Huang Zhongwei MBBS, PhD; Cheong Jit Kong, PhD
Competition Sponsor: Ministry of Health and National Research Foundation of Singapore
Infertility affects ~15% of Singapore’s population. The number of couples in Singapore seeking assisted reproductive technology (ART) to help them conceive more than doubled from 2005-2013. With the median age at first marriage and first birth rising, demand for ART treatment is set to increase but ART success rate hovers around 30–40%; it rapidly drops with increasing maternal age due to the inevitable decrease in oocyte numbers and quality. Yet, effective therapeutics to combat reproductive ageing in woman is sorely lacking. In current clinical practice, a woman’s reproductive lifespan and health-span is only determined by her age and one serum ovarian reserve marker, Anti-mullerian hormone (AMH), which is far from ideal. We thus hypothesise that miRNAs can be accurately quantified in follicular fluid and cumulus/granulosa cells and these molecular footprints coupled with the woman’s demographic characteristics can be used together to build a framework, via machine learning, to provide predictive power to infer true ovarian age and oocyte quality that will inform accurately on reproductive senescence. Having a robust predictive framework, based on accurate miRNA expression profiling, will aid clinicians in their decision-making process, allowing a precise, holistic and robust assessment of a woman’s true reproductive potential and longevity.