Hormone Intelligence

Applying artificial intelligence to modelling female hormones enables women to access hormone intelligence at her fingertips

Female hormone networks form the most complex aspect of the endocrine system. The menstrual cycle depends upon a delicate web of feedback mechanisms that trigger significant changes in hormone levels. This intricate physiological process generally operates reliably, but its timing and the hormone levels are affected by internal and external factors going on in a woman’s life. This is why women differ in their experiences of menstrual cycles and why an individual woman may notice differences between cycles.

Apart from being fascinating from a physiological point of view, why is this so important from a practical point of view for women? The reason is that female hormones are not just about fertility. The ovarian hormones oestradiol (most active form of oestrogen) and progesterone have significant effects through the body. Every biological system is dependent on these hormones: bones, muscle, nervous system, including brain function, skin, the cardiovascular and digestive systems [1]. This is why female hormones impact all aspects of health: physical, mental and social [2].

The cyclical fluctuations in female hormones occurring every menstrual cycle will also change over a woman’s lifespan. Completion of puberty is marked by the start of menstrual cycles: menarche. During her adult life a woman can expect regular menstrual cycles. However, subtle hormone disruption can be missed. Although blood testing is the most accurate way of measuring all four of the key female hormones, the standard protocol of taking a blood test at one time point in the cycle, when hormones are at their most quiescent, can miss subclinical menstrual cycle hormone dysfunction.

For example, in subclinical anovulatory cycles, although a woman may experience regular menstrual periods, subtle mistiming of female hormones will not be detected with a routine single blood test. Yet this type of hormone disruption can have potential adverse consequences on health. This is particularly relevant for exercisers, athletes and dancers who are either on the brink of or recovering from low energy availability. Early identification and prevention of relative energy availability in sport (RED-S) is important for both health and exercise performance [3].

A similar situation arises for women in the perimenopause when the responsiveness of her ovaries starts to decline. This is further complicated by the fact that the decrease in ovarian hormone production is not a smooth linear process. A blood test at a single time point may not identify these changes in key female hormone networks. Although perimenopause is a natural physiological process, it can be a challenging time for women, magnified by uncertainty. All change for female hormones

Women need a new, more supportive approach, to take away uncertainty and to empower them with insights into their hormone networks.

How can a woman understand the details of her female hormone network? In theory she could take daily blood tests for the four key hormones: pituitary control hormones follicle stimulating hormone (FSH), luteinising hormone (LH) and ovarian response hormones oestradiol and progesterone. Clearly this is not practical, but it may be possible to use fewer blood tests over a cycle. Machine learning, specifically Bayesian inference, can help by optimally combining test results with background information. This background knowledge includes medical understanding of hormone networks and the characteristics of the individual woman. Machine learning can revolutionise healthcare, as outlined in the report from the Chief Medical Officer of England [4]. It is an approach widely used in modelling biological systems [5]. Artificial intelligence is an important clinical tool to support the optimisation of personalised health [6].

It has recently become possible to create a personalised digital fingerprint of a woman’s menstrual cycle hormone network from just two finger prick capillary blood samples taken during a cycle. Artificial intelligence combines deep medical and mathematical understanding of female hormone networks with the individual details of a woman’s menstrual cycle length, age and activity levels. An expert report, providing an explanation of results with actionable, evidence-based advice, can be supplemented with a personal clinical medical discussion. This gives women the long-needed opportunity to connect with their personal female hormone networks. It empowers each woman to adopt a personalised, effective and proactive approach to optimise her hormone health.

To learn more about artificial intelligence applied to female hormone networks, have at look at previous discussions and forthcoming events where I am presenting on this topic and application of this approach for female health.Presentations

To take advantage of this exciting opportunity of fingerprinting hormone networks, you can order Female Hormone Mapping™ which combines medical, mathematical and technology expertise via the Forth website (available on a discounted introductory offer for a limited time). Your personal report is delivered at your fingertips on a mobile app. You can book an appointment for a personal discussion of your report with me Female Hormones

Every woman’s hormone network fluctuations are personal to her. Every woman is an individual.

References

Article St John’s College, Cambridge University

[1] Keay, N. What’s so good about Menstrual Cycles? British Journal of Sport and Exercise Medicine 2019

[2] Keay, N. Of Mice and Men (and Women) British Journal of Sport and Exercise Medicine 2019

[3] Keay, N. Relative energy deficiency in sport (RED-S) British Journal of Sport and Exercise Medicine 2018 and British Association of Sport and Exercise educational website Health4Performance

[4] “Machine learning for individualised medicine” Mihaela van der Schaar, Chapter 10 of the 2018 Annual Report of the Chief Medical Officer. Health 2040 – Better Health Within Reach. Accessed 2021

[5] Van de Schoot, R., Depaoli, S., King, R. et al. Bayesian statistics and modelling. Nat Rev Methods Primers 1, 1 (2021). https://doi.org/10.1038/s43586-020-00001-2

[6] Artificial Intelligence AI council. UK Government 2021


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s