Examples of embryos evaluated by the STORK-A algorithm. From left to right, an embryo predicted to have a normal chromosome count or a single chromosomal abnormality; an embryo predicted to have a normal chromosome count; an embryo predicted to have more than one chromosomal abnormality.
Examples of embryos evaluated by the STORK-A algorithm. From left to right, an embryo predicted to have a normal chromosome count or a single chromosomal abnormality; an embryo predicted to have a normal chromosome count; an embryo predicted to have more than one chromosomal abnormality.
Tyler O'Neal, Staff Editor HEALTH

Weill Cornell Medicine creates STORK-A for IVF embryo selection

An artificial intelligence algorithm can determine non-invasively, with about 70 percent accuracy, if an in vitro fertilized embryo has a normal or abnormal number of chromosomes, according to a new study from researchers at Weill Cornell Medicine. Dr. Zev Rosenwaks

Having an abnormal number of chromosomes, a condition called aneuploidy is a major reason embryo derived from in vitro fertilization (IVF) fail to implant or result in a healthy pregnancy. One of the current methods for detecting aneuploidy involves the biopsy-like sampling and genetic testing of cells from an embryo—an approach that adds cost to the IVF process and is invasive to the embryo. The new algorithm, STORK-A can help predict aneuploidy without the disadvantages of biopsy.  It operates by analyzing microscope images of the embryo and incorporates information about maternal age and the IVF clinic’s scoring of the embryo’s appearance.

“Our hope is that we’ll ultimately be able to predict aneuploidy in a completely non-invasive way, using artificial intelligence and computer vision techniques,” said study senior author Dr. Iman Hajirasouliha, associate professor of computational genomics and physiology and biophysics at Weill Cornell Medicine and a member of the Englander Institute for Precision Medicine. Dr. Iman Hajirasouliha

The study’s first author is Josue Barnes, a doctoral student at the Weill Cornell Graduate School of Medical Sciences who studies in the Hajirasouliha Laboratory. Dr. Nikica Zaninovic, associate professor of embryology in clinical obstetrics and gynecology and director of the Embryology Laboratory at the Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine at Weill Cornell Medicine and NewYork-Presbyterian/Weill Cornell Medical Center led the embryology work for the study.

According to the U.S. Centers for Disease Control and Prevention, there were more than 300,000 IVF cycles performed in the United States in 2020, resulting in about 80,000 live births. IVF experts are always looking for ways to boost that success rate, to achieve more successful pregnancies with fewer embryo transfers—which means developing better methods for identifying viable embryos.

Fertility clinic staff currently use microscopy to assess embryos for large-scale abnormalities that correlate with poor viability. To obtain information about the chromosomes, clinic staff may also use a biopsy method called preimplantation genetic testing for aneuploidy (PGT-A), predominantly in women over the age of 37.

To develop a computational approach to embryo assessment that capitalized on the Embryology Laboratory’s pioneering use of time-lapse photography, investigators from the Center for Reproductive Medicine teamed up with colleagues at the Englander Institute.

In a 2019 study, the teams developed an artificial intelligence (AI) algorithm, STORK, that could assess embryo quality as well as IVF clinic staff. For the new study, they developed STORK-A as a potential replacement for PGT-A—or as a more selective way of deciding which embryos should have PGT-A testing. Dr. Nikica Zaninovic

The new STORK-A algorithm uses microscope images of embryos taken five days past fertilization, clinic staff’s scoring of embryo quality, maternal age, and other information that is normally gathered as part of the IVF process. Because it uses AI, the algorithm automatically “learns” to correlate certain features of the data, often too subtle for the human eye, with the chance of aneuploidy. The team trained STORK-A on a dataset of 10,378 blastocysts for which ploidy status was already known.

From its performance, they assessed the algorithm’s accuracy in predicting aneuploid versus normal-chromosome “euploid” embryos at nearly 70 percent (69.3%). In predicting aneuploidy involving more than one chromosome—complex aneuploidy—versus euploidy, STORK-A was 77.6 percent accurate. They later tested the algorithm on independent datasets, including one from an IVF clinic in Spain, and found comparable accuracy results, demonstrating the generalizability of STORK-A.

