Abstract
In the past few years almost every aspect of an IVF cycle has been investigated, including research on sperm, color doppler in follicular studies, prediction of embryo cleavage, prediction of blastocyst formation, scoring blastocyst quality, prediction of euploid blastocysts and live birth from blastocysts, improving the embryo selection process, and for developing deep machine learning (ML) algorithms for optimal IVF stimulation protocols. Also, artificial intelligence (AI)-based methods have been implemented for some clinical aspects of IVF, such as assessing patient reproductive potential and individualizing gonadotropin stimulation protocols. As AI has the inherent capacity to analyze "Big" data, the goal will be to apply AI tools to the analysis of all embryological, clinical, and genetic data to provide patient-tailored individualized treatments. Human skillsets including hand eye coordination to perform an embryo transfer is probably the only step of IVF that is outside the realm of AI & ML today. Embryo transfer success is presently human skill dependent and deep machine learning may one day intrude into this sacred space with the advent of programed humanoid robots. Embryo transfer is arguably the rate limiting step in the sequential events that complete an IVF cycle. Many variables play a role in the success of embryo transfer, including catheter type, atraumatic technique, and the use of sonography guidance before and during the procedure of embryo transfer. In contemporary Reproductive Medicine human beings are not yet dispensable.
Avoid common mistakes on your manuscript.
Introduction
Culturing of human embryos in optimal conditions is crucial for a successful in vitro fertilization (IVF) program. In addition, the capacity to assess and grade embryos correctly will allow for transfer of the potentially 'best' embryo first, thereby shortening the time to pregnancy. It will also encourage and facilitate the implementation of single embryo transfers (SET), thereby increasing maternal & fetal safety. An increasing trend in research funding toward artificial intelligence (AI) & deep machine learning (ML) has re-animated huge expectations for future applications. According to the earliest proponents of AI in IVF, embryo evaluation and selection embody the aggregate manifestation of the entire in vitro fertilization (IVF) process. Indeed, it is generally acknowledged that even after embryo selection based on morphology, time-lapse videos, or embryo biopsy with preimplantation genetic testing (PGT-A), implantation rates in the human are difficult to consistently predict. Recently, several artificial intelligence (AI)-based and deep machine learning (ML) algorithms have emerged as objective, standardized, and efficient tools for evaluating human embryos [1].
Discussion
Human Skillset is the Most Important Variable Influencing Success Rates with EMBRYO TRANSFER
Embryo transfer is a key stage in IVF, in which the skillset of the gynecologist itself determines the outcome. Few advances have occurred in the last few decades regarding the actual procedure of Embryo Transfer. Studies conducted thus far have focused on factors and interventions taking place before, during (with simulators) and after this procedure. Numerous methods, including the use of ultrasound guidance for proper catheter placement in the endometrial cavity, have been suggested as more effective techniques of embryo transfer [2,3,4]. The moot question is which factors and interventions have thus far been proven to increase pregnancy rates and live birth rates. Factors affecting pregnancy rates following ET include either abdominal or transvaginal ultrasound guidance, ease of passage of ET transfer, catheter type and build, the transfer technique, the catheter-loading technique, blood or mucus inside or outside the catheter lumen, retained embryos, mock transfer, the physician's training & experience, and catheter tip location. Despite the lack of consensus regarding the optimal ET technique, it is generally recommended that during ET, the disruption of the endometrium and the induction of uterine contractions should be avoided [4].
Difficult transfers should be avoided, as they reduce implantation and pregnancy rates. A total of 7,714 ETs were analyzed by Kava-Braverman et al. [5]. The clinical pregnancy rate (CPR) was significantly higher in the cases of easy ET compared with difficult ET (38.2% vs. 27.1%). Each instrumentation needed to successfully deposit the embryos in the fundus involved a progressive reduction in the CPR—use of outer catheter sheath, use of Wallace stylet & use of tenaculum. Poor ultrasound visualization significantly diminished the CPR. The CPR decreased progressively with the use of additional maneuvers during ET [5].
