Use of artificial intelligence embryo selection based on static images to predict first-trimester pregnancy loss.

RESEARCH QUESTION: Can an artificial intelligence embryo selection assistant predict the incidence of first-trimester spontaneous abortion using static images of IVF embryos? DESIGN: In a blind, retrospective study, a cohort of 172 blastocysts from IVF cases with single embryo transfer and a positive biochemical pregnancy test was ranked retrospectively by the artificial intelligence morphometric algorithm ERICA. Making use of static embryo images from a light microscope, each blastocyst was assigned to one of four possible groups (optimal, good, fair or poor), and linear regression was used to correlate the results with the presence or absence of a normal fetal heart beat as an indicator of ongoing pregnancy or spontaneous abortion, respectively. Additional analyses included modelling for recipient age and chromosomal status established by preimplantation genetic testing for aneuploidy (PGT-A). RESULTS: Embryos classified as optimal/good had a lower incidence of spontaneous abortion (16.1%) compared with embryos classified as fair/poor (25%; OR = 0.46, P = 0.005). The incidence of spontaneous abortion in chromosomally normal embryos (determined by PGT-A) was 13.3% for optimal/good embryos and 20.0% for fair/poor embryos, although the difference was not significant (P = 0.531). There was a significant association between embryo rank and recipient age (P = 0.018), in that the incidence of spontaneous abortion was unexpectedly lower in older recipients (21.3% for age ≤35 years, 17.9% for age 36-38 years, 16.4% for age ≥39 years; OR = 0.354, P = 0.0181). Overall, these results support correlation between risk of spontaneous abortion and embryo rank as determined by artificial intelligence; classification accuracy was calculated to be 67.4%. CONCLUSIONS: This preliminary study suggests that artificial intelligence (ERICA), which was designed as a ranking system to assist with embryo transfer decisions and ploidy prediction, may also be useful to provide information for couples on the risk of spontaneous abortion. Future work will include a larger sample size and karyotyping of miscarried pregnancy tissue.

Outpatient paracentesis for the management of ovarian hyperstimulation syndrome: study protocol for the STOP-OHSS randomised controlled trial.

INTRODUCTION: Ovarian hyperstimulation syndrome (OHSS) is the most significant short-term complication of pharmacological ovarian stimulation. Symptoms range from mild abdominal discomfort to rare complications such as renal failure, thromboembolism and respiratory distress syndrome.Currently, clinical practice typically involves monitoring the patient until the condition becomes severe, at which point they are admitted to hospital, where drainage of ascitic fluid (paracentesis) may take place. Preliminary studies have indicated that earlier outpatient paracentesis may reduce the progression of OHSS and prevent hospitalisation in women. METHODS AND ANALYSIS: This UK, multicentre, pragmatic, two-arm, parallel-group, adaptive (group sequential with one interim analysis), open-label, superiority, confirmatory, group sequential, individually randomised controlled trial, with internal pilot will assess the clinical and cost-effectiveness and safety of outpatient paracentesis versus conservative management (usual care) for moderate or severe OHSS. 224 women from 20 National Health Service and private fertility units will be randomised (1:1) and followed up for up to 13.5 months. The primary outcome is the rate of OHSS related hospital admission of at least 24 hours within 28 days postrandomisation. The primary analysis will be an intention to treat with difference in hospitalisation rates as measure of treatment effect. Secondary outcomes include time to resolution of symptoms, patient satisfaction, adverse events and cost-effectiveness. A qualitative substudy will facilitate the feasibility of recruitment. Participant recruitment commenced in June 2022. ETHICS AND DISSEMINATION: London-Southeast Research Ethics Committee approved the protocol (reference: 22/LO/0015). Findings will be submitted to peer-reviewed journals and abstracts to relevant national and international conferences, as well as being disseminated to trial participants and patient groups. TRIAL REGISTRATION NUMBER: ISRCTN71978064.

Implantation in the lower half of the uterine cavity and decreased trophoblastic thickness can predict subsequent miscarriage: a prospective cohort study.

