Analyzing historical results shows that over half of IVF cycles had possible early or late trigger injections, impacting ovulation and egg retrieval outcomes.
San Francisco, California (May 16, 2022) – A study led by researchers at Alife Health, a fertility technology company building artificial intelligence (AI) tools designed to improve in vitro fertilization (IVF) outcomes, and co-authored by experts from Reproductive Science Center of the San Francisco Bay Area (RSC), Reproductive Medicine Associates (RMA) of New York, Boston IVF and University of California San Francisco (UCSF), found that an interpretable machine learning model can help doctors optimize ovulation trigger injection timing to improve patient outcomes for a significant number of IVF patients.
When undergoing IVF, patients are prescribed fertility medications to stimulate the ovaries to produce multiple eggs, or oocytes. In this process, physicians make a series of decisions that are critical to the outcome of the cycle. One of the most important decisions is when to give the final ovulation trigger injection to induce maturation of the oocytes (eggs). Triggering too early may not allow the oocytes to reach maturity, while triggering too late may result in post-mature oocytes – both decreasing chances of successful fertilization and creation of healthy embryos to use in IVF pregnancy.
Using AI to time ovulation induction
The study, published online in Fertility and Sterility, is one of the first to develop an interpretable machine learning model for helping clinicians optimize the day of trigger during ovarian stimulation. For their analysis, conducted with collaborators at RSC, RMA New York, Boston IVF and UCSF, the researchers drew from over 30,000 historical IVF cycles that were performed at multiple centers from 2014 to 2020.
Study results indicate that Alife’s machine learning model could help doctors retrieve up to two to three more mature oocytes (eggs), resulting in two more fertilized oocytes (eggs fertilized by sperm) and one more usable blastocyst (embryo) on average. The findings not only confirm previously reported results but do so across multiple different clinics and with a much larger sample size. The authors note that the study has limitations, the primary of which is its retrospective nature.
“Our results indicate that meaningful improvements in outcomes could potentially be achieved for a large percentage of ovarian stimulation cycles by using this model to assist with trigger injection timing,” says the study’s senior author, Kevin Loewke, head of data science at Alife. “We look forward to entering the clinic and performing prospective studies in the near future to confirm these retrospective findings.”
“These promising results further indicate that we are on the right path towards utilizing AI to improve the effectiveness of IVF for our patients,” says the study’s co-author Eduardo Hariton, MD, MBA. “As we aim to leverage technology to not only improve the outcomes for our patients, but also increase the efficiency of our providers and expand access to care, clinical decision support tools like this one will be crucial.”
Later this year Hariton will join the physician team at RSC of the San Francisco Bay Area, which has been actively using artificial intelligence technology to help select the best embryos for IVF patients.
The study, titled “An interpretable machine learning model for predicting the optimal day of trigger during ovarian stimulation,” was led by Michael Fanton, PhD, senior data scientist at Alife and co-authored by:
- Paxton Maeder-York, MS, MBA, CEO of Alife Health.
- Eduardo Hariton, MD, MBA, reproductive endocrinology and infertility fellow at UCSF Center for Reproductive Health, joining RSC later this year.
- Oleksii Barash, PhD, HCLD, IVF laboratory director at RSC.
- Louis Weckstein, MD, reproductive endocrinologist at RSC.
- Denny Sakkas, PhD, CSO, of Boston IVF.
- Alan Copperman, MD, FACOG, reproductive endocrinologist at RMA New York.
- Kevin Loewke, PhD, head of data science at Alife Health.