AI and IVF: A Fertility Doctor’s Vision for the Future of Reproductive Medicine

If it takes a village to raise a child, it takes a medical army to create a baby for couples unable to conceive.

Today, infertility rates are rising worldwide, but expanding IVF services is no easy feat. A single IVF cycle can be a lengthy process. Patients take a cocktail of hormones to stimulate their ovaries to produce more eggs. These eggs are retrieved by a doctor, and an embryologist fertilizes the eggs with sperm in a petri dish. The number of eggs that become viable embryos decreases as they progress through the different stages of IVF. After several days, the doctor places all of the viable embryos in the patient’s uterus. Each round of IVF involves three to six clinic visits, with blood samples and ultrasounds to monitor the patient’s body to make sure each step is happening at the right time. IVF is also expensive: Each round can cost between $15,000 and $30,000.

Dr. Amber Cooper is the Chief Medical Officer of Genomics and Laboratory Operations at Kindbody, a fertility and wellness clinic. Founded in 2018 by Gina Bartassi, Kindbody is now valued at $1.8 billion and provides fertility benefits directly to employers, as well as owning and operating its own clinics. Dr. Cooper believes that automation and artificial intelligence can make IVF more accessible to more people. Fast company I spoke with Dr. Cooper to understand what that would look like. The conversation has been edited for length and clarity.

Why is it important to increase reach? [to IVF]?

We are seeing rising rates of infertility or subfertility: in the past it was one in ten couples, one in six couples. Now it’s closer to one in five couples. We need at least ten times more access to IVF care than we do now. And it’s not just infertile people who need IVF. It’s people with recurrent miscarriages, people with a genetic condition, and the LGBTQ+ community.

So how can we increase access?

We’re not going to suddenly have 10 times the number of doctors, 10 times the number of embryologists, 10 times the number of clinics overnight. We need automation and artificial intelligence. By automation, I mean making a process or a system work automatically so that it replaces human labor. Then you have artificial intelligence, which is the ability to replace some of the human decision-making.

AI can automate manual steps related to blood and results processing, electronic medical records, billing, and other computer-based processes, resulting in faster response times and efficiency, which in turn can improve patient satisfaction and reduce costs.

What is the current status regarding artificial insemination?

Most clinics and labs use human procedures and do not use automation or artificial intelligence. A doctor performs the procedure and retrieves the eggs. You have an andrologist who prepares the sperm. Then you have an embryologist in the lab who injects the sperm into the egg to create an embryo. The doctor then returns the embryo to the body.

What does adding AI and automation to the IVF process look like?

Let’s break it down into each step of the patient journey. Maybe eight out of every hundred people who need to see a reproductive endocrinologist will come through our doors. First, there’s just getting people in the door and using AI models on social media to market the product to the right person.

There’s also the potential to use AI to predict what doses of drugs to give people. There are already AI-powered ultrasound programs that you can use to monitor patients and the development of their eggs. There’s also technology that lets a patient do blood tests and ultrasounds at home and send the information back to the clinic.

But the most important topic in AI is the lab. Preparing sperm involves using a needle to pick up individual sperm and injecting them into an egg to fertilize it. The fertilized eggs are then transferred to incubators to grow for several more days. All of this can be done automatically using robotics and AI, and some companies are already doing it.

Another big area where AI is entering is inventory tracking. Right now, most clinics use a process called dual certification, where two people verify that the correct label is on the correct tube. Adding an AI certification system adds protection for patients. More and more clinics are using RFID chips to help track sperm and egg trays, chain of custody, etc.

What are the barriers to implementation?

Many embryologists think this will replace jobs. That’s not true. We need them for the more complex steps. There are a lot of steps that can be simplified now, like preparing media for petri dishes for cells. If we free up time for embryologists, we free them up for more complex cases, like women with fragile eggs, or when we need to inject immature sperm into the egg instead of mature sperm, or when we need to biopsy embryos to treat complex genetic diseases.

There is a risk of reduced human interaction. From the patient’s perspective, you want to know that someone is thinking about your condition, the emotional context. On the commercial side, cost is a concern. How much will robots and technology cost?

What does the future hold?

There’s a question about how good AI models are. Right now, to predict a woman’s response to medication, I might use her blood test results, her ultrasound hair follicle count, her age, and her BMI. AI might be able to create an algorithm to help. But there are always outliers who respond differently, and that’s where the art of medicine comes in. We’re trying to figure out how to incorporate that into AI models as well.

In addition, there is the question of how far we can go with genetic testing. Currently, there are a few main areas where we do genetic testing. One is preimplantation genetic testing, which looks to see if there is too little DNA on certain chromosomes. This would result in an embryo that generally does not implant. The second area is preimplantation genetic testing for a single gene mutation, such as cystic fibrosis or Huntington’s disease.

But there’s a whole new world emerging of polygenic testing. These are diseases that aren’t linked to a single gene. In fact, certain traits in your genome may make you more susceptible to these diseases—like heart disease, autism, and type 1 diabetes. There are companies offering tests for some of these polygenic diseases. We’re nowhere near a world where people can choose their hair or eye color, but we may be able to reduce the burden of disease, which is complicated.

AI is going to lead us to a point where there are some really hard questions to ask about how much human choice and intervention there is in regards to birth.