Loading [Contrib]/a11y/accessibility-menu.js
1.
Shoham Z. Can Elective Single Embryo Transfer (eSET) with AI Integration Become the Future of IVF? Journal of IVF-Worldwide. 2025;3(1):32-41. doi:10.46989/​001c.130036

Abstract

This manuscript examines whether elective single embryo transfer (eSET) should be mandated in all IVF cycles, assessing its clinical benefits, challenges, and global implementation. Evidence shows that eSET significantly reduces multiple pregnancies and associated complications while maintaining cumulative live birth rates. However, ethical, regulatory, and practical considerations complicate universal enforcement. While a standardized eSET policy offers advantages, potential drawbacks include restricted patient autonomy and the need for additional IVF cycles in some instances. To navigate these complexities, the manuscript advocates for a balanced approach: promoting eSET as the preferred standard while allowing individualized decisions based on patient-specific factors. Alternative policy models—such as partial mandates or incentive-based strategies—are explored to enhance outcomes without imposing rigid requirements. This nuanced perspective balances patient safety, treatment efficacy, and shared decision-making in fertility care.

Introduction and Background

In modern IVF practice, the transfer of a single high-quality embryo through elective single embryo transfer (eSET) has become increasingly common as the primary approach to prevent multiple pregnancies. Advances in embryo selection and cryopreservation have since enabled eSET to emerge as a safer, viable alternative.1 This shift in practice addresses one of the most critical complications associated with IVF—multiple pregnancies—which has been well-documented as adding significant complexity and risk to pregnancies.2
The historical context for this change is important to understand. Initially, multiple embryo transfers were common in IVF due to low implantation rates, as practitioners attempted to increase the likelihood of successful pregnancy. However, this approach led to increased risks of multiple pregnancies, which can cause serious maternal complications including preeclampsia and hypertension, as well as fetal risks such as preterm birth, low birth weight, and cerebral palsy.3,4

Research has demonstrated that when high-quality embryos are available, eSET can maintain success rates while eliminating the risk of multiple pregnancies.2 However, the implementation of eSET requires careful patient selection, as individual variability in fertility factors remains a significant consideration in determining the most appropriate treatment approach.3

Clinical Outcome Success Rates

Research has shown that while eSET may result in lower immediate pregnancy rates compared to double embryo transfer in fresh IVF cycles, this difference can be effectively overcome through subsequent frozen embryo transfers.5,6 The ‘one plus one’ strategy—eSET followed by a frozen embryo transfer— optimizes outcomes has proven to be more effective than transferring multiple embryos simultaneously, as it leads to increased implantation chances while avoiding multiple gestations.

Real-world implementation data supports the effectiveness of eSET programs. In Switzerland, a universal eSET approach achieved cumulative pregnancy rates of 48.9% and live birth rates of 33.4% per oocyte collection, while completely eliminating multiple pregnancies.7 Similarly, Belgium saw a dramatic reduction in multiple pregnancy rates from 25% to 11.9% following the implementation of mandatory SET for patients under 36 years.8

The success of eSET has been demonstrated across different age groups. Studies have shown that eSET can be effectively applied to women aged 36-39 years, maintaining comparable cumulative pregnancy and live birth rates while significantly reducing multiple birth risks.9,10 When combined with frozen embryo transfers, Devroey et al.11 reported no significant difference in cumulative live birth rates (42.9% vs. 38.8%, p > 0.05).11

However, it’s important to note that while eSET significantly reduces multiple pregnancy risks, it may decrease the chance of live birth in a fresh IVF cycle.8,12 This initial difference is typically overcome through subsequent frozen embryo transfers, leading to comparable cumulative success rates while maintaining the safety benefits of single embryo transfer.9

Benefits and Evidence Supporting eSET

The primary benefit of eSET lies in its proven ability to significantly reduce multiple pregnancy rates without compromising overall success rates. Studies have demonstrated that implementing eSET can reduce multiple pregnancy rates from 25% to as low as 5%.13 This reduction is particularly significant given that twin gestations are associated with a 5-10 fold increase in fetal and maternal complications.14

