in two groups: the control group (107 CB without AH) and the study group (101 CB with AH). All blastocysts included in the study were cultured in a time-lapse system to identify the collapse episode (≥50% of the surface of the trofoctoderm separated from the zona pellucida), being verified the collapse through the Embryo ViewerTM or Asses 2.0 workstations. Both study and control group were formed by frozen blastocyst where the collapse episode was retrospectively identified before warming. AH was achieved in the study group through laser (eliminating one quarter part of the zona pellucida). All embryos were incubated for 3-4 hours before being transferred. Pregnancy and implantation rates were analyzed and compared in both groups by Χ2 test and regression logistic analysis(RLA) was performed considering body mass index, maternal age, blastocyst vitrification day(D5 vs D6) and blastocyst morphology as confounding factors to weight the effect of AH on ongoing pregnancy rate(OPR). Considering cases with known implantation, after applying AH in the collapsed blastocysts(101) resulted higher pregnancy rates(PR) compared to those without AH(107): 54.5% vs 40.6% for PR with p=0.049; 45.5% vs 31.7% for clinical pregnancy rate(CPR) with p= 0.043 and 35.6% vs 20.8% for OPR with p=0.019. When we only selected SET cases (177) the benefits were equally effective for CB with AH (84) compared to CB without AH(93), getting higher OPR (34.5% vs 17.2% p=0.008). The blastocysts were categorized by morphology (ASEBIR) into A, B or C. After performing a RLA , AH presented an odds ratio of 3.23 (CI95% 1.491-6.979) for OPR (p=0.003). Our findings support the use of AH for CB to improve up to three times the OPR. Maybe the strong contractions suffered by the blastocysts during the embryo development imply a waste of energy necessary for the implantation process. This behaviour would explain the decreased of the implantation of those embryos without AH. Performing AH in CB could recover the implantation capacity impaired by the collapse. Also irrespective of either blastocyst morphology or vitrification day a benefit was observed and quantified after carrying out AH.

Research question: Is embryo selection by Dana (automatic software for embryo evaluation) associated with a higher implantation rate in IVF treatments? Design: A three-phase study for Dana system's validation: creation of a data-cloud of known implantation data (KID) embryos from 1676 transferred embryos; embryo evaluation by Dana considering manual annotations and embryo development videos (389 transferred embryos); and validation of Dana automatic selection, without embryologist's intervention (147 transferred embryos); Results: The implantation rate of the 1021 KID embryos from phase 1 served to set four grades of embryos referring to implantation rate: A = 34%, B = 25%, C = 24%, and D = 19%. Phase 2: a classification ranking according to the unit average distance (UAD) and implantation potential was established: top (UAD <=.50), high (UAD = 0.51-0.66), medium (UAD = 0.67-1.03) and low (UAD >1.03). Pregnancy rates were 59%, 46%, 36% and 28%, respectively (P < 0.001). Phase 3: embryos were automatically categorized according to Dana's classification ranking. Most implanted embryos were found in groups top, high and medium (UAD <= 1.03), whereas the implantation rate in group low (UAD >1.03) was significantly lower: 46% versus 25%, respectively (P = 0.037). The twin gestation rate was higher when number of top embryos (UAD <= 0.5) transferred were two (52%) versus one (25%) (P < 0.001). Conclusions: Embryo selection based on Dana ranking increases the success of IVF treatments at least in oocyte donation programmes. The multicentre nature of the study supports its applicability at different clinics, standardizing the embryo development's interpretation. Dana's innovation is that the system increases its accuracy as the database grows.