Abstract: Embryo implantation is vital for successful conception but remains to be fully understood. Trophoblast invasion is key for implantation, with anchorage and depth of placentation determined by its extent. There is a dearth of synchronous information regarding IVF, implantation site, and trophoblastic thickness (TT). Our aim was to determine whether pregnancy implantation site and TT, had an impact on outcomes of IVF pregnancies. This prospective observational study was undertaken at a tertiary referral UK fertility unit over 14 months, collecting data on implantation site and TT from three-dimensional (3D) images of the uterus following early pregnancy scan. Of the 300 women recruited, 277 (92%) had live births, 20 (7%) miscarried, 2 (0.7%) had stillbirths, and 1 (0.3%) had a termination. Significantly more pregnancies that resulted in miscarriage (7/20, 35%) were located in the lower uterine cavity when compared to ongoing pregnancies (15/277, 5%) (P < 0.01). TT was significantly higher in ongoing pregnancies when compared with those who miscarried (7.2 mm vs 5.5 mm; P < 0.01). Implantation in the lower half of the uterine cavity and decreased TT are significantly associated with an increased rate of miscarriage. Identification of those at risk should prompt increased monitoring with the aim of supporting these pregnancies. Lay summary: Implantation of an embryo in the womb is vital for a successful pregnancy. We wanted to find out whether findings on an ultrasound scan in early pregnancy had an impact on outcomes of IVF pregnancies. Three hundred women were recruited to the study, 277 (92%) had live births and unfortunately 20 (7%) had a miscarriage, 2 (0.7%) had stillbirths, and 1 (0.3%) had a termination. Many more of the pregnancies that miscarried implanted in the lower part of the womb. The thickness of the infiltration of the pregnancy into the womb was significantly higher in the ongoing pregnancies. We concluded that implantation in the lower half of the womb and reduced infiltration of the pregnancy seen on scan are associated with an increased rate of miscarriage. We propose that when we identify those at risk, we should increase monitoring, with the aim of supporting these pregnancies.

Automated identification of blastocyst regions at different development stages.

The selection of the best single blastocyst for transfer is typically based on the assessment of the morphological characteristics of the zona pellucida (ZP), trophectoderm (TE), blastocoel (BC), and inner cell-mass (ICM), using subjective and observer-dependent grading protocols. We propose the first automatic method for segmenting all morphological structures during the different developmental stages of the blastocyst (i.e., expansion, hatching, and hatched). Our database contains 592 original raw images that were augmented to 2132 for training and 55 for validation. The mean Dice similarity coefficient (DSC) was 0.87 for all pixels, and for the BC, BG (background), ICM, TE, and ZP was 0.85, 0.96, 0.54, 0.63, and 0.71, respectively. Additionally, we tested our method against a public repository of 249 images resulting in accuracies of 0.96 and 0.93 and DSC of 0.67 and 0.67 for ICM and TE, respectively. A sensitivity analysis demonstrated that our method is robust, especially for the BC, BG, TE, and ZP. It is concluded that our approach can automatically segment blastocysts from different laboratory settings and developmental phases of the blastocysts, all within a single pipeline. This approach could increase the knowledge base for embryo selection.

Habitual physical activity levels in women attending the one stop infertility clinic: A prospective cross-sectional observational study.

Optimisation of lifestyle factors such as smoking and alcohol are encouraged to improve fecundability rates in the fertility setting. Currently, routine fertility consultations do not involve counselling or imparting advice regarding habitual physical activity (PA) and/or structured exercise, despite data showing that vigorous PA can be associated with delayed time to pregnancy. Therefore, this study aimed to determine habitual PA in a sample of women attending the one stop infertility (OSI) clinic. 250 women attending a large tertiary level NHS fertility unit prospectively anonymously completed a questionnaire over a period of 9 months. Participant's (mean age 34±5years, mean BMI 29±7kg/m2) habitual PA levels varied from vigorous exercise on ≥5 days/week (8%, n=17), to no moderate or high intensity activities across the whole week (66%, n=29). The majority of women reported no structured exercise (72%, n=179). No association was identified between any domain of PA and BMI, age, alcohol units, regular periods, or time spent trying to conceive (P > 0.05). Participant's habitual PA levels varied widely and no association between any domain of PA and background of the women was identified. No existing evidence and/or guidelines to explicitly inform women attempting to conceive regarding recommended PA levels are available, despite PA being a modifiable, affordable, and feasible lifestyle choice with the possible potential to improve fertility. A large-scale, clinical trial assessing effects of PA on fecundability is warranted to gain insights into the potential of this lifestyle factor to improve fertility outcomes and to explore the underlying biological mechanisms involved.