Modern embryo selection techniques have enhanced the effectiveness of eSET. The use of comprehensive chromosome analysis for embryo selection has optimized eSET outcomes by identifying embryos with the highest developmental potential.14 This advancement has made it possible to achieve acceptable pregnancy rates while minimizing the risk of multiple pregnancies.15

Cost-effectiveness analyses have shown that eSET can be economically advantageous. Despite potentially requiring more cycles to achieve pregnancy, the overall costs associated with eSET are comparable to or lower than multiple embryo transfer approaches due to reduced complications and neonatal care expenses. Gerris et al.16 found eSET reduced neonatal costs by €5,000 per case. Studies have demonstrated that while maternal costs remain similar, the neonatal care costs are significantly lower with eSET compared to double embryo transfer.17

The benefits of eSET extend across different patient populations. While initially recommended primarily for younger patients with good prognosis, research now supports extending eSET to women of advanced maternal age, as it can maintain treatment efficacy while improving safety outcomes.18 This approach has become particularly meaningful for older women undergoing assisted reproductive technology, given their increased risk of obstetrical complications.19

Leading professional organizations now recognize that successful IVF treatment should be measured by singleton birth rates rather than just pregnancy rates, acknowledging that a single healthy baby represents the optimal outcome.20 This shift in perspective has helped establish eSET as the most efficient approach to achieve better perinatal and neonatal outcomes.21

Challenges and Considerations

The successful implementation of eSET programs faces several significant challenges that must be carefully considered. A primary challenge is the need for advanced embryo selection capabilities, as the success of eSET heavily depends on the ability to identify embryos with the highest implantation potential.22 This becomes particularly crucial for older patients, where aneuploidy presents a major hurdle to success.23

The quality of available embryos significantly impacts treatment decisions. Sadeghi24 suggests poor-quality embryos may release factors inhibiting high-quality embryo implantation. This understanding has led to recommendations focusing on transferring only top-quality embryos, even if this means transferring fewer embryos overall.

Access to treatment represents another significant challenge, particularly in regions where IVF services are not covered by public healthcare systems or private insurance.25 The financial burden of multiple IVF cycles can influence both provider and patient decision-making regarding embryo transfer strategies.

A crucial consideration in eSET implementation is the balance between medical recommendations and patient autonomy. While eSET may be clinically preferable, factors such as advanced maternal age, prolonged infertility, and patient preferences must be carefully weighed in the decision-making process.26 Patients may prioritize immediate success over safety, necessitating tailored counseling. The success of eSET programs ultimately depends on effective patient education about both benefits and limitations, combined with a comprehensive approach that includes successful cryopreservation programs and access to subsequent frozen embryo transfers.22

Implementation and Regulation Worldwide

Implementation of eSET varies considerably worldwide, with adoption being most successful in countries that combine regulatory oversight with financial support for fertility treatments.27 The combination of insurance coverage and restrictions on embryo numbers has proven particularly effective in encouraging eSET adoption.27,28

Regional differences in eSET adoption are striking. While Europe achieved 38% eSET rates in 2016 across 1,200 clinics,28 the United States reaches 71%, Southeast Asia reports only about 10.2% of cycles using single embryo transfer.29 Countries with state-funded fertility treatment and strong regulatory frameworks, such as Australia, have achieved particularly high eSET rates of over 75%, resulting in multiple pregnancy rates below 6%.

Japan provides a notable example of successful regulatory implementation. Following the introduction of specific guidelines by medical societies in 2007-2008, Japan saw significant improvements in outcomes, including a dramatic reduction in twin pregnancies from 33.9% to 13% and decreased rates of preterm delivery and low birth weight.30

The primary barriers to widespread eSET implementation include treatment costs, lack of legislative policies in some regions, and inconsistent availability of ART services.29 Patient education has emerged as an important tool in implementation strategies, with studies showing that focused education about maternal and perinatal risks can effectively reduce patient preference for multiple embryo transfers.27

The Integration of AI in Embryo Selection

The integration of AI in embryo selection offers significant advantages, addressing longstanding challenges in IVF practice. Traditional embryo assessment methods have been subjective, time-consuming, and prone to variability.31 AI systems provide standardized, objective evaluations, outperforming trained embryologists by up to 24.7% in identifying implantation-capable embryos.32