The study provides a proof of concept for an approach that is currently experimental. Standardizing the use of STORK-A in clinics would require clinical trials comparing it to PGT-A, and Food and Drug Administration approval—all years in the future. But the new algorithm represents progress on the way to making IVF embryo selection less risky, less subjective, less costly, and more accurate.

“This is another great example of how AI can potentially transform medicine. The algorithm turns tens of thousands of embryo images into AI models that may ultimately be used to help improve IVF efficacy and further democratize access by reducing costs,” said co-author Dr. Olivier Elemento, director of the Englander Institute for Precision Medicine and a professor of physiology and biophysics and computational genomics in computational biomedicine at Weill Cornell Medicine.

Dr. Olivier Elemento“We believe that ultimately by using this technology we can reduce the number of embryos to be biopsied, reduce the costs, and provide a very good tool for consultation with the patient when they need to decide whether to do PGT-A or not,” said Dr. Zaninovic.

The team now plans to build on this success with algorithms trained on videos of embryo development.

“By using video classification, we can leverage both temporal and spatial information about the embryo’s development, and hopefully that will allow the detection of trends in development that distinguish aneuploidy from euploidy with even higher accuracy,” Barnes said. Josue Barnes

“This technology is being optimized with the hope that at some point its accuracy will be close to genetic testing, which is the gold standard and is more than 90 percent accurate,” said co-author Dr. Zev Rosenwaks, director and physician-in-chief of the Ronald O. Perelman and Claudia Cohen Center for Reproductive Medicine at NewYork-Presbyterian/Weill Cornell Medical Center and Weill Cornell Medicine, and the Revlon Distinguished Professor of Reproductive Medicine in Obstetrics and Gynecology at Weill Cornell Medicine. “But we realize that this goal is aspirational.” 

Imperial College London prof Zhang suggests the failing IT infrastructure is undermining safe healthcare in the NHS

Tyler O'Neal, Staff Editor HEALTH

Poorly functioning IT systems “a clear and present threat to patient safety,” warn experts

Joe Zhang at Imperial College London and colleagues point to a recent 10-day IT system outage at one of the largest hospital trusts in the NHS and warn that increasing digital transformation “means such failures are a no longer mere inconvenience but fundamentally affect our ability to deliver safe and effective care.”

The National Health Service (NHS) is the publicly funded healthcare system in England, and one of the four National Health Service systems in the United Kingdom.

They argue that, unlike the procurement of electronic health records, for example, investment in IT infrastructure is rarely prioritized and easily viewed as a cost to keep down rather than an investment that increases productivity.

Yet the consequences are substantial, they write. A recent survey of NHS clinicians commissioned by NHS England shows that user experiences of electronic health records are generally poor, resulting from unreliable, slow IT.

The British Medical Association (BMA) estimates that a substantial proportion (27%) of NHS clinicians lose over four hours a week through inefficient IT systems. The BMA report also found deficiencies in investment and a lack of clinician engagement in procurement.

Outdated infrastructure is a risk to data security, they add. It is unclear how many providers conform to national guidance by keeping multiple back-ups of data, including ‘off-site.’

There is also a growing disconnect between government messaging promoting a digital future for healthcare (including artificial intelligence) and the lived experience of clinical staff coping daily with ongoing IT problems.

“This digital future will not materialize without closer attention to crumbling IT infrastructure and poor user experiences,” they write.

There is no one-size-fits-all solution, but the NHS can learn from approaches taken elsewhere, they say. In the US, for example, the effect of health IT on end users is an active area of research, particularly on how the functionality of IT systems affects clinician burnout and effectiveness, while federal oversight of healthcare IT infrastructure can identify problems and coordinate a response.

To facilitate a transformation of IT infrastructure in the NHS “we need to include systematic and transparent measurement of IT capabilities and functionality at the level of clinicians – the people using the systems” they explain, “as well as at the level of those procuring the systems.”

