Here’s How AI Is Helping Make Babies By Revolutionizing IVF

One in four couples in developing countries is affected by infertility. Around 48.5 million pairs Infertility experience worldwide. Today, infertility is fast becoming an epidemic.

In vitro fertilization (IVF) is a technique that helps people who are facing fertility problems to have a baby. Despite the potential of IVF, the results are unpredictable. To make matters worse, access to fertility care is very poor. Even in developed markets like the United States, Just 2% of infertile people have had IVF.

“IVF has been around for over 40 years,” he says. Eran commendedCEO of integrity. “Despite the many innovations on the biotech side of things, it is surprising that there has been almost no use of data and technologies such as artificial intelligence (AI) to influence outcomes.”

While data science cannot solve biological problems, Esched believes AI will enhance the IVF process at every step decisions are made.

Today, we are seeing exciting applications of data science in fertility that could improve embryologists’ ability cycle by 50% and a plus The chances of a live birth are 4%.

Where the IVF process falls short today

IVF is a fertility technique in which an egg is removed from a person’s ovary and fertilized with sperm in a laboratory. The fertilized egg is then successfully implanted into the uterus to grow.

Doctors and embryologists make many decisions in several joints. “These decisions are based on experience, intuition, and a very primitive set of rules,” Eshed says.

Today, there are two main challenges with IVF:

1. Poor access to care

“When only 2% of the affected population can benefit from IVF, it is clear that access to care is a huge and significant problem,” Eshed highlights. “IVF is currently focused on infertile patients—those who do not get pregnant either through timely intercourse or simple treatments such as oral medications,” shares Dr. Gerard Lettree, a reproductive endocrinologist and partner in reproductive medicine in Seattle. “This is a relatively limited segment of the population.”

Dr. is expected. In the future, the patient population will include those interested in preserving fertility by freezing eggs or creating embryos for future use. He expects that “this will lead to a significant increase in the number of patients seeking care using assisted reproductive technologies.”

2. Unconfirmed results

How successful is artificial insemination? The chances of getting pregnant from a single IVF cycle are around 30%. Thus, most patients need to undergo multiple cycles before experiencing a successful live birth.

While the success of IVF is affected by age, data He explains that most IVF cycles fail even for the youngest, healthiest women. The outcome of IVF is highly dependent on the decisions made during the clinical process and on the expertise of the embryologists.

Artificial intelligence has the potential to reinvent fertility treatments

How long is the IVF process and what are the steps involved? IVF begins with a doctor’s evaluation of the cause of infertility. “Then it moves to the stimulation phase where the clinician determines the best ovarian stimulation protocol,” shares Eshed.

This is usually followed by egg and sperm collection, fertilization of the eggs using sperm to produce embryos, implantation of the embryos in the clinic, embryo transfer to the mother, and a live birth months later.

“As people go through this process, success rates drop dramatically at each stage,” says Eshed. Typically, six to seven strategic decision points determine the effectiveness of each step. “In the business world, we call them points of influence where you can make a difference,” he adds.

These points include clinicians’ decisions about the stimulation medication protocol or the timing of egg retrieval. In the lab, embryologists make many judgments by interpreting images regarding oocytes (developing eggs), sperm, and blastula cells (fertilized eggs).

“I am confident that AI can help simplify decisions to increase clinical decision-making,” says Dr. Letri. For example, complex neural network-based convolutional image analyzes can help embryologists interpret images to improve results.

The global IVF market is set to reach around $36 billion by 2026, per industry Report. Dr Leteri predicts that “there simply will not be enough skilled embryologists to meet this growing demand.” Recently, the fertility space is seeing multiple tech investments, with many startups funded and driven by artificial intelligence.

Echid founded Fairtility in Israel to take on the acute challenge of analyzing embryos using artificial intelligence. Recently, his company Starch $15 million in Series A funding. Other startups like EmrbyonicsAnd the mojoAnd the life They come up with AI-based fertility solutions to analyze embryos, assess sperm quality and customize IVF treatment plans.

How artificial intelligence is revolutionizing embryo analysis

Today, embryos are classified by embryologists who manually examine images for a range of visually detectable features. integrity Uses Computer vision algorithms to augment this process and predict the potential effectiveness of implants.