Computer software (SiD) assisted real-time single sperm selection associated with fertilization and blastocyst formation.

RESEARCH QUESTION: Is it possible to explore an association between individual sperm kinematics evaluated in real time and spermatozoa selected by an embryologist for intracytoplasmic sperm injection (ICSI), with subsequent normal fertilization and blastocyst formation using a novel artificial vision-based software (SiD V1.0; IVF 2.0, UK)? DESIGN: ICSI procedures were randomly video recorded and subjected to analysis using SiD V1.0, proprietary software developed by our group. In total, 383 individual spermatozoa were retrospectively analysed from a dataset of 78 ICSI-assisted reproductive technology cycles. SiD software computes the progressive motility parameters, straight-line velocity (VSL) and linearity of the curvilinear path (LIN), of each sperm trajectory, along with a quantitative value, head movement pattern (HMP), which is an indicator of the characteristics of the sperm head movement patterns. The mean VSL, LIN and HMP measurements for each set of spermatozoa were compared based on different outcome measures. RESULTS: Statistically significant differences were found in VSL, LIN and HMP among those spermatozoa selected for injection (P < 0.001). Additionally, LIN and HMP were found to be significantly different between successful and unsuccessful fertilization (P = 0.038 and P = 0.029, respectively). Additionally, significantly higher SiD scores were found for those spermatozoa that achieved both successful fertilization (P = 0.004) and blastocyst formation (P = 0.013). CONCLUSION: The possibility of carrying out real-time analyses of individual spermatozoa using an automatic tool such as SiD creates the opportunity to assist the embryologist in selecting the better spermatozoon for injection in an ICSI procedure.

The Role of Endometrial Stem/Progenitor Cells in Recurrent Reproductive Failure.

Recurrent implantation failure (RIF) and recurrent pregnancy loss (RPL), collectively referred to as recurrent reproductive failure (RRF), are both challenging conditions with many unanswered questions relating to causes and management options. Both conditions are proposed to be related to an aberrant endometrial microenvironment, with different proposed aetiologies related to a restrictive or permissive endometrium for an invading embryo. The impressive regenerative capacity of the human endometrium has been well-established and has led to the isolation and characterisation of several subtypes of endometrial stem/progenitor cells (eSPCs). eSPCs are known to be involved in the pathogenesis of endometrium-related disorders (such as endometriosis) and have been proposed to be implicated in the pathogenesis of RRF. This review appraises the current knowledge of eSPCs, and their involvement in RRF, highlighting the considerable unknown aspects in this field, and providing avenues for future research to facilitate much-needed advances in the diagnosis and management of millions of women suffering with RRF.

Altered endometrial oestrogen-responsiveness and recurrent reproductive failure.