Objective: To describe the outcome of preimplantation genetic testing (PGT-A) using their own oocytes in patients with mosaic Turner Syndrome (MTS). The impact of the assisted reproduction technique (ART) performed (PGT-A or oocyte donation) and the type of absence of the X chromosome (total or partial) were considered. Design: Retrospective observational multicenter study. Setting: University-affiliated private in vitro fertilization center. Patient(s): Fifty-six patients with MTS with whom 65 ovarian stimulation cycles for PGT-A (fluorescence in situ hybridization/arraysnext generation sequencing) were performed. The study included 90 women with MTS and 20 women with pure Turner Syndrome (PTS) who underwent 140 and 25 oocyte donation (OD) cycles, respectively. Intervention(s): In vitro fertilization for PGT-A (fluorescence in situ hybridization/arrays-next generation sequencing) or OD. Main Outcome Measure (s): Reproductive outcome and feto-maternal outcomes. Results: The live birth rate (LBR) per embryo transfer in patients with MTS tended to be higher in OD 37.7% (95% confidence interval [CI]: 29.3-46.1) than that observed for PGT-A 22.5% (95% CI 7.8-38.2), and the cumulative LBR (CLBR), with 77.6% vs. 43.3%, respectively. Likewise, the LBR per patient was significant when comparing PGT-A vs. OD, with 12.5% (95 CI 3.9-21.1) vs. 51.1% (40.7-61.4), respectively. While focusing on the X chromosome, partial MTS (PTS), we found significant differences in the CLBR per embryo transfer, with 77.6% vs. 29.2%, and also in the LBR per patient: 51.1% (40.7-61.4) in MTS vs. 15% (95 CI 0.0-30.1) in PTS. Conclusion(s): Oocyte donation is the best reproductive option in females with Turner Syndrome with or without mosaicisms. Nevertheless, PGT-A is a valid therapeutic option in patients with MTS using their own oocytes, and OD should not necessarily be directly recommended. (C) 2020 by American Society for Reproductive Medicine.

Research question: The study aimed to develop an artificial intelligence model based on artificial neural networks (ANNs) to predict the likelihood of achieving a live birth using the proteomic profile of spent culture media and blastocyst morphology. Design: This retrospective cohort study included 212 patients who underwent single blastocyst transfer at IVI Valencia. A single image of each of 186 embryos was studied, and the protein profile was analysed in 81 samples of spent embryo culture medium from patients included in the preimplantation genetic testing programme. The information extracted from the analyses was used as input data for the ANN. The multilayer perceptron and the back-propagation learning method were used to train the ANN. Finally, predictive power was measured using the area under the curve (AUC) of the receiver operating characteristic curve. Results: Three ANN architectures classified most of the embryos correctly as leading (LB+) or not leading (LB-) to a live birth: 100.0% for ANN1 (morphological variables and two proteins), 85.7% for ANN2 (morphological variables and seven proteins), and 83.3% for ANN3 (morphological variables and 25 proteins). The artificial intelligence model using information extracted from blastocyst image analysis and concentrations of interleukin-6 and matrix metalloproteinase-1 was able to predict live birth with an AUC of 1.0. Conclusions: The model proposed in this preliminary report may provide a promising tool to select the embryo most likely to lead to a live birth in a euploid cohort. The accuracy of prediction demonstrated by this software may improve the efficacy of an assisted reproduction treatment by reducing the number of transfers per patient. Prospective studies are, however, needed.