Armed with this understanding, quality improvement cycles must become routine in IT governance, as they are in clinical care, and government must provide the investment needed to identify and rectify poor performance but also demand accountability, with minimum standards for IT function and stability, they add.

“We must not tolerate problems with IT infrastructure as normal,” they conclude.

“Poorly functioning IT systems are a clear and present threat to patient safety that also limit the potential for future transformative investment in healthcare. Urgent improvement is an NHS priority.”

University of Sydney geoscientists find the future health of coral reefs is written in the sand

Tyler O'Neal, Staff Editor HEALTH

University of Sydney geoscientists deploying instruments into sand aprons at One Tree Island, Great Barrier Reef [Credit: University of Sydney]How are coral reefs responding to climate change?

University of Sydney geoscientists develop a technique that reveals the health of coral reefs from space.

How healthy are coral reefs? And how are they responding to climate change? After more than 10 years of monitoring the Great Barrier Reef, University of Sydney geoscientists have developed a technique that allows them to answer these questions using satellites. And it all relies on sand aprons.

It turns out that sand aprons, deposits of sand along the shore of a lagoon that is ubiquitous in coral reefs, can give a reliable estimate of how coral reefs are growing as well as their rate of carbonate sediment productivity – key to establishing their overall health.

“The traditional way of collecting such data is very work intensive,” said Associate Professor Ana Vila-Concejo, who led the study, published today in the journal Geology. “It requires actively measuring the chemistry of water or taking thousands upon thousands of photos to calculate how much each creature in the ecosystem is contributing to carbonate sediment productivity.”

But the study also found more signs of trouble for coral reefs: carbonate productivity today is half what has been for thousands of years of sand apron formation in the southern Great Barrier Reef. “Our results suggest that ecosystem health was much better then, so we’re likely seeing the effects of climate change in our present-day data,” added Associate Professor Vila-Concejo, Co-Director of the University’s Marine Studies Institute.

How corals grow and recede, under what conditions, and how healthy they are, are dependent on an incredibly complex combination of factors – such as waves and storm surges, sedimentation rates, seawater chemistry, land-based runoff, and even fish populations. Hence, predicting the health of any single coral reef group, and how they will behave in response to climate change, is an intricate puzzle.

However, the researchers found that sand aprons – formed as waves and currents from reef crests carry sediment that becomes trapped in the reef lagoons – can be used to estimate carbonate productivity over time, and therefore the health of a coral ecosystem.

The field team, coordinated by Dr. Sarah Hamylton, an Associate Professor at the University of Wollongong and an Honorary Associate at the University of Sydney, worked from a 12-meter catamaran to visit 21 reefs in the southern Great Barrier Reef, collecting over 100,000 records of reef bathymetry and composition.

The team later worked with satellite imagery to measure the sand aprons and estimate their volume for each reef. They then matched that data with carbonate production measurements taken over more than a decade to try and understand sand apron evolution, and how it correlated with productivity.

“The formation of sand aprons by lagoon infilling is a function of reef size, and a self-limiting process controlled by the surrounding hydrodynamics and in response to the ebb and flow of sea-level changes,” said Associate Professor Vila-Concejo, who is also Deputy Director of the One Tree Island Research Station, located in the Great Barrier Reef. “If we can understand the evolution of sand aprons in each reef over time, we can use the data to manage coral reefs and prepare for climate change.”

As coral reefs around the world respond to warming oceans, it will change how corals behave. The climate effects on the drivers for sand apron development – sediment production, hydrodynamic forcing, and the infilling of lagoons – are not yet clear. But the study indicates that understanding their behavior and evolution provides a powerful shortcut to determining overall reef health.

In addition, by combining modern analysis of sand apron accretion with data going back 8,000 years, the researchers can establish the background rate of coral productivity.

“Our findings show that the carbonate production was much higher during the Holocene – the last 11,700 years of Earth's history – but that the average rate of production today is down 50 percent on this. That is a cause for concern,” Associate Professor Vila-Concejo said.

“Our current research involves modeling what this will mean for the future of the Great Barrier Reef, and these data are going to be essential for that,” she added.