Artificial Intelligence & Machine Learning in IVF
Time-lapse technology (TLT) introduces the concept of stable culture conditions, in connection with the possibility of continuous viewing and documenting of the embryo throughout its development. However, so far, even when embryo quality scoring is based on large datasets, or when using TLT, the morphokinetic scores are still mainly based on subjective and intermittent annotations of morphology and set timings. Also, the application of strong algorithms for widespread use is hampered by large variations in culture conditions between individual IVF laboratory protocols. New methodology, involving deep machine learning, where every image from the time-lapse documentation is analyzed by an algorithm, looking for patterns that link to outcome, may in the future provide a more accurate and non-biased embryo selection process [6].
The conventional morphological assessment of embryos exhibits inevitable drawbacks which include time- and effort-consuming, and imminent risks of bias associated with subjective assessments performed by individual embryologists. A combination of these disadvantages, undeterred by the introduction of the time-lapse incubator technology, has been considered as a prominent contributor to the less preferable success rate of IVF cycles. An AI-powered assistant could improve the efficiency of performing certain tasks in addition to offering accurate algorithms that can inculcate objectivity and decrease subjectivity of the decision-making processes [7].
Sperms & AI
Although in vitro fertilization (IVF) facilitates the job of spermatozoa, a universally acceptable means of sperm selection is yet to be developed. Microfluidic devices, omics profiling, micronuclei studies, sperm plasma membrane markers, and other techniques, such as Magnetic Activated Cell Sorting (MACS), Raman micro-spectroscopy, and artificial intelligence systems offer fresh approaches to an old problem [8]. Kresch et al. identified multiple new promising technologies, each with its own distinct set of benefits and limitations, to enhance chances of sperm retrieval; these include the use of multiphoton microscopy, Raman spectroscopy, and full-field optical coherence tomography during a microdissection-testicular sperm extraction procedure [9]. Finally, artificial intelligence technology can play a role in the identification of sperm and, perhaps, better-quality sperm for use with assisted reproduction.
Artificial Intelligence & Ovarian Stimulation for IVF
Letterie & Mac Donald designed a computer algorithm for in vitro fertilization (IVF) management and set up a study to assess the algorithm's accuracy in the day-to-day decision making during ovarian stimulation for IVF when compared to evidence-based decisions by the clinical team [10]. The study described a first iteration of a predictive analytic algorithm that is highly accurate and in agreement with evidence-based decisions by expert teams during ovarian stimulation during IVF [10]. Can workflow during IVF be facilitated by artificial intelligence to limit monitoring during ovarian stimulation to a single day and enable level-loading of retrievals? A first-iteration algorithm described by Letterie et al. was designed to improve workflow, minimize visits and level-load embryology work [11]. Siristatidis et al. [12] penned down the construction and evaluation of an enhanced web-based system with a novel artificial neural network (ANN) architecture for a functional in vitro fertilization (IVF) prediction model.
Implantation Prediction Algorithms Studying the Endometrium
Mehrjerd et al. aimed to analyze the impact of endometrial thickness on the ongoing pregnancy rate in couples with unexplained infertility using deep machine learning & artificial intelligence based algorithms [13]. They obtained a 7.7 mm cut-off point for IUI and 9.99 mm for IVF/ICSI treatment. The results showed machine learning is a valuable tool in predicting ongoing pregnancy and is trustable via multicenter data for the two subject treatments.
Combining RNA sequencing data (transcriptomics) with artificial intelligence (AI) led to a clinical revolution in personalizing disease diagnosis and fostered the concept of precision medicine.
Translation of endometrial transcriptomics to the clinic yielded an objective definition of the limited time during which the maternal endometrium is receptive to an embryo, known as the window of implantation (WOI). Personalized embryo transfer (pET) may be possible by synchronizing embryo transfer with each patient's WOI [14].