Fertilization failure or low fertilization rate after ICSI is around 1–3% in IVF treatments. Several strategies have been studied in order to bypass the lack of activation. The aim of this study is to evaluate embryo morphokinetics and reproductive outcomes after intracytoplasmic sperm injection (ICSI) with assisted oocyte activation (AOA) using a calcium ionophore (CaI) in patients with previous fertilization failure or low fertilization rate (under 30%) and severe male factor. Multicentric retrospective cohort study including 70 patients with fertilization failure or low fertilization rate and severe male factor (sperm concentration under 1 million/mL) who underwent ICSI with CaI (756 oocytes), and 76 patients with severe male factor without previous fertilization failure who had standard ICSI (748 oocytes) between January 2011 and December 2016. CaI Exposed and non-exposed groups differed significantly for normal fertilization rates, pronuclear disappearance timing (tPNf), time to 4 cells stage, multinucleation at the 2- and 4-cell stages, and direct cleavage events. Implantation rate was higher in the non-exposed group (p = 0.023). Other morphokinetic variables were similar between groups. Pregnancy (higher in the non exposed group), abortion, and live birth rates, were also not statistically different among groups. Although the fertilization and implantation rates were higher in the non-exposed group, ICSI-CaI was associated with an increased fertilization rate compared to patient previous attempts and thus with increased pregnancy chances. Because of the specific patient populations involved (patients with severe male factor with or without previous fertilization failure), the results might not generalize for patients with different etiologies. Trial Registration: 1506-VLC-045-MM. El fracaso de la fertilización o la baja tasa de fertilización después de la ICSI es de alrededor del 1 al 3% en los tratamientos de FIV. Se han estudiado varias estrategias para evitar la falta de activación. El objetivo de este estudio es evaluar la morfocinética del embrión y los resultados reproductivos después de la inyección intracitoplasmática de espermatozoides (ICSI) con activación asistida de ovocitos (AOA) mediante un ionóforo de calcio (CaI) en pacientes con fracaso previo de fertilización o baja tasa de fertilización (menos del 30%) y factor masculino grave. Estudio multicéntrico, retrospectivo, de cohorte, que incluye 70 pacientes con fracaso de la fecundación o baja tasa de fecundación y factor masculino grave (concentración de espermatozoides inferior a 1 millón/mL) que se sometieron a ICSI con CaI (756 ovocitos) y 76 pacientes con factor masculino grave sin fracaso previo de la fecundación que tuvieron ICSI estándar (748 ovocitos) entre enero de 2011 y diciembre de 2016. Los grupos expuestos y no expuestos al CaI difirieron significativamente en cuanto a las tasas normales de fertilización, el tiempo de desaparición pronuclear (tPNf), el tiempo hasta la etapa de 4 células, la multinucleación en las etapas de 2 y 4 células y los eventos de división directa. La tasa de implantación fue mayor en el grupo no expuesto (p = 0,023). Otras variables morfocinéticas fueron similares entre los grupos. Las tasas de embarazo (más altas en el grupo no expuesto), de aborto y de nacidos vivos tampoco fueron estadísticamente diferentes entre los grupos. Aunque las tasas de fertilización e implantación fueron más altas en el grupo no expuesto, el ICSI-CaI se asoció con una mayor tasa de fertilización en comparación con los intentos anteriores de la paciente y, por lo tanto, con mayores posibilidades de embarazo. Debido a las poblaciones de pacientes específicamente implicadas (pacientes con factor masculino severo con o sin fracaso previo de fertilización), es posible que los resultados no se puedan generalizar a pacientes con diferentes etiologías. Registro de ensayos: 1506-VLC-045-MM.

The aim of this study is to develop an artificial intelligence (AI) model able to predict the life-birth probability of in-vitro cultured embryos, combining morphology and morphokinetic (MK) information of their development with their oxidative stress level. This retrospective study includes 131 transferred embryos (fresh and frozen-thawed) cultured individually in an Embryoscope (ESD) incubator (Vitrolife, Denmark) until day 5/6. They belong to 100 ICSI cycles performed between May 2017 and December 2018, using autologous or donated eggs. After transfer, the oxidative status of the culture media was assessed by the Thermochemioluminiscence (TCL) AnalyzerTM (Carmel diagnostics, Israel) as an indirect measurement of their metabolic activity. A machine learning algorithm was trained using MK data obtained using the time-lapse monitoring system, the TCL values and the clinical outcome of each embryo, generating a predictive model of life-birth probability. Fertilization was performed following the standard protocol of the clinic. Scoring and selection for transfer/freezing were performed according to the ASEBIR criteria, combining morphological and MK assessment. The oxidative status of 15 μL aliquots of media was measured by the TCL Analyzer, which counts the photons emitted per second (cps) as result of the heat-induced oxidation and modification of the sample. TCL parameters used were H1, H2 and H3 (TCL amplitude at 55, 155 and 255 seconds after heating, respectively), as well as their "sm" variants, resulting from applying a smoothing algorithm to normalize the data. The AI analysis was performed using machine learning algorithms, combining different sets of variables. Data from 105 embryos was used for the training of the machine, and 26 for the simulation. Properly timed development and higher TCL parameters directly related to higher chances of achieving life-birth, as previously published. Five datasets were formed using different combinations of MK and TCL parameters with the stronger statistic correlation with life-birth result: MK+H1+H2+H3, MK+H1sm+H2sm+H3sm, MK+H1sm, MK+H2sm and MK+H3sm. They were compared to a reference model using only MK. The combination with the highest predictive capacity was MK + H2sm. In the training, the model achieved a 93.6% accuracy for predicting positive life-birth (LB+) and 86.2% for negative (LB-), compared to the 97.9% LB+ and 94.8% LB- using solely MK. The blind test of MK + H2sm model had a stronger predictive power (83.3% LB+, 85.7% LB-) than only MK (66.7% LB+, 85.7% LB-). Other combinations of oxidation variables did not show an improved predictive capacity when compared to the MK algorithm. The presented AI algorithm combining MK and TCL parameter H2sm scores a higher predictive power for life-birth than using only MK data. This supports the relevance of the oxidative status of the culture media as an indirect measurement of metabolic activity, higher in embryos that achieve birth. This AI algorithm provides an upgraded score system to assist embryo selection, potentially improving clinical results.

