AI adoption by fertility centers accelerated last year
Fertility clinics are straining under fragmented data systems, inconsistent monitoring protocols, and widespread manual data entry. Providers face rising patient expectations for personalized, transparent care, yet legacy tools create variability that prevents standardization. AI solutions are finally beginning to close these gaps:
Fertility care remains hampered by fragmented data systems, limited predictive visibility, and highly variable manual processes. Ninety-seven percent of healthcare information—including fertility data—remains unstructured, a barrier that limits accuracy and makes many AI tools prone to hallucination when not grounded in real-world data.
Clinicians and Embryologists Are Responsible for Too Much Data Entry. Way Too Much.
“Data flows are not necessarily automated. They're often manual. They're often left up to the patient,” Dr. Eduardo Hariton, VP of Strategic Initiatives at US Fertility told Inside Reproductive Health, describing the human and material costs of outdated data management. “And there's a loss of control at the clinic level of how that happens. It's also very expensive to pay the personnel that it takes to move a patient through the clinical team”.
Clinics also face measurement variability in ultrasound monitoring, prolonged diagnostic timelines for endocrine disorders, and a patient experience often shaped by uncertainty.
The gap between rising patient expectations and static clinical workflows is widening. Patients increasingly expect personalized predictions, transparency, and efficient monitoring—but legacy tools require repetitive manual inputs and inconsistent measurement techniques. Meanwhile, providers must balance clinical accuracy, economic sustainability, and increasingly complex patient volumes. AI is emerging not as a single category, as even Inside Reproductive Health’s Business Intelligence Hub categorizes it. Rather, artificial intelligence is now the engine of very different tools designed to stabilize, standardize, and scale these critical processes.
Variance In Monitoring Protocols, Grading, Causes Chaos
Clinics continue to struggle with inconsistent follicular measurements and the inefficiencies of standard monitoring protocols. These challenges affect clinical accuracy, patient experience, and the predictability of lab workflows. Providers also report that traditional ultrasound assessments require time-intensive probe contact and create variability that complicates both patient counseling and cycle planning.
Cycle Clarity’s AI-enabled ultrasound system directly targets these issues by standardizing follicle measurement and reducing variability across providers. In a comparison of 177 IVF cycles, REIs under-predicted mature oocytes by 4.85%, while Cycle Clarity’s algorithm over-predicted by only 0.71%, closely matching physician performance using solely ultrasound-derived data. At the lab level, the algorithm predicted mature oocytes within 10 oocytes on 76% of days.
A retrospective cohort of 858 patients found that AI-only ultrasound monitoring produced outcomes equivalent to traditional monitoring using both ultrasound and hormone levels, offering a path toward lower-cost, lower-burden cycles. Patient experience data mirrored these operational gains: probe contact time dropped by 66%, and all surveyed patients indicated they would refer a clinic using Cycle Clarity.
Clinicians and patients face longstanding uncertainty around egg quality, especially in cycles involving elective preservation or donor eggs. Donor egg programs, in particular, require stronger predictive tools to support grading, grouping, and blastocyst-level forecasting at a time when demand is rising and global donor egg usage is estimated at roughly 10% of cycles.
Future Fertility’s suite of AI-powered tools is designed to address these gaps. VIOLET™ and MAGENTA™, recently added to insurer coverage in Canada, give patients personalized egg-quality assessments for IVF and egg freezing. For donor programs, ROSE™ standardizes oocyte grouping and predicts blastocyst potential, supporting consistent distribution at scale within a donor egg market projected to reach $6.6B by 2032.
The company also introduced Euploidy Insights, a non-invasive model identifying which oocytes are most likely to develop into euploid blastocysts, alongside real-time oocyte predictions and updated patient-facing reports to improve clarity and decision-making.
Women Waiting Far Too Long To Seek Diagnosis, Treatment
One of the most persistent access barriers in fertility care is delayed diagnosis. Only 16% of women with infertility are ever formally diagnosed, and some wait up to 11 years for answers. OB-GYNs—who see most patients first—often lack efficient tools to assess endocrine disorders such as PCOS, leading to missed or delayed identification of treatable conditions.
