Could Retinal Scans Help Fertility Medicine?

Reproductive aging—the gradual diminution of a woman’s fertility—is a proverbial ticking clock that complicates family planning decisions for many individuals and couples. Realizing the need to have reliable biomarkers of this normal and inevitable process, many researchers point to anti-Müllerian hormone (AMH) as a robust biomarker for ovarian reserve, which can provide insights into an individual’s reproductive potential. However, the current method for measuring AMH levels is invasive and its accuracy is subject to variability due to hormonal fluctuations. Recent findings suggest a bidirectional relationship between AMH levels and vascular aging and propose that the latter could serve as a proxy for ovarian aging.  While not on the immediate horizon, the potential to use retinal imaging as a tool for assessing reproductive aging was described in this paper, offering a promising direction for early intervention and personalized care in clinical and community settings. These images from the study show retinal “heat maps” for different age groups based on AI assessment of the vasculature. Photo: Miao H, et al. NPJ Digit Med. 2025;8(1):367. Click image to enlarge. Into this environment comes retinal fundus imaging, long recognized for its quick and noninvasive ability to capture microvascular features in the eye that reflect systemic aging.“Given the vascular aspects of both retinal and ovarian aging, retinal imaging may represent a groundbreaking, noninvasive approach to predicting AMH levels and, by extension, reproductive health,” researchers based in China proposed in an article for NPJ Digital Medicine, a part of the Nature group of medical journals. “By combining advanced AI techniques with retinal imaging, this research represents a novel, multimodal approach to understanding reproductive aging.”The team developed a deep learning framework designed to predict retinal age from fundus images with high precision and used it to examine associations between the retinal age gap and AMH. Findings revealed a negative association between the retinal age gap and AMH levels, particularly among women aged 40 to 50. Lower AMH levels correlated with earlier reproductive aging milestones, emphasizing the predictive value of retinal aging. A smaller retinal age gap correlated with later menopause, indicative of prolonged reproductive function, further supporting its potential role as an indicator of reproductive aging.Using fundus images and incorporating healthy model weights derived from healthy cohorts (20,139 fundus images from 10,013 subjects), the research team developed a model using data from a healthy female cohort and examined the association between the retinal age gap and AMH levels. The healthy female cohort, consisting of 2,560 fundus images from 1,294 women aged between 25 and 47 years, was categorized into three groups based on AMH levels: high (n = 320, median = 4.66ng/mL), medium (n = 654, median = 1.96ng/mL) and low (n = 320, median = 0.58ng/mL). The retinal age model was then trained on the medium AMH group to capture typical female aging patterns.The model was used to predict retinal age in women from high and low AMH groups to explore the relationship between retinal age gap and AMH levels. While mean retinal age was similar across groups, the low AMH group showed a significantly higher retinal age gap (mean = 0.71 years) compared to the high AMH group (mean = 0.36 years). Age subgroup analysis revealed significant differences in the 40–50 years range, with the high AMH group showing a significantly smaller retinal age gap compared to the low AMH group of the same age group.“This age range is crucial for reproductive health, as AMH levels typically begin to decline in the years leading up to menopause,” the researchers wrote in their paper. “This decline in protective hormones may accelerate retinal aging, creating the link between reproductive aging and retinal health.”The team did emphasize that the cross-sectional study design restricted causal inferences, and longitudinal studies are needed to establish temporal relationships. They also suggested expanding the sample to include multiethnic cohorts as well as women with diverse reproductive conditions, such as primary ovarian insufficiency or polycystic ovary syndrome. Doing so would enhance the study’s generalizability. Technical improvements, such as higher-quality retinal imaging, could also refine model accuracy, while balancing dataset age distribution would help minimize bias.“Ultimately, the integration of AI, retinal imaging and genetic data holds great promise for advancing our understanding of reproductive aging and improving women’s health care outcomes,” the researchers concluded.Click here for the journal source. Miao H, Liu S, Wang Z, et al. Artificial intelligence-derived retinal age gap as a marker for reproductive aging in women. NPJ Digit Med. 2025;8(1):367.