To introduce the analysis of blastocysts images from alternative time-lapse monitoring systems (TLM) by using Artificial Intelligence in the prediction of live birth (LB). Retrospective cohort Study. We used image analysis technology as a tool to evaluate TLM images of 244 blastocyst stage embryos at 111.5 ± 1.5h post ICSI. The embryos were cultured in Geri-TLM incubator (Genea, Australia) until day 5 of development. Of the 244 blastocysts analyzed, from a single embryo transfer program, 200 were used for training (82%) and 44 for a blind test (18%) for prediction of LB by using AI. It was built a model of artificial neuronal network (ANN) to produce a predictable outcome of LB. Several independent numerical variables extracted from standardized TLM images as an input data were used. The efficacy of prediction of live birth was quantified and assessed using confusion matrices (True Positive-TP, True Negative-TN, False Positive-FP, False Negative-FN; Positive Prediction Value-PPV and Negative Prediction Value-NPV), ROC curves and AUC. The accuracy (ACC) of prediction of live birth by AI using an ANN model was 85.2% (208/244; TP= 68, TN= 140, FP= 19, FN= 17). In the training dataset the ACC was 90.5% (181/200; TP= 58, TN= 123, FP= 14, FN= 5, AUC= 0.868), and in the blind test dataset, ACC was 61.4% (27/44; TP= 10, TN= 17, FP= 15, FN= 12, AUC= 0.634). The PPV, precision with which the ANN model was able to classify correctly a positive LB was 78.2%. In training dataset, the precision was 80.6% for LB+, and in blind test dataset 66.6%. Likewise, the overall NPV, capacity to classify correctly a negative LB, was 89.2%. In training dataset, the NPV was 96.0%, and in blind test dataset 58.6% for LB-. The AUC in the Blind test for positive and negative LB were very similar, 0.634 and 0.618 respectively. This is the first ANN model using images from Geri TLM incubator as a target in image analysis technology. The model shows a competitive accuracy, predictive power and precision to improve the efficacy of embryo selection performed by the standard morphology and increasing the odds of LB per embryo transfer.

The aim of this study is to compare the timing of the main development events of embryos cultured in humid (HC) or dry conditions (DC) in a time-lapse system (TLM) incubator. In this retrospective study we analysed the morphokinetics of 7014 embryos belonging to 832 ICSI treatments performed during two consecutive years, from autologous (n=393) or ovum donation programs (n=439). Embryos were cultured in an incubator equipped with time-lapse monitoring system, in dry (3281 embryos) or humid conditions (n=3149). Timing of the main development events of each embryo were annotated and compared between the two study groups. Stimulation, oocyte pickup and fertilization were performed according to the standard procedures of the clinic. Fertilized oocytes were cultured in a Geri incubator (Genea Biomedx, Australia). This incubator has 6 separated chambers for individual patients, 3 of them operating with dry environment, and 3 adapted for culture in a high relative humidity atmosphere. Embryo cohorts were randomly assigned to DC or HC. Embryo development was monitored using Assess 2.0 TLM software from Geri and the main morphokinetic parameters were automatically annotated and compared between those incubated in dry vs humid conditions. Statistical analysis was performed using the Statistical Package for Social Sciences (SPSS) in search for significant differences between the two groups. Morphokinetic parameters were compared between all embryos cultured in HC and DC, as well as only good morphology blastocysts and only transferred embryos. Significant differences (p≤0,05) were found in the mean values of tPNf (23,350h in HC vs 23,591h in DC), t2 (26,809h in HC vs 27,149h in DC), tM (85,958h in HC vs 86,904h in DC) and tEB (114,727h in HC vs 113,805h in DC), being all except the latter lower in embryos cultured in HC. When comparing only good morphology blastocysts, tPNf (22,821h vs 23,165h), t2 (25,569h vs 25,843h) and tM (85,226h vs 86,573h, p≤0,001) remained being significantly lower in HC, as well as tSC (98,499h vs 99,187h), but no significant difference was found in tEB. However, when comparing only transferred embryos (n=394), no significant differences in tPNf nor t2 were found, although tM remained significantly lower in HC (83,424h vs 86,020h in DC, p=0,002). Later developmental events occurred faster in transferred embryos cultured in HC than DC: tSB (95,806h vs 97,249h, p=0,042), tB (101,870h vs 103,662h, p=0,05) and tEB (108,086h vs 109,851h, p= 0,012), in contrast with the observed in the whole set. Embryos cultured in HC had a slightly faster development than those cultured in DC, being the time to reach morulae stage the most affected parameter, which has been previously related with higher embryo quality and implantation potential (Goodman et al, 2016). These findings are consistent with previously published results (Albert et al, 2020) where embryos cultured in HC had higher ongoing pregnancy rates than those cultured in DC.