Key Benefits of AI in Embryo Selection

Reduced Observer Variability: AI-based systems eliminate inter- and intra-observer variability in embryo assessment.33 This consistency is essential as the demand for ART treatments continues to grow, increasing manual workload.34

Efficiency in Data Processing: AI tools efficiently process large datasets while maintaining consistent quality standards. They expedite calculations and improve precision, reducing the manual workload for embryologists.35

Improved Patient Experience: By optimizing treatment plans, AI systems help reduce the financial, physical, and emotional burden on patients, minimizing the need for repeated IVF cycles.36

Enhanced Clinical Insights: Deep learning techniques support more objective and accurate results, offering a noninvasive, efficient approach to embryo selection.37,38

Limitations and Challenges

Despite the advancements in AI-driven embryo selection, the ultimate decision-making authority remains with clinicians. The effectiveness of these systems depends significantly on how closely clinicians adhere to AI-generated recommendations.37

AI Tools and Technologies in Embryo Selection. Machine Learning-Based Image Analysis (Table 1)

Table 1.AI tools and technologies in embryo selection
Technology/System Functionality Key Features/Performance Reference
Machine learning-based image analysis
Algorithms learn from morphological features like cell cleavage, fragmentation, and clinical factors
Evaluates embryo development - Analyzes cell cleavage, fragmentation, clinical factors
- Processes single and time-lapse images
Afnan et al.39; del Arco de la Paz et al.40
Convolutional neural networks (CNNs) Assesses implantation capability - 90% accuracy in image analysis
- Outperforms embryologists by 24.7% in binary classification
Mishra41; Bormann et al.31; VerMilyea et al.32
STEM/STEM+ Predicts blastocyst formation High accuracy in blastocyst prediction Cimadomo et al.42
CHLOE Evaluates embryo quality Consistent performance vs. expert embryologists Cimadomo et al.43
IVY Scores embryos for implantation potential Deep learning-based scoring Tran et al.44
DeepEmbryo Predicts pregnancy success 75% accuracy in pregnancy prediction Borna et al.45

Notes: AI = artificial intelligence; CNNs = convolutional neural networks.
Sources: Adapted from cited studies in the reference list.

Time-Lapse Integration Systems

  • AI systems combine continuous observation with analysis to track developmental timing and morphokinetic parameters.40

  • Compatible with existing IVF laboratory protocols.45

Literature Comparison Table
Paper Technology Used Evaluation Method Clinical Validation
del Arco de la Paz et al.40 Non-invasive AI analysis Accuracy, AUC, sensitivity, specificity Clinically validated with retrospective data
Bormann et al.31 Deep learning, CNN, genetic algorithms Accuracy, AUC, sensitivity 97 patient cohorts, 97 euploid embryos
VerMilyea et al.32 Deep learning ensemble modeling Sensitivity 70.1%, specificity 60.5% Retrospective data from 8886 embryos
Cimadomo et al.42 3D CNN (iDAScore v1.0) AUC 0.60 for euploidy prediction Validated on 3604 blastocysts
Tran et al.44 Time-lapse video AI 5-fold cross-validation, AUC Retrospective with potential clinical application
Borna et al.45 CNN (AlexNet, ResNet, Inception) Precision, Recall, F-Score Retrospective analysis

More information can be found in Appendix 2.

Clinical Implications

Clinical studies indicate that combining AI with time-lapse imaging improves embryo selection outcomes. AI-based selection systems have achieved up to 75% accuracy in predicting pregnancy success, compared to 65% accuracy by embryologists.46 AI tools like iDAScore have reduced evaluation time while maintaining consistent performance.43 See Appendix 1 for standardized eSET protocols.

Future Directions and Challenges

The future of AI in embryo selection lies in the development of multi-modal models integrating morphological, genetic, and metabolic data. Machine learning algorithms may soon assist with optimizing endometrial receptivity and predicting IVF success based on lifestyle factors.47 Challenges include integrating diverse datasets while addressing ethical concerns like AI bias and patient data security

Conclusion

While eSET should not be universally mandated due to patient variability, it should be the default for good-prognosis cases. The adoption of eSET has demonstrated significant benefits in improving IVF safety, reducing complications from multiple pregnancies while maintaining comparable success rates. The integration of advanced embryo selection techniques, supported by AI technologies, continues to enhance outcomes. Regulatory frameworks and patient education are essential to successful implementation worldwide, with future innovations likely to further optimize embryo selection and improve fertility treatment success rates.