Abstract: Recurrent reproductive failure (RRF) encompasses recurrent implantation failure (RIF) and recurrent pregnancy loss (RPL). These highly prevalent, distressing conditions have many unanswered questions regarding aetiology and management. Oestrogen receptor beta (ERß) is the predominant oestrogen receptor expressed in the vascular endothelium of the endometrium during the window of implantation (WOI). The establishment of normal endometrial receptivity is integrally associated with progesterone receptor (PR). Therefore, we aimed to investigate whether women with RRF have clinical, type-specific endometrial aberrations of ERß, PR and Ki-67 expression during the WOI. Thirty-eight endometrial biopsies were collected; 29 RRF (10 RIF, 9 recurrent loss of early pregnancy (RLEP) and 10 recurrent fetal loss (RFL)) and 9 fertile controls (FC). Within RIF, RLEP and RFL groups, the perivascular compartment showed significantly lower levels of ERß vs FC (P = 0.02, P = 0.03 and P = 0.01, respectively). Vascular endothelium also displayed significantly lower levels of ERß within RIF and RFL cohorts vs FC (P = 0.03 and P = 0.003). The expression of Ki-67 was significantly lower within vascular endothelium of all RRF; RIF (P = 0.02), RLEP (P = 0.02) and RFL (P <0.01). PR was significantly reduced (P <0.001) in the perivascular area of women with RIF. These findings provide novel insights into biological correlates of clinical subtypes of RRF. The endometrium of women with RRF display significantly altered levels of ERß, PR and Ki-67 during the WOI, furthering our understanding of the defective endometrial phenotype of women suffering from RRF, with possible impaired glandular function, angiogenesis and decidualisation. Lay summary: Recurrent reproductive failure (RRF) refers to a group of devastating conditions with many unanswered questions regarding their causes and treatment options. The lining of the womb, the endometrium, is primed and suitable for successful embryo implantation for a short time during the menstrual cycle; the window of implantation (WOI). Oestrogen is a key hormone that plays an important role in regulating the endometrium and its effects are exerted via two oestrogen receptor subtypes. Oestrogen receptor beta (ERß) is the main oestrogen receptor present during the WOI. Progesterone receptor allows the other main hormone, progesterone, to influence the endometrial activity and Ki-67 reflects the proliferative activity of the cells within the endometrium. We investigated the expression of these markers in endometrial samples collected from women with RRF and proven fertility. We found that the endometrium of women with RRF has significantly lower levels of ERß and Ki-67 during the WOI, possibly leading to unsuccessful pregnancies.

National Survey Highlights the Urgent Need for Standardisation of Embryo Transfer Techniques in the UK.

Embryo transfer (ET) is one of the vital steps in the in vitro fertilisation (IVF) process, yet there is wide variation in ET technique throughout the UK, without a nationally approved standardised approach. The aim of this study was to gain contemporaneous information regarding the current clinical ET practice in the UK. METHOD: A 38-question electronic survey was distributed to the 79 UK Human Fertilisation and Embryology Authority (HFEA) registered clinics performing ETs. RESULTS: In total, 59% (47/79) of units responded, 83% (39/47) performing ultrasound-guided transfers, with 42% (20/47) of units using a tenaculum; 22% (10/45) would proceed with transfer regardless of fluid in the endometrial cavity. In 91% (43/47) of units, embryos were deposited in the upper/middle portion of the uterine cavity, but interpretation of this area ranged from 0.5 to >2 cm from the fundus, with 68% (32/47) allowing patients to mobilise immediately after transfer. In 60% (27/45) of clinics, success rates were based on clinical pregnancy rates (CPR). CONCLUSION: Within the UK there is a wide range of variability in ET techniques, with >70% of discordance in survey-responses between clinics. Whilst there are areas of good practice, some disadvantageous techniques continue to persist. This survey emphasises the importance of developing a standardised, evidence-based approach to improve ET success rates.

A randomised controlled trial to assess the clinical effectiveness and safety of the endometrial scratch procedure prior to first-time IVF, with or without ICSI.