To improve of treatment outcome in terms of fertilization, implantation and pregnancy rates as well as cancelation rate after applying AOA in the following treatments for those patients with previous very low or failed fertilization attempts. Additionally were tested both delivery rate and obstetric outcomes in children born after AOA use. Retrospective Cohort Study. Period included between April 2013 and December 2018. The total number of oocytes included in the study was 1125 distributed in two groups: the control group formed by 509 oocytes from 66 patients who were injected without AOA, acquiring either a failure or unusually low fertilization values (<30%) and the study group consisted of 616 oocytes from the same patients (66) in a second attempt but using AOA. Injection technique with AOA is comparable to conventional injection (ICSI) but in this case each oocyte was injected by spermatozoon together with a previous phase of buffered medium mixed with ionophore calcium (ICa) aspirating it up to filling one third of the overall length of the pipette under 40X microscope magnification. Just after, they were kept for ten minutes with Ica into benchtop incubator and finally were incubated under the same culture conditions (37ºC, 6% CO2, 5% O2 atmosphere) Fertilization, pregnancy, implantation and abortion rates were analysed and compared in both groups by Χ2, t-Student and ANOVA tests. Both live birth and neonatal outcome was also reported. After applying AOA, we observed a significant increase in the fertilization rate (51% vs 13.1%), ongoing pregnancy rate (47% vs. 21.7%) as well as implantation rate (31.1% vs 13.1%) and lower chances of cancellation (22.7% vs 69.3%). Additionally, no adverse obstetric and perinatal outcomes effects were found after the use of AOA compare to conventional ICSI. Our findings support the use of AOA for a specific population of patients with previous very low fertilization or fertilization failure and in consequence, the outcome was impaired. After applying AOA, the reproductive success was significantly enhanced, mainly by the significant increase in the fertilization rate, the number of embryos available for selection, reducing dramatically the cancellation rate. The safety of AOA is reflected in the current practice after confirming non-detrimental effects in the offspring.

To identify in fertilized oocytes previously unrecognized predictive features for live birth following IVF treatment that can apparently be revealed only by an advanced novel AI algorithm. The study used AI to analyse TL videos of embryos in their pronuclei stage. We analyzed video images of 123 fertilized embryos obtained from a time-lapse system Embryoscope. Of the 123 videos, 111 were clear enough for analysis. All embryos analyzed were graded as Top-Graded embryos and were transferred back to the uterus. Of these embryos 88 (71.5%) successfully implanted and 45 (36.6%) resulted in a live birth. Using a machine learning algorithm, we were able for the first time to characterize a previously unrecognized feature, the pale cytoplasm creating a "halo" surrounding the nucleus of the fertilized oocyte. The measurable amount of this halo over a range of images was compared to a set threshold. The resulting yes/no decision was assessed in relation to the likelihood of the embryo to implant successfully. We calculated a relative brightness/smoothness measure, comparing each image to a reference image of the same embryo 7 hours earlier. These measurements were compared to an internal threshold obtained experimentally, with the result reported as above threshold (significant halo identified) or below threshold (no significant halo identified). The halo was identified in 42% of 49 videos of embryos that successfully implanted versus in only 17% of embryos that failed to implant. There was no difference in the proportion of embryos that implanted, where a halo was identified, according to whether they carried out to a live birth or miscarried. Using the halo to predict successful implantation of a Top-Graded transferred embryo had a sensitivity of 42% and a specificity of 83%, with a positive predictive value of 85% and a negative predictive value of 46%. An AI algorithm identified in video images of fertilized oocytes a previously unrecognized feature that is associated with a high positive predictive value for subsequent successful implantation. The Automated Halo Identification may help improve embryo selection and result in higher live birth rates.