Funding Statement

There has been no funding received for this study.

Competing Interest

None

Submission declaration & Declaration of interest

The manuscript has never been published before. There are no other publications considering it. The author declares no conflict of interest and have no relevant affiliations or financial involvement with any organization or entity with a financial interest. This includes employment, consultancies, honoraria, expert testimony, grants or royalties.

Accepted: February 21, 2025 CDT

References

1.
Tvrdonova K, Belaskova S, Rumpíková T, Malenovská A, Rumpík D, Myslivcová Fučíková A, et al. Differences in morphokinetic parameters and incidence of multinucleations in human embryos of genetically normal, abnormal and euploid embryos leading to clinical pregnancy. J Clin Med. 2021;10(21):5173. doi:10.3390/​jcm10215173
Google Scholar
2.
Kontopoulos G, Simopoulou M, Zervomanolakis I, Prokopakis T, Dimitropoulos K, Dedoulis E, et al. Cleavage stage versus blastocyst stage embryo transfer in oocyte donation cycles. Medicina (Kaunas). 2019;55(6):293. doi:10.3390/​medicina55060293
Google Scholar
3.
Boudjenah R, Molina-Gomes D, Torre A, Boitrelle F, Taieb S, Dos Santos E, et al. Associations between individual and combined polymorphisms of the TNF and VEGF genes and the embryo implantation rate in patients undergoing in vitro fertilization (IVF) programs. PLoS One. 2014;9(9):e108287. doi:10.1371/​journal.pone.0108287
Google Scholar
4.
El-Toukhy T, Kamal A, Wharf E, Grace J, Bolton V, Khalaf Y, et al. Reduction of the multiple pregnancy rate in a preimplantation genetic diagnosis programme after introduction of single blastocyst transfer and cryopreservation of blastocysts biopsied on day 3. Hum Reprod. 2009;24(10):2642-2648. doi:10.1093/​humrep/​dep229
Google Scholar
5.
Tomic M, Vrtacnik Bokal E, Štimpfel M. Non-invasive preimplantation genetic testing for aneuploidy and the mystery of genetic material: a review article. Int J Mol Sci. 2022;23(7):3568. doi:10.3390/​ijms23073568
Google Scholar
6.
McLernon DJ, Harrild K, Bergh C, Davies MJ, de Neubourg D, Dumoulin JC, et al. Clinical effectiveness of elective single versus double embryo transfer: meta-analysis of individual patient data from randomised trials. BMJ. 2010;341:c6945. doi:10.1136/​bmj.c6945
Google Scholar
7.
De Geyter C. Single embryo transfer in all infertile couples treated with assisted reproduction produces excellent results and avoids multiple births. Swiss Med Wkly. 2021;151:w20499. doi:10.4414/​smw.2021.20499
Google Scholar
8.
Abuzeid O, Deanna J, Abdelaziz A, Joseph S, Abuzeid Y, Salem W, et al. The impact of single versus double blastocyst transfer on pregnancy outcomes: a prospective, randomized control trial. Facts Views Vis Obgyn. 2017;9(4):195-206.
Google Scholar
9.
Mitta K, Tsakiridis I, Giougi E, Mamopoulos A, Kalogiannidis I, Dagklis T, et al. Comparison of fetal crown-rump length measurements between thawed and fresh embryo transfer. J Clin Med. 2024;13(9):2575. doi:10.3390/​jcm13092575
Google Scholar
10.
Veleva Z, Vilska S, Hydén-Granskog C, Tiitinen A, Tapanainen JS, Martikainen H. Elective single embryo transfer in women aged 36-39 years. Hum Reprod. 2006;21(8):2098-2102. doi:10.1093/​humrep/​del137
Google Scholar
11.
Devroey P, Fauser BC, Diedrich K. Approaches to improve the diagnosis and management of infertility. Hum Reprod Update. 2009;15(4):391-408. doi:10.1093/​humupd/​dmp007
Google Scholar
12.
Kamath MS, Mascarenhas M, Kirubakaran R, Bhattacharya S. Number of embryos for transfer following in vitro fertilisation or intra-cytoplasmic sperm injection. Cochrane Database Syst Rev. 2020;(8):CD003416. doi:10.1002/​14651858.CD003416.pub5
Google Scholar
13.
Tiitinen A, Unkila-Kallio L, Halttunen M, Hydén-Granskog C. Impact of elective single embryo transfer on the twin pregnancy rate. Hum Reprod. 2003;18(7):1449-1453. doi:10.1093/​humrep/​deg301
Google Scholar
14.