STUDY QUESTION: What is the clinical-effectiveness and safety of the endometrial scratch (ES) procedure compared to no ES, prior to usual first time in vitro fertilisation (IVF) treatment? SUMMARY ANSWER: ES was safe but did not improve pregnancy outcomes when performed in the mid-luteal phase prior to the first IVF cycle, with or without intracytoplasmic sperm injection (ICSI). WHAT IS KNOWN ALREADY: ES is an 'add-on' treatment that is available to women undergoing a first cycle of IVF, with or without ICSI, despite a lack of evidence to support its use. STUDY DESIGN, SIZE, DURATION: This pragmatic, superiority, open-label, multi-centre, parallel-group randomised controlled trial involving 1048 women assessed the clinical effectiveness and safety of the ES procedure prior to first time IVF, with or without ICSI, between July 2016 and October 2019. PARTICIPANTS/MATERIALS, SETTING, METHODS: Participants aged 18-37 years undergoing their first cycle of IVF, with or without ICSI, were recruited from 16 UK fertility clinics and randomised (1:1) by a web-based system with restricted access rights that concealed allocation. Stratified block randomisation was used to allocate participants to TAU or ES in the mid-luteal phase followed by usual IVF with or without ICSI treatment. The primary outcome was live birth after completing 24 weeks gestation within 10.5 months of egg collection. MAIN RESULTS AND THE ROLE OF CHANCE: In total, 1048 women randomised to TAU (n = 525) and ES (n = 523) were available for intention to treat analysis. In the ES group, 453 (86.6%) received the ES procedure. IVF, with or without ICSI, was received in 494 (94.1%) and 497 (95.0%) of ES and TAU participants respectively. Live birth rate was 37.1% (195/525) in the TAU and 38.6% (202/523) in the ES: an unadjusted absolute difference of 1.5% (95% CI -4.4% to 7.4%, P = 0.621). There were no statistical differences in secondary outcomes. Adverse events were comparable across groups. LIMITATIONS, REASONS FOR CAUTION: A sham ES procedure was not undertaken in the control group, however, we do not believe this would have influenced the results as objective fertility outcomes were used. WIDER IMPLICATIONS OF THE FINDINGS: This is the largest trial that is adequately powered to assess the impact of ES on women undergoing their first cycle of IVF. ES was safe, but did not significantly improve pregnancy outcomes when performed in the mid-luteal phase prior to the first IVF or ICSI cycle. We recommend that ES is not undertaken in this population. STUDY FUNDING/COMPETING INTEREST(S): Funded by the National Institute of Health Research. Stephen Walters is an National Institute for Health Research (NIHR) Senior Investigator (2018 to present) and was a member of the following during the project: National Institute for Health Research (NIHR) Health Technology Assessment (HTA) Clinical Trials and Evaluation Committee (2011-2017), NIHR HTA Commissioning Strategy Group (2012 to 2017); NIHR Programme Grants for Applied Research Committee (2020 to present); NIHR Pre doctoral Fellowship Committee (2019 to present). Dr. Martins da Silva reports grants from AstraZeneca, during the conduct of the study; and is Associate editor of Human Reproduction and Editorial Board member of Reproduction and Fertility. Dr. Bhide reports grants from Bart's Charity and grants and non-financial support from Pharmasure Pharmaceuticals outside the submitted work. TRIAL REGISTRATION NUMBER: ISRCTN number: ISRCTN23800982. TRIAL REGISTRATION DATE: 31 May 2016. DATE OF FIRST PATIENT'S ENROLMENT: 04 July 2016.

Omics and Artificial Intelligence to Improve In Vitro Fertilization (IVF) Success: A Proposed Protocol.

The prediction of in vitro fertilization (IVF) outcome is an imperative achievement in assisted reproduction, substantially aiding infertile couples, health systems and communities. To date, the assessment of infertile couples depends on medical/reproductive history, biochemical indications and investigations of the reproductive tract, along with data obtained from previous IVF cycles, if any. Our project aims to develop a novel tool, integrating omics and artificial intelligence, to propose optimal treatment options and enhance treatment success rates. For this purpose, we will proceed with the following: (1) recording subfertile couples' lifestyle and demographic parameters and previous IVF cycle characteristics; (2) measurement and evaluation of metabolomics, transcriptomics and biomarkers, and deep machine learning assessment of the oocyte, sperm and embryo; (3) creation of artificial neural network models to increase objectivity and accuracy in comparison to traditional techniques for the improvement of the success rates of IVF cycles following an IVF failure. Therefore, "omics" data are a valuable parameter for embryo selection optimization and promoting personalized IVF treatment. "Omics" combined with predictive models will substantially promote health management individualization; contribute to the successful treatment of infertile couples, particularly those with unexplained infertility or repeated implantation failures; and reduce multiple gestation rates.

Anterior Gradient Protein 3 and S100 Calcium-Binding Protein P Levels in Different Endometrial Epithelial Compartments May Play an Important Role in Recurrent Pregnancy Failure.