To describe the impact of the group embryo culture over the oxidative profile of the medium and over the fertilization and the blastocyst rates in two types of culture dishes from two time-lapse incubators. A retrospective analysis, including 299 IVF cycles from May 2017 to December 2018, was conducted. Culture media from 413 groups of embryos (15 μl/group) monitored with EmbryoScope Plus® (ES+) and Geri Plus® were analysed by the Thermochemiluminescence (TCL) AnalyzerTM (Carmel Diagnostics, Israel). A total of 299 spent embryo culture media from ES+ and 114 from Geri were analyzed. Sequential medium was used in 227 embryo groups and single-step medium in 186. The TCL AnalyzerTM consists on the heat-induced oxidation of biological fluids, leading to the production of light energy counted as photons emitted per second (cps). The oxidative parameters were obtained after 55 sec. (H1), 155 sec. (H2) and 255 sec. (H3). A smoothing algorithm (sm) was used to normalize data. Data were analyzed with ANOVA and Chi-squared tests (SPSS software). Higher fertilization rates were found as the number of oocytes increased in the same group. However, blastocyst rate and the number of good quality blastocysts decreased when the number of embryos per group increased: 73.6±30.3% for ≤6 embryos, 69.0±23.7% for 7-8 embryos, 67.4±23.1% for 9-12 embryos and 64.9±23.2% for ≥13 embryos. The comparison between two time-lapse incubators with this kind of embryo culture showed significantly (p<.05) higher fertilization rates for Geri (78.9±17.3% for Geri vs. 73.7±20.6% for ES+) and higher blastocyst rates for ES+ (70.6±26.7% for ES+ vs. 65.7±22.6% for Geri). According to our data, sequential culture medium worked significantly better (p<.05) than single-step medium in terms of blastocyst rate (72.13±24.5% for sequential medium vs. 65.57±26.6% for single-step medium). In addition, oxidative stress level of the medium the fifth day post ICSI was significantly higher as more oocytes were successfully fertilized (Table). Table: Mean and standard deviation of the TCL parameters according to the number of successfully fertilized oocytes.Tabled 1Oocytes fertilizedN (Groups)H1sm (cps)H2sm (cps)H3sm (cps)≤411788.7 ± 32.891.5 ± 34.998.3 ± 39.45-610883.6 ± 35.985.8 ± 37.592.9 ± 41.57-893103.3 ± 49.2108.0 ± 54.5117.14 ± 63.8≥995105.1 ± 32.3109.9 ± 32.6121.3 ± 37.1P Values<0.001<0.001<0.001 Open table in a new tab Group embryo culture strategies affect embryo development results: as the number of oocytes cultured per group increased fertilization rates were improved, but not blastocyst rates, which were higher when medium was replaced. Moreover, media's oxidative stress level was higher when more fertilized oocytes were cultured per group.

To analyze the abilities of DANA automatic embryo selection software to interpret embryo morphokinetic parameters by massive comparison with a database of embryos with known implantation potential and generate a transfer order ranking in a single embryo transfer policy. DANA compares each cohort of embryos with a data cloud of KID (Known Implantation Data). This data cloud was performed from a retrospective analysis of 1021 KID embryos. For that, timings of embryo cleavage and cell cycle lengths were included in the DANA software. Morphokinetic parameters were arranged on a 2D graph and the software analysed the unit average distance (UAD) of the embryos to the centre of the cloud. We defined a category of TOP embryos with an UAD ≤ 0.5. The percentage of twin gestation was calculated in our double embryo transfer cases comparing whether 1 or 2 of the transferred embryos had a high score in the Dana ranking. A total of 357 fresh cycles from infertile couples undergoing oocyte donation were included; 1562 embryos were analyzed from which 536 were transferred, and 371 embryos achieved the status of KID embryos. Therefore, we compared cases in which the two blastocysts transferred were TOP, compared to those cases in which only 1 being TOP. The twin gestation rate was significantly higher in those cases in which the number of TOP embryos (UAD ≤ 0.5) transferred was two 52% vs. 25% in one top group (P < .001). In cases in which a double embryo transfer was performed, the twin gestation rate was significantly higher when the two embryos were classified as TOP by the software, reaching very high values. In consequence, the selection method here presented, is a relevant strategy, to encourage single embryo transfer at least when two TOP blastocyst are available.

