ДалееСледующее руководство
Выбор площадок для клинических испытаний с помощью ИИ
Отрасли
РУКОВОДСТВО ПО Отраслям
AI embryo selection uses models trained on time-lapse videos or images of embryos to rank which embryo in an IVF cycle is most likely to implant, helping clinics choose which to transfer first.
Прослушайте это руководствоОзвучено ИИ · ~3 min
It matters because IVF is costly and emotionally demanding, and a better first choice could shorten time to pregnancy. Trial evidence so far shows AI saves embryologists time but has not clearly raised pregnancy or live-birth rates.
In IVF, eggs are fertilised in the laboratory and the embryos grow for about five days to the blastocyst stage. When several embryos are available, the clinic chooses which to transfer first. Traditionally embryologists do this by eye, grading features such as how expanded the blastocyst is and the quality of its inner cell mass and outer layer, the trophectoderm, often with the Gardner grading system. Time-lapse incubators, such as Vitrolife's EmbryoScope, photograph each embryo every few minutes without removing it from the incubator. This produces a video of development, including when each cell division happens. AI models trained on these videos, and on whether transferred embryos went on to implant, generate a ranking score. Examples include Vitrolife's iDAScore, Fairtility's CHLOE, and Presagen's Life Whisperer, which works from single still images. The evidence is more modest than the marketing. A large randomised trial published in Nature Medicine in 2024 compared iDAScore with standard morphology grading and did not show the AI was non-inferior on clinical pregnancy rates, although it greatly reduced the time embryologists spent assessing embryos. Cochrane reviews of time-lapse imaging have found the evidence uncertain on whether it improves live-birth rates. A crucial point is often missed: ranking cannot create a better embryo. It only changes the order in which a patient's existing embryos are used. For patients who will eventually transfer all their embryos, the main possible gain is getting pregnant sooner, not a higher overall chance. Ethical questions include charging for add-ons with weak evidence, opaque scores patients cannot question, models trained on data from particular clinics or populations, and a slide toward selecting embryos for traits. Polygenic embryo screening, which claims to rank embryos by genetic risk scores, has been widely criticised by genetics societies as unproven.
A clinic's time-lapse incubator records each embryo at short, regular intervals for five days, and software gives each blastocyst a score used to decide which to transfer first.
An embryologist uses an AI ranking to check their own grading, spending much less time per embryo while still making the final decision.
A patient with only one good-quality embryo learns that AI ranking cannot improve her chances, because there is nothing to choose between.
A clinic considers adding an AI scoring fee to its price list and reviews the randomised trial evidence before deciding whether to charge patients for it.
More randomised trials comparing AI ranking with standard grading, ideally measuring live birth and time to pregnancy, are needed before AI scores can be called better rather than just faster. Research is also exploring whether images can predict chromosomal normality without a biopsy, but those predictions are not yet reliable enough to replace genetic testing. Expect regulators and professional bodies to keep scrutinising IVF add-ons and how they are marketed. Debate over polygenic embryo screening and trait selection will continue, with most genetics experts urging caution. The most realistic near-term benefit is standardising and speeding up embryologists' work.
Бесплатная рассылка
Три проверенных AI-истории каждое утро буднего дня, написанные простым английским. Бесплатно навсегда, без рекламы.
Одно электронное письмо каждый будний день. Отписаться в один клик. Мы никогда не продаем и не передаем ваш адрес.
Проверьте себя
Мгновенная обратная связь по каждому ответу и общий сертификат с проверяемым идентификатором после прохождения курса.
Поддержите бесплатное образование в области искусственного интеллекта. AI Understanding — это некоммерческая организация 501(c)(3). Никакой рекламы и платного доступа. Сделать пожертвование
AI embryo selection uses models trained on time-lapse videos or images of embryos to rank which embryo in an IVF cycle is most likely to implant, helping clinics choose which to transfer first. It matters because IVF is costly and emotionally demanding, and a better first choice could shorten time to pregnancy. Trial evidence so far shows AI saves embryologists time but has not clearly raised pregnancy or live-birth rates.
Он захватывает частые изображения внутри инкубатора, создавая видео развития, например, время деления клеток.
Исследование не продемонстрировало не меньшей эффективности при клинической беременности, хотя эмбриологи потратили на оценку гораздо меньше времени.
Эмбрионы одни и те же, в каком бы порядке они ни использовались, поэтому основным возможным преимуществом является более ранняя беременность.
Эмбрионы, которые никогда не переносились, не имели известного результата, а меченые эмбрионы были предварительно отобраны, что искажало данные обучения.
Дискриминация невелика, поскольку матка, генетика и случайность сильно влияют на то, произойдет ли имплантация.
Продолжайте учиться
Другие руководства, выбранные по этой теме
ДалееСледующее руководство
Выбор площадок для клинических испытаний с помощью ИИ
Отрасли