Recurrent implantation failure (RIF) and recurrent pregnancy loss (RPL) are distressing conditions without effective treatments. The luminal epithelium (LE) is integral in determining receptivity of the endometrium, whereas functionalis glands and stroma aid in nurturing early embryo development. Calcium signalling pathways are known to be of vital importance to embryo implantation and pregnancy establishment, and anterior gradient protein 3 (AGR3) and S100 calcium-binding protein P (S100P) are involved with these pathways. We initially examined 20 full-thickness endometrial biopsies from premenopausal women across the menstrual cycle to characterize levels of AGR3 protein in each endometrial sub-region at the cellular level. A further 53 endometrial pipelle biopsies collected in the window of implantation were subsequently assessed to determine differential endometrial AGR3 and S100P levels relevant to RIF (n = 13) and RPL (n = 10) in comparison with parous women (n = 30) using immunohistochemistry. Significantly higher AGR3 and S100P immunostaining was observed in ciliated cells of the LE of women with recurrent reproductive failure compared with parous women, suggesting aberrant subcellular location-associated pathophysiology for these conditions. The nuclear localisation of S100P may allow transcriptional regulatory function, which is necessary for implantation of a viable pregnancy. Further work is thus warranted to assess their utility as diagnostic/therapeutic targets.

ESHRE guideline: medically assisted reproduction in patients with a viral infection/disease.

STUDY QUESTION: What is the recommended management for medically assisted reproduction (MAR) in patients with a viral infection or disease, based on the best available evidence in the literature? SUMMARY ANSWER: The ESHRE guideline on MAR in patients with a viral infection/disease makes 78 recommendations on prevention of horizontal and vertical transmission before, during and after MAR, and the impact on its outcomes, and these also include recommendations regarding laboratory safety on the processing and storage of gametes and embryos testing positive for viral infections. WHAT IS KNOWN ALREADY: The development of new and improved anti-viral medications has resulted in improved life expectancy and quality of life for patients with viral infections/diseases. Patients of reproductive age are increasingly exploring their options for family creation. STUDY DESIGN SIZE DURATION: The guideline was developed according to the structured methodology for the development of ESHRE guidelines. After the formulation of nine key questions for six viruses (hepatitis B virus, hepatitis C virus, human immunodeficiency virus, human papilloma virus, human T-lymphotropic virus I/II and Zika virus) by a group of experts, literature searches and assessments were performed. Papers published up to 2 November 2020 and written in English were included in the review. Evidence was analyzed by female, male or couple testing positive for the virus. PARTICIPANTS/MATERIALS SETTING METHODS: Based on the collected evidence, recommendations were formulated and discussed until consensus was reached within the guideline group. There were 61 key questions to be answered by the guideline development group (GDG), of which 12 were answered as narrative questions and 49 as PICO (Patient, Intervention, Comparison, Outcome) questions. A stakeholder review was organized after the finalization of the draft. The final version was approved by the GDG and the ESHRE Executive Committee. MAIN RESULTS AND THE ROLE OF CHANCE: This guideline aims to help providers meet a growing demand for guidance on the management of patients with a viral infection/disease presenting in the fertility clinic.The guideline makes 78 recommendations on prevention of viral transmission before and during MAR, and interventions to reduce/avoid vertical transmission to the newborn. Preferred MAR treatments and interventions are described together with the effect of viral infections on outcomes. The GDG formulated 44 evidence-based recommendations-of which 37 were formulated as strong recommendations and 7 as weak-33 good practice points (GPP) and one research only recommendation. Of the evidence-based recommendations, none were supported by high-quality evidence, two by moderate-quality evidence, 15 by low-quality evidence and 27 by very low-quality evidence. To support future research in the field of MAR in patients with a viral infection/disease, a list of research recommendations is provided. LIMITATIONS REASONS FOR CAUTION: Most interventions included are not well-studied in patients with a viral infection/disease. For a large proportion of interventions, evidence was very limited and of very low quality. More evidence is required for these interventions, especially in the field of human papilloma virus (HPV). Such future studies may require the current recommendations to be revised. WIDER IMPLICATIONS OF THE FINDINGS: The guideline provides clinicians with clear advice on best practice in MAR for patients with a viral infection/disease, based on the best evidence currently available. In addition, a list of research recommendations is provided to stimulate further studies in the field. STUDY FUNDING/COMPETING INTERESTS: The guideline was developed and funded by ESHRE, covering expenses associated with the guideline meetings, with the literature searches and with the dissemination of the guideline. The guideline group members did not receive any financial incentives, all work was provided voluntarily. A.D. reports research fees from Ferring and Merck, consulting fees from Ferring, outside the submitted work. C.P. reports speakers fees from Merck and MSD outside the submitted work. K.T. reports speakers fees from Cooper Surgical and Ferring and consultancy fees as member of the advisory board BioTeam of Ferring, outside the submitted work. The other authors have no conflicts of interest to declare. DISCLAIMER: This guideline represents the views of ESHRE, which were achieved after careful consideration of the scientific evidence available at the time of preparation. In the absence of scientific evidence on certain aspects, a consensus between the relevant ESHRE stakeholders has been obtained. Adherence to these clinical practice guidelines does not guarantee a successful or specific outcome, nor does it establish a standard of care. Clinical practice guidelines do not replace the need for application of clinical judgment to each individual presentation, nor variations based on locality and facility type. ESHRE makes no warranty, express or implied, regarding the clinical practice guidelines and specifically excludes any warranties of merchantability and fitness for a particular use or purpose. (Full disclaimer available at  www.eshre.eu/guidelines.).