To apply Artificial Intelligence (AI) technology on time-lapse (TLM) embryo images and morphokinetic parameters to predict live birth. The morphokinetic parameters (n=131, ICSI only), with known live birth data from single blastocyst transfers, and 131 TLM images of embryos at 111.5 hours post ICSI were used to train (70%), validate (15%), and blindly test (15%) for prediction of live birth by an AI feature-extraction system. Inclusion criteria involved recipients from our oocyte donation program with single blastocyst transfer and non-PGT. Absolute and interim cleavage time points (t2 to t8) were used, along with 33 independent numerical variables extracted from standardized TLM images as an input data. The artificial neural network (ANN) architecture associated with the genetic algorithm was used to produce a predictable output of live birth. The efficacy of prediction of live birth was quantified and assessed using ROC curves, AUC and confusion matrices (True Positive -TP, True Negative -TN, False Positive -FP, and False Negative-FN). Overall accuracy of prediction of live birth by AI using morphokinetic data was 96.2% (126/131; TP= 37, TN= 69, FP= 1, FN= 4, AUC= 0.946). In the training dataset, the accuracy was 95.5% (86/91, AUC 0.96), and in the blind test dataset, accuracy was 100% (20/20, AUC=0,961). The overall accuracy of live birth by AI using image analysis was 90.1% (100/111, TP=39, TN= 61, FP= 7, FN= 4, AUC= 0.91). In the training dataset, the accuracy was 89% (81/91, AUC 0.887), and in the blind test dataset, accuracy was 95% (19/20, AUC=0.67-0.94). The combination of morphology and morphokinetics, the AUC for positive were similar (0.96) but for negative live birth were less predective (0.65). This is the first time that AI is used to evaluate human embryo quality using morphokinetic and morphological assessment in a data set of single embryo transfers from an oocyte donation program with known live birth. Our data suggests that AI can be used to enhance the efficacy of embryo selection performed by the standard morphology or the existing algorithms of morphokinetics. Applying AI in conjunction with morphokinetic or image analysis has the potential for being the platform of embryo selection, with similar predictive abilities when treated independently although its combination may not improve the performance of AI.

Objective: To develop a noninvasive embryo selection algorithm consisting of time-lapse morphokinetics and the oxidative status of the spent embryo culture medium determined using the Thermochemiluminescence (TCL) Analyzer. Design: Retrospective cohort. Setting: Not applicable. Patient(s): From women participating in the oocyte donation program, data from 505 samples of spent embryo culture media samples from 292 intracytoplasmic sperm injection cycles. Intervention(s): None. Main Outcome Measure(s): Morphokinetic parameters assessed during incubation in the time-lapse system Embryoscope. Oxidative parameters (H-1sm, H-2sm, and H-3sm) from the spent culture medium on day 5 of incubation measured using the TCL assay; and a combined assessment algorithm, including morphology, morphokinetics, and the embryo's culture medium oxidative status, developed as a tool for embryo selection, based on implantation success and confirmed ongoing pregnancy. Result(s): The levels of the oxidative parameters H-1sm, H-2sm, and H-3sm on day 5 of incubation were statistically significantly higher in transferred and vitrified embryos compared with discarded embryos and in successfully implanted embryos compared with those that did not result in pregnancy. The assessment algorithm resulted in a hierarchical classification with six embryo quality categories (A to F), associated with implantation rates of between 76.5% and 29.2%. Conclusion(s): An assessment algorithm combining morphology, morphokinetics and the embryo's culture medium oxidative status may help to improve current embryo selection methods criteria and in vitro fertilization success. (C) 2019 by American Society for Reproductive Medicine.