Artificial Intelligence-Aided Ultrasound
Artificial intelligence (AI) has gradually become an effective supplementary method for the assessment of female reproductive function. It has been used in clinical follicular monitoring, optimum timing for embryo transfer, and prediction of pregnancy outcome. Chen et al. published the applicability, feasibility, and value of clinical application of AI in ultrasound to monitor follicles, assess endometrial receptivity, and predict the pregnancy outcome of in vitro fertilization and embryo transfer (IVF-ET) [15].
AI-based Algorithm Using Cytoplasm Movement Velocity of Embryos to predict Blastulation
In a proof-of-principle study, 230 human preimplantation embryos were retrospectively assessed using an artificial neural network [16]. After intracytoplasmic sperm injection, embryos underwent time-lapse monitoring for 44 h. In the experimental approach, in embryos that developed to blastocyst or destined to arrest, cytoplasm movement velocity was recorded by time-lapse monitoring during the first 44 h of culture and analyzed with a Particle Image Velocimetry algorithm to extract quantitative information. This study suggests the possibility of predicting human blastocyst development at early cleavage stages by detection of cytoplasm movement velocity and artificial intelligence analysis [16].
Artificial Vision Morphometry-Based Implantation Prediction Algorithms
Assessing the viability of a blastocyst is still empirical and non-reproducible nowadays. Chavez Badiola et al. developed an algorithm based on artificial vision and machine learning that predicts pregnancy from both the morphology of an embryo and the age of the patients. Their results suggest that the system can 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 with easy integration into clinical practice [17]. VerMilyea et al. have combined computer vision image processing methods and deep learning techniques to create the non-invasive Life Whisperer AI model for robust prediction of embryo viability, as measured by clinical pregnancy outcome, using single static images of Day 5 blastocysts obtained from standard optical light microscope systems [18].These studies demonstrated an improved predictive ability for evaluation of embryo viability when compared with embryologists' traditional morphokinetic grading methods.
Artificial Vision Morphometry-Based Euploidy Prediction Algorithm
The genetics AI model was trained using static two-dimensional optical light microscope images of Day 5 blastocysts with linked genetic metadata obtained from PGT-A [19]. The endpoint was ploidy status (euploid or aneuploid) based on PGT-A results. 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. 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 [19].
Time Lapse Technology-Based Euploidy Prediction Algorithm
Currently, evaluation of embryo genetic status is most 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. TLT has the characteristics of large amount of data and non-invasiveness. If we want to accurately predict embryo ploidy status from TLT, artificial intelligence (AI) technology is a good choice. A total of 469 preimplantation genetic testing (PGT) cycles and 1803 blastocysts from April 2018 to November 2019 were included in Huang’s study [20]. Their AI model named EPA can predict embryo ploidy well based on TLT data [20].
Time Lapse Technology-Based Live Birth Prediction Algorithms
An AI system was created by using the Attention Branch Network associated with deep learning to predict the probability of live birth from 141,444 images recorded by time-lapse imaging of 470 transferred embryos, of which 91 resulted in live birth and 379 resulted in non-live birth that included implantation failure, biochemical pregnancy and clinical miscarriage [21]. The authors concluded that an AI system with a confidence score that is useful for non-invasive selection of embryos that could result in live birth [21].
AI Algorithm Using Artificial Vision Morphometry & Spent Culture Media & for Live Birth Prediction of Euploid Embryos
Bori et al. set up a 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 [22]. A single image of each of 186 embryos were studied, and the protein profile was analyzed in 81 samples of spent embryo culture medium from patients included in the preimplantation genetic testing program. 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 [22].
Raw Time-Lapse Videos-based Deep Machine Learning Implantation Prediction Algorithm
Tran et al. [23] created a deep learning model named IVY, which was an objective and fully automated system that predicts the probability of FH pregnancy directly from raw time-lapse videos without the need for any manual morphokinetic annotation or blastocyst morphology assessment. This study was a retrospective analysis of time-lapse videos and clinical outcomes of 10 638 embryos from eight different IVF clinics, across four different countries, between January 2014 and December 2018 [23].