Data sharing: using blockchain and decentralized data technologies to unlock the potential of artificial intelligence: What can assisted reproduction learn from other areas of medicine?

The extension of blockchain use for nonfinancial domains has revealed opportunities to the health care sector that answer the need for efficient and effective data and information exchanges in a secure and transparent manner. Blockchain is relatively novel in health care and particularly for data analytics, although there are examples of improvements achieved. We provide a systematic review of blockchain uses within the health care industry, with a particular focus on the in vitro fertilization (IVF) field. Blockchain technology in the fertility sector, including data sharing collaborations compliant with ethical data handling within confines of international law, allows for large-scale prospective cohort studies to proceed at an international scale. Other opportunities include gamete donation and matching, consent sharing, and shared resources between different clinics.

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

Artificial intelligence (AI) systems have been proposed for reproductive medicine since 1997. Although AI is the main driver of emergent technologies in reproduction, such as robotics, Big Data, and internet of things, it will continue to be the engine for technological innovation for the foreseeable future. What does the future of AI research look like?

Embryo Ranking Intelligent Classification Algorithm (ERICA): artificial intelligence clinical assistant predicting embryo ploidy and implantation.

RESEARCH QUESTION: Can a deep machine learning artificial intelligence algorithm predict ploidy and implantation in a known data set of static blastocyst images, and how does its performance compare against chance and experienced embryologists? DESIGN: A database of blastocyst images with known outcome was applied with an algorithm dubbed ERICA (Embryo Ranking Intelligent Classification Algorithm). It was evaluated against its ability to predict euploidy, compare ploidy prediction against randomly assigned prognosis labels and against senior embryologists, and if it could rank an euploid embryo highly. RESULTS: A total of 1231 embryo images were classed as good prognosis if euploid and implanted or poor prognosis if aneuploid and failed to implant. An accuracy of 0.70 was obtained with ERICA, with positive predictive value of 0.79 for predicting euploidy. ERICA had greater normalized discontinued cumulative gain (ranking metric) than random selection (P = 0.0007), and both embryologists (P = 0.0014 and 0.0242, respectively). ERICA ranked an euploid blastocyst first in 78.9% and at least one euploid embryo within the top two blastocysts in 94.7% of cases, better than random classification and the two senior embryologists. Average embryo ranking time for four blastocysts was under 25 s. CONCLUSION: Artificial intelligence lends itself well to image pattern recognition. We have trained ERICA to rank embryos based on ploidy and implantation potential using single static embryo image. This tool represents a potentially significant advantage to assist embryologists to choose the best embryo, saving time spent annotating and does not require time lapse or invasive biopsy. Future work should be directed to evaluate reproducibility in different data sets.

Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning.

Assessing the viability of a blastosyst is still empirical and non-reproducible nowadays. We developed an algorithm based on artificial vision and machine learning (and other classifiers) that predicts pregnancy using the beta human chorionic gonadotropin (b-hCG) test from both the morphology of an embryo and the age of the patients. We employed two high-quality databases with known pregnancy outcomes (n = 221). We created a system consisting of different classifiers that is feed with novel morphometric features extracted from the digital micrographs, along with other non-morphometric data to predict pregnancy. It was evaluated using five different classifiers: probabilistic bayesian, Support Vector Machines (SVM), deep neural network, decision tree, and Random Forest (RF), using a k-fold cross validation to assess the model's generalization capabilities. In the database A, the SVM classifier achieved an F1 score of 0.74, and AUC of 0.77. In the database B the RF classifier obtained a F1 score of 0.71, and AUC of 0.75. Our results suggest that the system is able to predict a positive pregnancy test from a single digital image, offering a novel approach with the advantages of using a small database, being highly adaptable to different laboratory settings, and easy integration into clinical practice.