Their AI algorithms are trained from a data set of more than 200,000 fetal videos and more than 5 million clinical data points drawn from a diverse patient population. This gives AI models the ability to analyze subtle features that are often undetectable even by the most experienced embryologists.

Fairtility’s solution, CHLOE, is a cloud-based system that serves as a decision support tool for AI-powered embryo selection. The tool integrates with time-lapse imaging (TLI) systems to provide continuous predictions from fertilization to the blastocyst stage. As the TLI system captures images of embryos at different stages of development, they are automatically identified, segmented, and analyzed at the pixel level.

In addition to automating this process, the AI ​​model helps to precisely define attributes such as size, area, shape, proportion, and symmetry. “It’s not something a human can do, so, in a sense, we’re bringing in a lot of intelligence in the process,” Eshed shares. This accurate information combined with the probability of implantation allows the embryologist to make data-driven decisions for each embryo implanted in the TLI device.

CHLOE’s algorithms can predict blastocysts with 96% accuracy, implantation with 71% accuracy, and whether an embryo is genetically healthy with 69% accuracy, in each paper submitted to ESHRE . Conference. Results such as these improve embryologists’ prediction of embryo viability, which currently stands at about 65%.

In addition, the AI ​​solution could help embryologists identify anomalies, such as unusual cleavage patterns, severe fragmentation, or abnormalities of the nucleus that might otherwise be missed. Thus, CHLOE increases the likelihood of selecting healthy embryos.

However, despite the improved results in embryo selection and process efficiency, studies have yet to show appreciable improvements in live birth rates, which are considered the gold standard.

“AI cannot and should not replace embryologists and clinicians,” Eshed explains. “It is important that every patient receives the same and the highest standard of care, regardless of the practitioner’s experience or workload.” This is where CHLOE balances the playing field.

Fairtility provides its software-as-a-service (SaaS) solution to clinics and fertility centers around the world. For Eshed, CHLOE installation requires no hardware and can be done remotely. With more than 25 active facilities worldwide, Fairtility has achieved CE mark registration (European Certificate for Safety, Health and Environment) and is said to be in the advanced stages of FDA approval.

The 3 prerequisites for making an impact with AI

To realize the full potential of AI, several key challenges must be overcome:

1. Addressing data availability issues

“Data is a huge challenge in this field,” Eshed says. Data range from notes about treatment history, electronic medical records (EMR), ultrasound images and videos. Esched says that while the data is there, it’s very scattered, and it’s not well formatted or organized. Even today, many clinics archive records in physical files. The entire process must be digitized to gain a comprehensive perspective from which AI models can learn.

2. Integration into the workflow

“Current practices have not been complicated in terms of workflow and process development,” shares Dr. literal. These AI solutions can only help deliver results when they are integrated into clinical and laboratory workflows. “This will also require education on the part of all stakeholders,” he adds. For example, Dr. Leteri will launch a 15-course curriculum on Artificial Intelligence in Fertility using presentations from thought leaders at the upcoming ESHRE conference.

3. Enhancing trust and adoption

Even after efficacy has been demonstrated, achieving clinical absorption and routine use takes time. Never underestimate resistance to change, warns Esched. “A great AI solution won’t necessarily impress anyone.”

Dr. Lettre shares the example of beta-blockers, medications that prevent cardiovascular disease, as an example. These drugs were initially used in patients recovering from a myocardial infarction (MI) to prevent recurrence of a heart attack. Despite studies showing a clear reduction in morbidity and mortality, it took more than 7 years to incorporate beta-blockers into routine clinical care.

Dr. Leteri warns: “Likewise, we have an uphill battle to convince clinicians and embryologists that using AI tools will improve outcomes. Most practitioners are not familiar with AI and its applications in the clinical setting; thus, they are very reluctant to change practice patterns.” He feels it is necessary to show a clear improvement in results before big uptake can be expected. Meanwhile, we must prepare for delays in building trust with technology-enabled treatments.

A future where fertility care is commonplace

Dr. is expected. Let’s see IVF grow in prevalence with better success and lower cost of care barriers. He anticipates developing early detection tools that warn patients who may experience reduced fertility, unlike today where patients end up with the possibility of irreversible fertility. With enhanced visibility about their fertility, patients will then be able to take early action by freezing sperm, eggs or embryos.

It concludes that smartphones will be one of the biggest and most significant improvements in the delivery of fertility care.