LEVY Health’s clinical decision support system aims to reduce these delays by equipping OB-GYNs with structured diagnostic pathways. In a pilot, 96% of women using LEVY’s software received previously unknown diagnoses, averaging three newly identified conditions, with many beginning treatment within eight weeks. The company also developed an automated egg-donor triage system that streamlines ovarian reserve evaluation, PCOS identification, educational requirements, and legal considerations, shortening the screening timeline to 2–3 months and reducing the high attrition typical in donor pathways.
Women seeking reproductive health guidance often encounter misinformation, content censorship, and inconsistent online resources. These barriers affect patients across the fertility spectrum, from early symptom investigation to treatment decision-making.
Rescripted created Clara—the first LLM trained exclusively on medically reviewed women’s health content—to address these gaps. Built on Rescripted’s editorial library and partner-provided resources, Clara is designed to offer clear, cited answers that reflect current scientific consensus. Reaching roughly 20 million women monthly, the tool prioritizes transparency and contextualized learning and aims to provide a reliable alternative to general-purpose AI models that may produce inaccuracies in sensitive clinical domains.
Patients often struggle to interpret IVF success probabilities, and clinics face limitations when counseling based on generalized or non-center-specific data. This uncertainty contributes to hesitation around IVF initiation and inconsistent treatment uptake.
Univfy’s machine-learning models are built to reduce that ambiguity by generating center-specific prognostic reports. In a multicenter cohort of 24,238 patients, those who received a Univfy report had substantially higher IVF conversion rates: 213% higher for direct IVF at 180 days and 241% higher for total IVF utilization compared to those without a report. These trends held at 360 days and across “ever” intervals, demonstrating how personalized prognostics can influence treatment decisions and support more accurate counseling.
IVY Fertility, US Fertility, Standardize Data
Fertility providers continue to operate within highly fragmented data environments. Clinics and networks need a solution that can standardize their data, even across multiple clinics and disparate EMRs. A company called Cercle has emerged as the early favorite. Evelyn Carone, CTO of Ivy Fertility, emphasized the importance of leveraging technology to enhance performance across the network. “As we continue to grow, we’re focused on delivering the best outcomes to our patients and the most efficient workflows to our teams. Cercle gives us the technology backbone to do both — unifying our data, helping us drive better decisions….”
Dr. Hariton described how Cercle has helped to standardize US Fertility’s data to provide individualized patient care. “ I have a 34 year old with PCOS and AMH of 3.5 and antral follicle count of so-and-so. And this is the partner’s semen analysis. [The patient is] asking me what's their pregnancy rate if they do IUI and IVF. So I go to this predictor tool, I enter these variables and I'm able to, within seconds, present them data from the last eight years across our network of how patients like them did. That helps the patient make an informed decision,”
Medical records, genomics, and laboratory data often exist in unstructured formats, limiting their clinical utility and increasing the risk of hallucinations in AI models that are not grounded in real-world datasets.
Cercle’s platform addresses this fragmentation by standardizing diverse datasets into usable formats for clinics and researchers. Cercle also focuses on reducing AI hallucinations through retrieval-augmented generation and graph-database architecture.
New technologies are only beginning to stabilize workflows and enable more accurate, scalable, data-driven fertility care.
You Can Stop Being Left Out Now, Y’Know
Next Big Exposure Before PCRS. Why miss out when you get so much for so little? 🤪
If your organization belongs to this category but wasn’t included in this “State of” report, then your competitors are dominating the attention of your customers: REIs, fertility network executives, embryologists, and others.
These same competitors will get more coverage in a report or podcast episode, about your category
To start the year
Before PCRS
Before ESHRE
Before ASRM
Why let them get all the attention?
If you don’t want to miss out before PCRS, you have to join the IVF Heroes Universe as a sponsor now, before the next deadline.
You read it. Your employees read it. Your customers read it. Why miss out when you get so much for so little? 🤪