Aspirin for in vitro fertilisation.

BACKGROUND: Aspirin is used to improve the outcome in women undergoing in vitro fertilisation despite inconsistent evidence of its efficacy. The most appropriate time to commence aspirin therapy and the length of treatment required are also still to be determined. This is an update of the review first published in 2007. OBJECTIVES: To determine the effectiveness and safety of aspirin for improving the outcome of in vitro fertilisation and intracytoplasmic sperm injection treatment cycles. SEARCH STRATEGY: We searched the Cochrane Menstrual Disorders and Subfertility Group Trials Register, Cochrane Central Register of Controlled Trials (CENTRAL) (The Cochrane Library January 2011), MEDLINE (1966 to January 2011) and EMBASE (1980 to January 2011) databases. We used the research terms: "(aspirin OR acetylsalicylic acid) AND (in-vitro fertilisation OR intracytoplasmic sperm injection)", combined with the Cochrane Menstrual Disorders and Subfertility Group's search strategy, in order to identify randomised controlled trials on aspirin for women undergoing in vitro fertilisation. SELECTION CRITERIA: Randomised controlled trials. DATA COLLECTION AND ANALYSIS: Two authors independently selected studies to include in the review, extracted data and assessed trial quality. MAIN RESULTS: The searches identified 13 trials which were eligible for inclusion in the review, including a total of 2653 participants. No significant differences were found between the treatment and control groups for any of the outcomes assessed. No significant differences were found in the meta-analysis of studies investigating the effect of aspirin compared with control on live birth rate (RR 0.91, 95% CI 0.72 to 1.15; three studies and 1053 participants), clinical pregnancy rate (RR 1.03, 95% CI 0.91 to 1.17; 10 studies and 2142 participants), ectopic and miscarriage rates (RR 1.86, 95% CI 0.75 to 4.63; RR 1.10, 95% CI 0.68 to 1.77) respectively (three and five studies involving 1135 and 1497 participants). AUTHORS' CONCLUSIONS: Use of aspirin for women undergoing in vitro fertilisation cannot be recommended due to lack of evidence from the current trial data. Adequately powered trials are needed. It was proposed in the initial version of this review that a sample size of 350 women in each group would be required in order to demonstrate a 10% improvement from the use of aspirin, with 80% power at the 5% significance level. Until such evidence is available, this treatment can not be recommended.

A randomized controlled clinical trial of 2295 ultrasound-guided embryo transfers.

BACKGROUND: We wanted to test the hypothesis that using abdominal ultrasound at the time of embryo transfer to guide replacement, improved pregnancy rates by at least 5%. METHODS: An RCT in a large assisted conception unit. A pilot study and power calculation suggested that at least 2000 embryo transfers were required to demonstrate a difference of 5%, for a test with 80% power and Type 1 error 0.05. Randomization, data entry and analysis were arranged independently. Randomization was stratified for age and fresh/frozen embryo transfer. Analysis was by intention to treat. RESULTS: There was no difference in clinical pregnancy or live birth rates between the two groups. The clinical pregnancy rate for ultrasound-guided embryo transfer was 22% and for non-ultrasound-guided embryo transfer was 23% (odds ratio: 0.96; 95% confidence interval: 0.79-1.18). CONCLUSIONS: We set out to determine whether ultrasound-guided embryo transfer improved clinical pregnancy rates and live birth rates in assisted conception. We used an appropriately powered RCT design. We did not demonstrate a difference. This outcome is at odds with the UKs National Institute of Clinical Excellence recommendations for fertility treatment (Fertility Assessment and Treatment for People with Fertility Problems. London, UK: RCOG Press, 2004, 112.) which used a meta-analysis of four smaller trials (range 362-800 patients, totalling 2051 embryo transfers) to conclude that ultrasound should be offered. We suggest that the current Cochrane review should be updated with data from our trial and recommend that consideration is given to accounting for heterogeneity between the included trials.