Disclaimer: EMA by AIVF has CE mark. In the US, an AI component of EMA is considered an investigational device. Limited by Federal (or United States) law to investigational use.
©All rights reserved AIVF 2023
Single knowledge center top

The new IVF frontier.

Carol Lynn Curchoe, PhD, HCLD | Jan 12, 2023 | Jan 12, 2023

The new IVF frontier. Augmented. Automated. Intelligent.

Despite the high cost of IVF in the US, success rates remain stagnant (less than 50%), and multiple gestations and complications are far too common. There have been various proposals for measuring the true cost of IVF; dollars per baby, time to baby, life disruption to baby, clinic workflow, laboratory workflow and process optimization. Financial costs are only part of the story, albeit an important one in countries where patients are paying out of pocket. Online, people trying to conceive are sharing their stories of the impact infertility or the need for medically assisted reproduction has had on their jobs, careers, relationships, as well as their mental health.

Artificial intelligence, or AI, has been touted as the next big thing that will transform our lives and our work. AI has already settled casually into our daily lives. Alexa and Siri use AI to provide answers to our questions. Google Maps uses AI to give us real-time traffic conditions. Recommendations from Amazon and Netflix are powered by AI.

While there are some visionaries that predict we will be replaced by AI (haha!), the stakes are high as we take care of very precious cargo.


The are many applications for AI to reduce costs for IVF patients. Predictive modeling (ie, taking young age, long menstrual cycles, polycystic ovary syndrome (PCOS), AMH, and AFC into account) has already been shown to reduce IVF cycle cancellation and patient hospitalization, to achieve a significant reduction in costs.

As AI systems increase in accuracy, and uncover new determinants of IVF success, their predictive ability will grow. AI has already found utility in the IVF lab with oocyte, sperm and embryo evaluation. This makes so much sense because research has demonstrated time and time again the variability between embryologists and clinics. This technology not only purports to see more than the human eye, but it provides consistent AND objective assessment. There is no need for us to get defensive here – AI helps us do our job – better! It’s like working with your favorite pipette.

Free up embryologist time.

Recently, AIVF CEO, Daniella Gilboa was able to present a vision for how AI is ushering in a new era of embryology, computational embryology, and a new type of computational embryologist. The computational embryologist will have a different tool kit at their disposal, and use a different vocabulary than we do today, that includes measures of; true PN Scoring, halo effects, cytoplasm rearrangement, values and ratios of time events, cell edges and dynamics, speed of blastulation and hatching, embryo pumping, among others.

The promise of AI mitigated freedom for the computational embryologist, is not just a new toolkit, but the re-acquisition of free-time. Free time to perform at the higher levels as only humans can; higher order data analysis, research, intellectual work, training, mentoring, and quality functions.

Cost of care.

One AI application with enormous potential is non-invasive biopsy. Evidence is accumulating for the disadvantages of PGT-A, including increased cost, clinical uncertainty about how to handle mosaic results, and concerns that the trophectoderm biopsy is not representative of the entire embryo or may cause cellular damage. AI nicely answers those challenges. Research has demonstrated that AI can predict ploidy (number of chromosome sets in a cell). It is clear that AI provides a feasible method for selecting chromosomally normal embryos without the need for expensive and damaging invasive biopsies.

Furthermore, embryo evaluation using AI will facilitate reduced costs through the optimization of our labor, laboratory performance, shorter time to a healthy, live birth of a singleton, and reduction of failed cycles by not transferring embryos with a low chance of implantation (deselected embryos).

Lastly, AI holds promise to improve the system. High cost, high-complexity laboratories with a small, highly skilled staff to oversee greater and great numbers of IVF cycles won’t cut it. Clinics were always busy, but now IVF labs are slammed as well.  With a worldwide shortage of expert embryologists and REIs, efficiency is no longer nice to have, it is a necessity.

As we integrate AI technology into IVF practices and our work as embryologists and clinicians, the goals should remain the same – minimize costs and patient drop-out due to stress and financial fatigue, while ensuring the highest quality of patient care.

Yates AP, Rustamov O, Roberts SA, Lim HY, Pemberton PW, Smith A, et al. Anti-Mullerian hormone-tailored stimulation protocols improve outcomes whilst reducing adverse effects and costs of IVF. Hum Reprod. 2011;26:2353–62.

Domar AD, Rooney K, Hacker MR, Sakkas D, Dodge LE. Burden of care is the primary reason why insured women terminate in vitro fertilization treatment. Fertil Steril. 2018;109(6): 1121–6. https://doi.org/10.1016/j.fertnstert.2018.02.130.

Curchoe, C.L. Proceedings of the first world conference on AI in fertility. J Assist Reprod Genet (2023). https://doi.org/10.1007/s10815-022-02704-9