Preparing follicles for egg retrieval may be most effective when they are sized between 13 and 18mm, a new study has found.
In a retrospective study, researchers from Imperial College Healthcare and Imperial College London analysed data from more than 19,000 patients who had completed IVF treatment to find out which follicle sizes were associated with improved rates of babies being born. The analysis was conducted using a process that allows humans to understand and trust the results of machine learning algorithms, known as 'explainable artificial intelligence (AI)'.
'IVF produces so much rich data that it can be challenging for doctors to fully make use of all of it when making treatment decisions for their patients,' said Dr Ali Abbara, clinical scientist at Imperial College London and co-senior author of the study. 'Our study has shown that AI methods are well suited to analysing complex IVF data. In future, AI could be used to provide accurate recommendations to improve decision-making and aid in personalisation of treatment, so that we can give each couple the very best possible chance of having a baby.'
The study published in Nature Communications used data from patients aged between 18 and 49 and who had had treatment in one of 11 clinics in the UK, and two in Poland.
During IVF treatment, a hormone injection known as a 'trigger' is given to prepare eggs for collection. The timing of this trigger impacts the number of mature eggs retrieved, and the ultimate success of the treatment, but methods to determine the best time for the trigger are not precise.
On average, each ovary has between six and ten follicles which can grow to 23mm. The trigger injection is given when an ultrasound reveals that the largest of these follicles is around 17mm, with the sizes of each individual follicle or the likelihood of a mature egg being yielded, not taken into account.
The research team found that increasing the proportion of follicles of an intermediate size – between 13 and 18mm – could increase the number of mature eggs retrieved and lead to more births.
The study also revealed that stimulating the ovaries for too long could have a negative impact on IVF success by prematurely stimulating the hormone progesterone, which is associated with the development of the tissue that lines the uterus.
'Explainable AI can be a valuable resource in healthcare,' said Dr Thomas Heinis, co-senior author from the Department of Computing at Imperial College London.
'Where the stakes are so high for making the best possible decision, this technique can support doctors' decision making and lead to better outcomes for patients. Importantly, we expect computing power to improve exponentially in the near future, enabling us to make decisions using precise data in a way that hasn't been possible previously.'
Source:
Lynne Smit - https://www.progress.org.uk/ai-could-identify-optimal-follicle-size-for-ivf-success/
