Alec Silberg ’28
Healthcare has long been defined by innovation. Be it vaccinations, diagnostic tools, or drugs, the industry is dominated by change. With an influx of artificial intelligence (AI) research and development in recent years, even the most human-centered fields have become subject to modernization. For example, scientists are investing in AI solutions to infertility, a person’s inability to conceive children.
Given that infertility is a very sensitive and significant medical issue, it has motivated many therapeutic developments to treat infertility, ranging from very taxing to less (Johns Hopkins, n.d.). Many drugs, both oral medications and injectables, have been created to restore fertility which largely target women with ovulation disorders. These work in place of natural hormones, like follicle-stimulating hormone (FSH) and luteinizing hormone (LH), to trigger ovulation. Clomiphene citrate, commonly known as Clomid, increases the release of these hormones to stimulate ovulation. Adverse drug reactions, such as swollen and painful ovaries as well as an increased likelihood for pregnancy with multiples, are rare (Mayo Clinic, n.d.). Therefore, many women look to these therapeutics before more aggressive treatments.
In vitro fertilization (IVF) has been established as the dominant and most recognizable fertility treatment. It is a type of assisted reproductive technology where doctors fertilize eggs with sperm outside of the body in a laboratory. After fertilization, the embryo is placed inside a uterus, and pregnancy results if the embryo successfully implants itself into the uterine wall. Oftentimes, people resort to IVF when one partner is infertile or the couple is same-sex. This is because patients can utilize sperm and egg donors. The process contains many steps and tends to last four to six weeks. This time frame includes the patient taking fertility medication before egg retrieval. The highest success rate for IVF in 2019, at ages younger than 35, was 46.7%. Though the percentage seems relatively high, this is the most optimal period for performing the process and the greatest likelihood for pregnancy. Therefore, there is significant room to improve. Due to the complexity of the process, failure can be attributed to many factors, including, but not limited to premature ovulation, sperm quality, and a lack or surplus of developed eggs (Cleveland Clinic, n.d.). Therefore, innovators are looking to new technology to better the process.
Fertility startups and doctors have begun utilizing artificial intelligence (AI) to improve IVF efficacy and outcomes. After training AI models on millions of data points, doctors use softwares that considers factors such as age, ancestry, weight, and existing diagnoses to guide clinicians and patients based on outcomes of similar patients. These tools cover most steps of the fertility process. Additionally, some, like Alife, use machine-learning to analyze a woman’s data and deliver recommendations, including the optimal dosage of FSH a woman should take and the best day for egg retrieval. Dr. Kylie Dunning, a reproductive biologist and associate professor at the University of Adelaide, anticipates greater collaboration between researchers and clinics to make the process more accurate with increased data sets (Newcomb, 2024). Theoretically, relying on this data can save money on medicine and unnecessary future rounds of IVF–one complete round of IVF, including medicine, costs an average of $23,474, according to an analysis by FertilityIQ. In the future, these doctors and developers will look to see more collaboration within healthcare systems to create larger datasets across diverse demographics to better predict success (Newcomb, 2024).
Fairtility™ created a transparent AI-based decision support tool named CHLOE™ to provide insight for prospective patients and clinicians into laboratory data. The startup looks to transparent AI which focuses on understanding context and reasoning instead of conclusions themselves. Their philosophy is that doctors can best utilize AI when the model explains how it reached a certain decision because the complexity of the process and the software’s pattern make the technology vulnerable (Fairtility, n.d.).
In his fertility practice, Dr. Alan Copperman has implemented Alife to both inform patient decisions and streamline administrative duties to meet demand. On the subject, he said: “It’s nice to know a week in advance that there are going to be 15 patients that are going to be heading toward an egg retrieval on Sunday, because you want to staff the weekend appropriately. It’s also great in visualizing data in advance at various parts because certain people are scheduled depending upon when they get their period. But once somebody starts, it actually bakes in metrics and helps divide their predictive algorithms so we can advance where your needs are going to be on a system level” (Newcomb, 2024).
Considering that fertility is such a delicate and important matter, it is a testament to the power of AI that innovators, scientists, and healthcare providers are investing in it and relying on it in the reproductive sciences. With IVF usage on the rise, AI will allow patients and doctors to more easily overcome obstacles that would remain and become widespread otherwise. In fact, the term Repro-AI has been coined to describe the integrative technology between mathematical and reproductive sciences to grow AI applications in the diagnosis and treatment of infertility. Between 2021 and 2026, the global IVF industry is predicted to grow 10% annually, from $638 million to $987 million. This is a response to a decline of fertility rates and increase in male infertility, obesity, public awareness of infertility, and age of first pregnancy (Sadeghi, 2022). Through AI implementation, care providers can more effectively and efficiently meet this increased demand.
Alec Silberg is a staff writer at The Princeton Medical Review. He can be reached at as0159@princeton.edu.
References
Fairtility. Retrieved December 1, 2024, from https://fairtility.com/chloe/
Female infertility-Female infertility – Diagnosis & treatment. (n.d.). Mayo Clinic. Retrieved
November 6, 2024, from https://www.mayoclinic.org/diseases-conditions/female-infertility/symptoms-causes/syc-20354308
Fertility and Reproductive Health. (n.d.). Johns Hopkins Medicine. Retrieved November 6,
2024, from https://www.hopkinsmedicine.org/health/conditions-and-diseases/fertility-and-reproductive-health
IVF (In Vitro Fertilization): Procedure & How It Works. (2022, March 2). Cleveland Clinic.
Retrieved November 6, 2024, from https://my.clevelandclinic.org/health/treatments/22457-ivf
Newcomb, A. (2024, March 18). Inside some IVF clinics, AI is helping to call the shots. Fortune.
Retrieved November 6, 2024, from https://fortune.com/2024/03/18/inside-ai-fertility-femtech-ivf
Sadeghi, M. R. (n.d.). Will Artificial Intelligence Change the Future of IVF? National Library of
Medicine. Retrieved November 6, 2024, from https://pmc.ncbi.nlm.nih.gov/articles/PMC9666597
Leave a Reply