Stern HJ. Preimplantation genetic diagnosis: prenatal testing for embryos finally achieving its potential. J Clin Med. 2014;3(1):280-309. doi:10.3390/​jcm3010280
Google Scholar
15.
Tiitinen A, Halttunen M, Härkki P, Vuoristo P, Hydén-Granskog C. Elective single embryo transfer: the value of cryopreservation. Hum Reprod. 2001;16(6):1140-1144. doi:10.1093/​humrep/​16.6.1140
Google Scholar
16.
Gerris J, De Sutter P, De Neubourg D, Van Royen E, Van der Elst J, Mangelschots K, et al. A real-life prospective health economic study of elective single embryo transfer versus two-embryo transfer in first IVF/ICSI cycles. Hum Reprod. 2004;19(4):917-923. doi:10.1093/​humrep/​deh188
Google Scholar
17.
De Sutter P, Gerris J, Dhont M. A health-economic decision-analytic model comparing double with single embryo transfer in IVF/ICSI. Hum Reprod. 2002;17(11):2891-2896. doi:10.1093/​humrep/​17.11.2891
Google Scholar
18.
Ubaldi FM, Capalbo A, Colamaria S, Ferrero S, Maggiulli R, Vajta G, et al. Reduction of multiple pregnancies in the advanced maternal age population after implementation of an elective single embryo transfer policy coupled with enhanced embryo selection: pre- and post-intervention study. Hum Reprod. 2015;30(9):2097-2106. doi:10.1093/​humrep/​dev159
Google Scholar
19.
Su W, Xu J, Arhin SK, Liu C, Zhao J, Lu X. The feasibility of all-blastocyst-culture and single blastocyst transfer strategy in elderly women: a retrospective analysis. Biomed Res Int. 2020;2020:5634147. doi:10.1155/​2020/​5634147
Google Scholar
20.
Ezeome IV, Akintola S, Jegede A, Ezeome ER. Perception of key ethical issues in assisted reproductive technology (ART) by providers and clients in Nigeria. Int J Womens Health. 2021;13:1033-1052. doi:10.2147/​IJWH.S333399
Google Scholar
21.
Simopoulou M, Sfakianoudis K, Antoniou N, Maziotis E, Rapani A, Bakas P, et al. Making IVF more effective through the evolution of prediction models: is prognosis the missing piece of the puzzle? Syst Biol Reprod Med. 2018;64:305-323. doi:10.1080/​19396368.2018.1505652
Google Scholar
22.
Faramarzi A, Khalili M, Micara G, Agha-Rahimi A. Revealing the secret life of pre-implantation embryos by time-lapse monitoring: a review. Int J Reprod Biomed. 2017;15(5):257-264. doi:10.29252/​ijrm.15.5.257
Google Scholar
23.
Wu MY, Chao KH, Chen CD, Chang LJ, Chen SU, Yang YS. Current status of comprehensive chromosome screening for elective single-embryo transfer. Obstet Gynecol Int. 2014;2014:581783. doi:10.1155/​2014/​581783
Google Scholar
24.
Sadeghi M. Poor quality embryos hamper the development of high-quality ones. J Reprod Infertil. 2017;18(2):211-212.
Google Scholar
25.
Déniz FP, Encinas C, Fuente JL. Morphological embryo selection: an elective single embryo transfer proposal. JBRA Assist Reprod. 2018;22(1):20-25. doi:10.5935/​1518-0557.20180007
Google Scholar
26.
Adashi EY, Gleicher N. Is a blanket elective single embryo transfer policy defensible? Rambam Maimonides Med J. 2017;8(2):e0022. doi:10.5041/​RMMJ.10297
Google Scholar
27.
Sunderam S, Kissin DM, Zhang Y, Folger SG, Boulet SL, Warner L, et al. Assisted reproductive technology surveillance—United States, 2016. MMWR Surveill Summ. 2019;68(4):1-23. doi:10.15585/​mmwr.ss6804a1
Google Scholar
28.
Maheshwari A, Griffiths S, Bhattacharya S. Global variations in the uptake of single embryo transfer. Hum Reprod Update. 2011;17(1):107-120. doi:10.1093/​humupd/​dmq028
Google Scholar
29.
Panapakkam Jayakumar N, Solanki M, Karuppusami R, Joseph T, Kunjummen AT, Kamath M. Acceptance of elective single-embryo transfer in a resource-limited setting: a cross-sectional questionnaire-based study. J Hum Reprod Sci. 2023;16(3):233-241. doi:10.4103/​jhrs.jhrs_65_23
Google Scholar
30.
Hayashi M, Satoh S, Matsuda Y, Nakai A. The effect of single embryo transfer on perinatal outcomes in Japan. Int J Med Sci. 2015;12(1):57-62. doi:10.7150/​ijms.10337
Google Scholar
31.
Bormann C, Kanakasabapathy M, Thirumalaraju P, Gupta R, Pooniwala R, Kandula H, et al. Performance of a deep learning based neural network in the selection of human blastocysts for implantation. Elife. 2020;9:e55301. doi:10.7554/​eLife.55301