AI Ranked Metabolic Activity-Based Implantation Prediction Algorithm
Morphological and morphokinetic analyses utilized in embryo selection provide insight into developmental potential, but alone are unable to provide a direct measure of embryo physiology and inherent health. Glucose uptake is a physiological biomarker of viability and amino acid utilization is different between embryos of varying qualities. Blastocysts with higher developmental potential and a higher probability of resulting in a viable pregnancy consume higher levels of glucose and exhibit distinct amino acid profiles. Embryos were individually cultured in a time-lapse incubator system, and those reaching the blastocyst stage had their morphokinetics annotated and were each assigned a Gardner grade, KID Score and Embryo Score. Glucose and amino acid metabolism were measured. Glucose consumption was at least 40% higher in blastocysts deemed of high developmental potential using either the Gardner grade, KID Score or Embryo Score, compared to less viable blastocysts and in blastocysts that resulted in a clinical pregnancy compared to those that failed to. Additionally, duration of cavitation was inversely related to glucose consumption. These results confirm that metabolites, such as glucose and amino acids, are valid biomarkers of embryo viability and could therefore be used in conjunction with other systems to aid in the selection of a healthy embryo [24].
Conclusions
Despite the many advances in the field of medically assisted reproduction, accurately predicting the outcome of an IVF cycle has yet to be achieved. One probable reason for this is the method of selecting an embryo for transfer. Morphological assessment of embryos is the traditional method of evaluating embryo quality and selecting which embryo to transfer. However, this subjective method of assessing embryos leads to inter- and intra-observer variability, resulting in less-than-optimal IVF success rates. To overcome this, it is common practice to transfer more than one embryo, potentially resulting in high-risk multiple pregnancies. Although time-lapse incubators and preimplantation genetic testing for aneuploidy have been introduced to help increase the chances of live birth, the outcomes remain less than ideal. Utilization of artificial intelligence (AI) has become increasingly popular in the medical field and is increasingly being leveraged in the embryology laboratory to help improve IVF outcomes [25,26,27,28,29,30,31,32,33,34]. And assume we have the perfect AI + ML algorithm for prediction of the correct embryo that will implant and give rise to a live birth, you will still need a skilled gynecologist who will safely and successfully transfer this embryo into the AI + ML ranked receptive uterus. In contemporary Reproductive Medicine human beings are yet not dispensable!
References
Curchoe CL, Bormann CL. Artificial intelligence and machine learning for human reproduction and embryology presented at ASRM and ESHRE 2018. J Assist Reprod Genet. 2019;36(4):591–600. https://doi.org/10.1007/s10815-019-01408-x.
Allahbadia GN. Ultrasonography-guided embryo transfer: evidence-based practice. In: Rizk BRMB editor. Ultrasonography in Reproductive Medicine and Infertility, Cambridge University Press. © Cambridge University Press; 2010.
Allahbadia GN, Kadam K, Gandhi G, et al. Embryo transfer using the SureView catheter-beacon in the womb. Fertil Steril. 2010;93(2):344–50.
Allahbadia GN. Embryo transfer. New Delhi: Jaypee Brothers Medical Publishers; 2008. p. 558.
Kava-Braverman A, Martínez F, Rodríguez I, et al. What is a difficult transfer? Analysis of 7,714 embryo transfers: the impact of maneuvers during embryo transfers on pregnancy rate and a proposal of objective assessment. Fertil Steril. 2017;107(3):657-663.e1. https://doi.org/10.1016/j.fertnstert.2016.11.020.
Lundin K, Park H. Time-lapse technology for embryo culture and selection. Ups J Med Sci. 2020;125(2):77–84. https://doi.org/10.1080/03009734.2020.1728444.
Louis CM, Erwin A, Handayani N, et al. Review of computer vision application in in vitro fertilization: the application of deep learning-based computer vision technology in the world of IVF. J Assist Reprod Genet. 2021;38(7):1627–39. https://doi.org/10.1007/s10815-021-02123-2.
