Futurologists often tell us that we humans are at the start of the second stage of the information revolution: a sort of InfoRev v.2.00, where new technologies come together and are managed by artificial intelligence (A.I.).
In terms of diagnosis of diseases, this is already having an impact in the area of medical imaging. One of the limiting factors in looking at x-rays, MRI scans, CT scans, ultrasound sonograms etc is the sheer number of images that a medical professional/technician has to evaluate, often for very small anomalies. Powerful data processors can now scan, compare and contrast thousands of different images in a short space of time, speeding up the process immensely and cutting down on human error.
The addition of A.I. management to the data management process means that, in addition to the speed and error-elimination, the system can also ‘learn’ as it processes data. At the same time the A.I. ‘manager’ can access all previous electronic patient records to come to a diagnostic conclusion, which is then checked by the human medical professional.
It is clear that such systems could be useful in the field of IVF in the near future, particularly embryo selection. With this in mind a team of researchers at Cornell University in New York have trained A.I. software to evaluate human embryos with a high level of precision.
The A.I. programme, called ‘STORK’, was trained using time-lapse recordings of the development of over 10,000 embryos, and then matched and tested for decision-making, against five embryologists.
STORK agreed with the majority decision of the embryologists (3 out of 5) in 95.7 percent of cases proving that it could be a valuable partner in embryo evaluation.
‘Our algorithm will help embryologists maximise the chances that their patients will have a single healthy pregnancy’ said lead researcher, Dr Olivier Elemento. ‘The IVF procedure will remain the same, but we’ll be able to improve outcomes by harnessing the power of artificial intelligence.’
The group is now planning a trial to compare implantation rates between STORK and embryologist-selected embryos, in order to establish the clinical benefit of the system.