Google Scholar
32.
VerMilyea M, Hall J, Diakiw S, Johnston A, Nguyen T, Perugini D, 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):770-784. doi:10.1093/​humrep/​deaa013
Google Scholar
33.
Berntsen J, Rimestad J, Lassen J, Tran D, Kragh M. Robust and generalizable embryo selection based on artificial intelligence and time-lapse image sequences. PLoS One. 2022;17(2):e0262661. doi:10.1371/​journal.pone.0262661
Google Scholar
34.
Presacan O, Dorobanţiu A, Thambawita V, Riegler MA, Stensen M, Iliceto M. Embryo 2.0: merging synthetic and real data for advanced AI predictions. Published online 2024.
35.
Mapari SA, Shrivastava D, Bedi GN, Pradeep U, Gupta A, Kasat P. Revolutionizing reproduction: the impact of robotics and artificial intelligence (AI) in assisted reproductive technology: a comprehensive review. Cureus. 2024;16:e63072. doi:10.7759/​cureus.63072
Google Scholar
36.
Urcelay L, Hinjos D, Martin-Torres PA, González M, Méndez M, C’ivico S. Exploring the role of explainability in AI-assisted embryo selection. In: Proceedings of the International Conference of the Catalan Association for Artificial Intelligence. Updated as arXiv preprint arXiv:2308.02534; 2024. doi:10.3233/​FAIA230678
Google Scholar
37.
Kim HM, Kang H, Lee C, Park JH, Chung M, Kim M. Evaluation of the clinical efficacy and trust in AI-assisted embryo ranking: survey-based prospective study. J Med Internet Res. 2024;26:e52637. doi:10.2196/​52637
Google Scholar
38.
Patel DJ, Chaudhari K, Acharya N, Shrivastava D, Muneeba S. Artificial intelligence in obstetrics and gynecology: transforming care and outcomes. Cureus. 2024;16(7):e64725. doi:10.7759/​cureus.64725
Google Scholar
39.
Afnan M, Rudin C, Conitzer V, Savulescu J, Mishra A, Liu Y, et al. Ethical implementation of artificial intelligence to select embryos in in vitro fertilization. In: Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society (AIES ’21). ; 2021:16. doi:10.1145/​3461702.3462589
Google Scholar
40.
del Arco de la Paz A, Giménez-Rodríguez C, Selntigia A, Meseguer M, Galliano D. Advancements and challenges in preimplantation genetic testing for aneuploidies: towards non-invasive techniques. Genes (Basel). 2024;15(12):1613. doi:10.3390/​genes15121613
Google Scholar
41.
Mishra S. Artificial intelligence: a review of progress and prospects in medicine and healthcare. J Electron Electromed Eng Med Inform. 2022;4:15-23. doi:10.35882/​jeeemi.v4i1.1
Google Scholar
42.
Cimadomo D, Chiappetta V, Innocenti F, Saturno G, Taggi M, Marconetto A, et al. Towards automation in IVF: pre-clinical validation of a deep learning-based embryo grading system during PGT-A cycles. J Clin Med. 2023;12(5):1806. doi:10.3390/​jcm12051806
Google Scholar
43.
Cimadomo D, Garolla A, Vitagliano A. P4 reproductive medicine: prediction, prevention, personalization, and participation in infertility care. J Clin Med. 2024;13:5860. doi:10.3390/​jcm13195860
Google Scholar
44.
Tran D, Cooke S, Illingworth P, Gardner D. Deep learning as a predictive tool for fetal heart pregnancy following time-lapse incubation and blastocyst transfer. Hum Reprod. 2020;35(2):374-381. doi:10.1093/​humrep/​dez225
Google Scholar
45.
Borna MR, Sepehri MM, Maleki B. An artificial intelligence algorithm to select most viable embryos considering current process in IVF labs. Front Artif Intell. 2024;7:1375474. doi:10.3389/​frai.2024.1375474
Google Scholar
46.
Salih M, Austin C, Warty R, Tiktin C, Rolnik D, Momeni M. Embryo selection through artificial intelligence versus embryologists: a systematic review. Hum Reprod Open. 2023;2023(3):hoad031. doi:10.1093/​hropen/​hoad031
Google Scholar
47.
Yang Y, Dong X, Bai J, Jin L, Huang B. Faster fertilization and cleavage kinetics reflect competence to achieve a live birth: data from single-embryo transfer cycles. Biomed Res Int. 2022;2022:8501362. doi:10.1155/​2022/​8501362
Google Scholar