Pedrosa ML, Furtado MH, Ferreira MCF, Carneiro MM. Sperm selection in IVF: the long and winding road from bench to bedside. JBRA Assist Reprod. 2020;24(3):332–9. https://doi.org/10.5935/1518-0557.20190081.
Kresch E, Efimenko I, Gonzalez D, et al. Novel methods to enhance surgical sperm retrieval: a systematic review. Arab J Urol. 2021;19(3):227–37. https://doi.org/10.1080/2090598X.2021.1926752.
Letterie G, Mac Donald A. Artificial intelligence in in vitro fertilization: a computer decision support system for day-to-day management of ovarian stimulation during in vitro fertilization. Fertil Steril. 2020;114(5):1026–31. https://doi.org/10.1016/j.fertnstert.2020.06.006.
Letterie G, MacDonald A, Shi Z. An artificial intelligence platform to optimize workflow during ovarian stimulation and IVF: process improvement and outcome-based predictions. Reprod Biomed Online. 2022;44(2):254–60. https://doi.org/10.1016/j.rbmo.2021.10.006.
Siristatidis C, Vogiatzi P, Pouliakis A, et al. Predicting IVF Outcome: a proposed web-based system using artificial intelligence. In Vivo. 2016;30(4):507–12.
Mehrjerd A, Rezaei H, Eslami S, Khadem GN. Determination of cut off for endometrial thickness in couples with unexplained infertility: trustable AI. Stud Health Technol Inform. 2022;294:264–8. https://doi.org/10.3233/SHTI220450.
Ruiz-Alonso M, Valbuena D, Gomez C, et al. Endometrial receptivity analysis (ERA): data versus opinions. Hum Reprod Open. 2021;2021(2):hoab011. https://doi.org/10.1093/hropen/hoab011.
Chen Z, Wang Z, Du M, Liu Z. Artificial Intelligence in the assessment of female reproductive function using ultrasound: a review. J Ultrasound Med. 2022;41(6):1343–53. https://doi.org/10.1002/jum.15827.
Coticchio G, Fiorentino G, Nicora G, et al. Cytoplasmic movements of the early human embryo: imaging and artificial intelligence to predict blastocyst development. Reprod Biomed Online. 2021;42(3):521–8. https://doi.org/10.1016/j.rbmo.2020.12.008.
Chavez-Badiola A, Flores-Saiffe Farias A, Mendizabal-Ruiz G, et al. Predicting pregnancy test results after embryo transfer by image feature extraction and analysis using machine learning. Sci Rep. 2020;10(1):4394. https://doi.org/10.1038/s41598-020-61357-9.
VerMilyea M, Hall JMM, Diakiw SM, et al. Development of an artificial intelligence-based assessment model for prediction of embryo viability using static images captured by optical light microscopy during IVF. Hum Reprod. 2020;35(4):770–84. https://doi.org/10.1093/humrep/deaa013.
Diakiw SM, Hall JMM, VerMilyea MD, et al. Development of an artificial intelligence model for predicting the likelihood of human embryo euploidy based on blastocyst images from multiple imaging systems during IVF. Hum Reprod. 2022;37(8):1746–59. https://doi.org/10.1093/humrep/deac131.
Huang B, Tan W, Li Z, Jin L. An artificial intelligence model (euploid prediction algorithm) can predict embryo ploidy status based on time-lapse data. Reprod Biol Endocrinol. 2021;19(1):185. https://doi.org/10.1186/s12958-021-00864-4.
Sawada Y, Sato T, Nagaya M, et al. Evaluation of artificial intelligence using time-lapse images of IVF embryos to predict live birth. Reprod Biomed Online. 2021;43(5):843–52. https://doi.org/10.1016/j.rbmo.2021.05.002.
Bori L, Dominguez F, Fernandez EI, et al. An artificial intelligence model based on the proteomic profile of euploid embryos and blastocyst morphology: a preliminary study. Reprod Biomed Online. 2021;42(2):340–50. https://doi.org/10.1016/j.rbmo.2020.09.031.
