AI could boost IVF success rates major study finds

Women could avoid the heartbreak of suffering a miscarriage or stillbirth during fertility treatment with the use of artificial intelligence.A study shows that having a baby using IVF would be more likely if clinics used a computer to assess embryo quality.Half of all miscarriages are caused by an abnormal number of chromosomes in the embryo.Working out which is the best to transfer into the womb is considered key to IVF success.The new study shows that when a computer equipped with AI was shown images of hundreds of embryos, it could predict which would lead to a live birth with 85 per cent accuracy.Researchers say the technology could be available for use within five years, revolutionising fertility treatment.The team, from Imperial College, London and Cornell University in the USA, is set to present their data to the American Society for Reproductive Medicine conference in Denver today (Wednesday). Dr Nikica Zaninovic, from Cornell University, who led the study said: “If AI can recognise embryos that are normal and those that have abnormal chromosomes, that will result in a reduced miscarriage and stillbirth rate, which is the reason for doing this research.“This is something new and an 85 per cent success rate is huge.”The researchers say that hospitals and fertility clinics would not need to buy the computer. Instead they could simply send photos of embryos to the machine and would receive results ‘in minutes.’The AI system is based on time-lapse photographs of growing embryos that are already used in many fertility clinics.A photo is taken of the embryo every 10 minutes and given to embryologists who use their expertise to decide which appear normal.Looking at images rather than putting an embryo under a microscope may reduce the risk of damaging it.One study published in the British Journal of Obstetrics and Gynaecology earlier this year showed time-lapse imaging could improve live birth rates in women using fresh embryos by up to 28 per cent.However, the Human Fertilization and Embryology Authority has recently said that more research is needed before patients can be told it guarantees a higher chance of having a baby.The latest study on adding AI to time-lapse imaging could provide this missing data that doctors and patients need.The computer, nicknamed “The Beast”, was given 700 images of embryos and told which resulted in a birth and which led to a miscarriage or stillbirth so it could learn to search for subtle changes that could indicate a problem.In the trial, the computer analysed images of 328 embryos implanted into prospective mothers.When asked which of these would result in a baby being born, it correctly identified 280.The machine is also capable of continuing to learn from the data it is given, adapting its algorithm to make it ever more accurate.Dr Zaninovic added: “To make a baby embryo is probably 80 per cent to 90 per cent of the value [reason] but there are other factors why an embryo doesn’t make a life birth.“So these numbers are almost 100 per cent because there are other factors in the mother after implantation. That’s why we think this is extremely high.”He said that in his clinics, women under 35 with no underlying health conditions had around a 50 per cent of having a baby using IVF and time-lapse imaging.Using AI, this could rise to between 60 and 70 per cent, he added.Dr Zaninovic, whose team are currently patenting the technology, said: “I just need patient information from a hospital in London and the image of the embryo and I can put this in the computer.“It’s all web based. It doesn’t mean every hospital will have to have this it can just be done over the internet very easily.”He added: “Within five years it will be routinely used in clinical settings.”Leading UK fertility expert Prof Allan Pacey, of Sheffield University, said: “The ability to observe embryo development using time lapse systems has developed greatly in recent years and these devices have become commonplace in clinical practice.“However to date, data doesn’t find that they actually help in selecting the best embryo and improving the chances of pregnancy.“Therefore the application of artificial intelligence to the data collected from time lapse systems is a very good idea as it may find patterns and algorithms that are not visible to the human eye.”Prof Charles Kingsland founded Britain’s largest NHS IVF unit, the Hewitt IVF centre in Liverpool, which was the first to successfully use time-lapse technology.Prof Kingsland, clinical director of CARE Fertility, said: “Although the numbers in the study are small these results are encouraging.“By adding artificial intelligence to the computer, this takes it one stage further into the future.“The final arbiter in embryo quality though will always be a highly trained embryologist or clinician.“We’re many years away from dispensing with humans in the IVF lab.”Meanwhile, experts have raised fears that an “Instagram generation” of young British women do not realise they should take folic acid before they fall pregnant.A survey of 11,000 women found that more than half of 18-24 year-olds who wanted to conceive do not take the vitamin.Folic acid can prevent birth defects in babies such as spina bifida. But in order to benefit from its protective effects, women need to take it before they start trying to conceive.Researchers from fertility test company SPD said public health messages need to target online forums and sites such as Instagram and SnapChat, amid fears young women are not receiving information from traditional routes. Want the best of The Telegraph direct to your email and WhatsApp? Sign up to our free twice-daily  Front Page newsletter and new  audio briefings. read more