Appendices

Appendix: 1

Protocol for Selective Embryo Transfer (SET)
Section Details
Objective Maximize pregnancy success while minimizing multiple gestations by transferring the best-quality embryo(s).
Pre-Transfer Preparation
Patient Selection - Age ≤ 35 with good prognosis (first cycle, good ovarian reserve, high-quality embryos).
- Previous successful IVF cycles.
- Medical contraindications for multiple gestations.
Embryo Selection - Morphology: Blastocyst stage (Day 5/6) with excellent grading (e.g., AA).
- PGT-A tested for euploid status.
- Regular cell division with minimal fragmentation.
Endometrial Preparation - Natural cycle: Monitor LH surge and confirm ovulation.
- HRT cycle: Estrogen priming and progesterone initiation.
- Endometrial thickness ≥7 mm with trilaminar appearance.
Embryo Transfer Procedure
Day of Transfer - Confirm embryo quality and endometrial readiness.
- Obtain informed consent from the patient.
Procedure Steps 1. Position patient in lithotomy position.
2. Clean cervix with sterile saline.
3. Insert soft catheter through cervix under ultrasound guidance.
4. Transfer embryo(s) 1-2 cm from uterine fundus.
5. Withdraw catheter and verify embryo placement on ultrasound.
Post-Transfer Care - Rest for 10-15 minutes post-transfer.
- Luteal phase support with progesterone (oral, vaginal, IM).
Post-Transfer Monitoring
Follow-Up Tests - Serum β-hCG test 10-14 days post-transfer.
- Transvaginal ultrasound at 4-6 weeks to confirm pregnancy.
Outcome Assessment - Track implantation, pregnancy, and live birth rates.
- Evaluate embryo selection effectiveness.
Best Practices - Prioritize blastocysts with confirmed euploid status.
- Optimize lab culture conditions.
- Educate patients on SET benefits, especially younger women with favorable prognosis.
Reference Guidelines - American Society for Reproductive Medicine (ASRM).
- European Society of Human Reproduction and Embryology (ESHRE).