Tran D, Cooke S, Illingworth PJ, Gardner DK. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum Reprod. 2019;34(6):1011–8. https://doi.org/10.1093/humrep/dez064.
Ferrick L, Lee YSL, Gardner DK. Metabolic activity of human blastocysts correlates with their morphokinetics, morphological grade, KIDScore and artificial intelligence ranking. Hum Reprod. 2020;35(9):2004–16. https://doi.org/10.1093/humrep/deaa181.
Dimitriadis I, Zaninovic N, Badiola AC, Bormann CL. Artificial intelligence in the embryology laboratory: a review. Reprod Biomed Online. 2022;44(3):435–48. https://doi.org/10.1016/j.rbmo.2021.11.003.
Zaninovic N, Rosenwaks Z. Artificial intelligence in human in vitro fertilization and embryology. Fertil Steril. 2020;114(5):914–20. https://doi.org/10.1016/j.fertnstert.2020.09.157.
Siristatidis C, Stavros S, Drakeley A, et al. Omics and artificial intelligence to improve in vitro fertilization (IVF) success: a proposed protocol. Diagnostics. 2021;11(5):743. https://doi.org/10.3390/diagnostics11050743.
Trolice MP, Curchoe C, Quaas AM. Artificial intelligence-the future is now. J Assist Reprod Genet. 2021;38(7):1607–12. https://doi.org/10.1007/s10815-021-02272-4.
Chow DJX, Wijesinghe P, Dholakia K, Dunning KR. Does artificial intelligence have a role in the IVF clinic? Reprod Fertil. 2021;2(3):C29–34. https://doi.org/10.1530/RAF-21-0043.
Kragh MF, Karstoft H. Embryo selection with artificial intelligence: how to evaluate and compare methods? Embryo selection with artificial intelligence: how to evaluate and compare methods? J Assist Reprod Genet. 2021;38(7):1675–89. https://doi.org/10.1007/s10815-021-02254-6.
Doody KJ. Infertility treatment now and in the future. Obstet Gynecol Clin North Am. 2021;48(4):801–12. https://doi.org/10.1016/j.ogc.2021.07.005.
Matorras R, Valls R, Azkargorta M, et al. Proteomics based drug repositioning applied to improve in vitro fertilization implantation: an artificial intelligence model. Syst Biol Reprod Med. 2021;67(4):281–97. https://doi.org/10.1080/19396368.2021.1928792.
Molina M, Ramasamy R, Geller J, et al. An artificial intelligence-based algorithm for predicting pregnancy success using static images captured by optical light microscopy during intracytoplasmic sperm injection. J Hum Reprod Sci. 2021;14(3):288–92. https://doi.org/10.4103/jhrs.jhrs_53_21.
Fernandez EI, Ferreira AS, Cecílio MHM, et al. Artificial intelligence in the IVF laboratory: overview through the application of different types of algorithms for the classification of reproductive data. J Assist Reprod Genet. 2020;37(10):2359–76. https://doi.org/10.1007/s10815-020-01881-9.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Dr Gautam N Allahbadia is an Editor Emeritus of the Journal of Obstetrics & Gynecology of India as well as the Journal of Minimal Stimulation IVF and Founder Mentor of Rotunda-CHR, Parel, Mumbai. He is presently the Medical Director & Consultant Reproductive Endocrinology & IVF at MMC IVF, DHCC, Dubai, UAE; Swati G Allahbadia is a Consultant Obstetrics, Gynecology & IVF Rotunda-CHR, Parel, Mumbai Golbal Hospital, Parel, Mumbai; Akanksha A Gupta is a Consultant Obstetrcs, Gynecology & IVF Sumitra Hospital, NOIDA, UP.
Rights and permissions
About this article
Cite this article
Allahbadia, G.N., Allahbadia, S.G. & Gupta, A. In Contemporary Reproductive Medicine Human Beings are Not Yet Dispensable. J Obstet Gynecol India 73, 295–300 (2023). https://doi.org/10.1007/s13224-023-01747-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13224-023-01747-x