A research team at Imperial College Healthcare and staff from Imperial College London recently published findings from an AI analysis, noting that AI could help guide the optimum time to collect eggs for IVF success.
The analysis looked at 19,000 patients who had completed IVF treatment, using “explainable AI” to provide an understanding of how decisions or predictions were made, and examining the follicle sizes associated with retrieving more mature eggs and babies being born. The results showed that giving patients a hormone injection to prepare the eggs for collection was linked to being more successful when follicles were sized between 13-18mm.
The team now plan to apply for funding to then test their findings in a clinical trial and create an AI tool that will use “data, including findings from this study, to personalise IVF treatment and support doctors’ decision making at each step of the IVF process”.
Dr Ali Abbara, consultant in reproductive endocrinology and co-senior author of the study commented: “IVF provides help and hope for many patients who are unable to conceive but it’s an invasive, expensive, and time-consuming treatment. It can be heartbreaking when it fails, so it’s important to ensure that this treatment is as effective as possible. AI can offer a new paradigm in how we deliver IVF treatment and could lead to better outcomes for patients.”
When discussing the role of AI in healthcare, Dr Thomas Heinis, co-senior author from the department of computing at Imperial College London, added: “Explainable AI can be a valuable resource in healthcare. 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.”
AI in healthcare
In other news for Imperial College Healthcare, last month the trust published a framework on their approach to future-proof the trust’s adoption and utilisation of AI. It defined four focus areas of work where AI can help to solve key problems including: delivery of clinical care; clinical and patient administration; corporate back office functions; and prediction and prevention. Learn more about this framework here.
South Yorkshire Digital Health Hub recently announced £500,000 of funding for seven innovative projects to help with disease diagnosis and address health inequalities across the region. This includes several projects which utilise AI to help improve healthcare, including using AI and data from wearables to help diagnose coronary artery disease and using AI to better predict how long people with lung cancer will live and how well they will respond to treatment.
Earlier this month, we reported on the development of a new device that helps with identifying the most common causes of dizziness. Norfolk and Norwich University Hospitals has been working with University of East Anglia to create the Continuous Ambulatory Vestibular Assessment (CAVA), employing 20 hospitals to take part in a clinical trial to help train its AI algorithm.