Embryo Transfer Protocols: ASRM and ESHRE

ASRM Embryo Transfer Protocol
Age Group Recommended Embryo Transfer
< 35 years Single embryo transfer (SET) recommended, regardless of embryo stage.
35–37 years Strong consideration for single embryo transfer.
38–40 years Up to 3 cleavage-stage embryos or 2 blastocysts; if euploid embryo available, transfer a single blastocyst.
41–⁠42 years Up to 4 cleavage-stage embryos or 3 blastocysts; if euploid embryo available, transfer a single blastocyst.
≥ 43 years Insufficient data for specific recommendations.
ESHRE Embryo Transfer Protocol
Factor Recommendations
Clinical Factors Patient age, ovarian response, embryo quality, and previous IVF outcomes should guide the decision on the number of embryos transferred.
eSET Recommended for patients with a good prognosis to minimize multiple pregnancy risks.
Non-Clinical Factors Patient preferences, psychosocial aspects, and financial considerations should be included in counseling.
Individualized Treatment Embryo transfer plans should be personalized to balance pregnancy success with the risk of multiple gestations.
Patient Education Encourage shared decision-making to help patients understand the benefits and risks of embryo transfer options.

Appendix: 2

Using AI Technology for Selecting the Embryo to Transfer

Artificial intelligence (AI) is increasingly being integrated into in vitro fertilization (IVF) protocols to enhance embryo selection and improve pregnancy outcomes. While specific standardized AI-based protocols are still under development, several AI-driven systems have demonstrated promising results:

AI Algorithms for Embryo Viability Assessment

  • Deep Learning Models:
    Studies have introduced AI algorithms capable of analyzing static images of embryos at various post-insemination intervals. These models predict pregnancy outcomes with higher accuracy than traditional morphological assessments, achieving accuracy rates of up to 75%.

    Reference:
    An artificial intelligence algorithm to select the most viable embryos considering current processes in IVF labs. Front. Artif. Intell., 30 May 2024. * Medicine and Public Health, Volume 7 - 2024, DOI: https://doi.org/10.3389/frai.2024.1375474

  • Automated Blastocyst Evaluation:
    AI systems have been developed to assess blastocyst quality by assigning scores that correlate with the likelihood of clinical pregnancy. This aids in selecting embryos with the highest implantation potential.

    Reference:

    Yael Fruchter-Goldmeier, Ben Kantor, Assaf Ben-Meir, Tamar Wainstock, Itay Erlich, Eliahu Levitas, Yoel Shufaro, Onit Sapir, Iris Har-Vardi. An artificial intelligence algorithm for automated blastocyst morphometric parameters demonstrates a positive association with implantation potential. Scientific Reports, 5 September 2023; 13(1):14617 DOI: 10.1038/s41598-023-40923-x

AI-Driven Embryo Selection Platforms

AIVF’s EMA Platform:
This AI-powered system evaluates embryo viability by analyzing biological data from fertilization through blastocyst stages. It assigns scores based on the probability of successful implantation, aiming to standardize embryo evaluations and reduce subjectivity.

AiVF: Non-invasive AI can ID genetic characteristics in embryos. Israel Hayom. 2024 Aug 6. Available from: https://www.israelhayom.com.

ERICA (Embryo Ranking Intelligent Classification Algorithm):
ERICA uses deep learning and artificial vision to non-invasively rank embryos according to their genetic status and implantation potential. This enhances objectivity and accuracy in embryo selection.

Reference:
Chavez-Badiola A, et al. Deep learning for automatic determination of blastocyst embryo development stage. Fertil Steril. 2019;112(3 Suppl):e276.doi:10.1016/j.fertnstert.2019.07.809

3. Considerations for Clinical Practice

While these AI technologies are promising, it is crucial to note that standardized AI-based embryo selection protocols are still evolving. Clinics adopting AI tools should:

  • Ensure rigorous validation of AI algorithms before implementation.

  • Provide training for embryologists and clinical staff on AI tool utilization.

  • Continuously monitor and assess AI performance to maintain accuracy and reliability.

By integrating AI into IVF protocols, clinics can potentially improve embryo selection accuracy, enhance pregnancy outcomes, and offer patients a more efficient and personalized fertility journey.