This article contirbuted by Andrew Horne was first published on healthandcare.scot

Our capacity to diagnose and treat endometriosis lags behind that of other chronic conditions that similarly blight lives. But machine learning could change that, says consultant gynaecologist and Special Advisor to Scotland’s Chief Medical Officer for Obstetrics and Gynaecology, Professor Andrew Horne.

Despite one in ten women being affected, endometriosis – a painful condition where womb-like tissue grows outside of the womb –  is still under-researched and poorly understood. Lack of funding and interest in the disease has meant that our knowledge trails years behind that of other chronic conditions such as heart disease, asthma and diabetes.

Diagnosing endometriosis takes on average eight years, and treatment still involves trial and error, and often a blunt approach of hormones and/or surgery.  

One in ten women living with chronic pain, waiting years for diagnosis and then not being able to access effective treatment is not acceptable in the 21^st century. We need to use the modern tools at our disposal – AI and machine learning – to leapfrog the hurdles and close the knowledge gap around this prevalent, debilitating disease.

In a new way of working for me, I am collaborating with my University of Edinburgh colleague, Thanasis Tsanas, Professor of Digital Health and Data Science and the Usher Institute’s Director of Knowledge Exchange and Research Impact. We are working on a new health data research project, called Endo1000.

We aim to collect data from 1000 women with suspected endometriosis, from their sleep rhythms to their genome, over two years. We will then process that data with machine learning to ‘phenotype’, or map, symptoms, and ultimately improve diagnosis and treatment. 

Firstly, we will use wearable sensing technology to collect data on movement, activity, temperature changes and sleep patterns, without interfering in participants’ daily lives. So women would wear a device like a smartwatch and go about their day-to-day while we capture this information. 

Secondly, these insights will be combined during data processing with information participants would track and record themselves using specially designed apps: their symptoms, treatments, surgeries, diet and exercise patterns. 

Thirdly, we will support participants to collect saliva, blood, urine and faecal samples at home, that will allow us to test for information about genes (the ‘genome’), the gut (the ‘microbiome’) and their body’s metabolism (the ‘metabolome’).  

Recent research shows that that gut microbiome – the genetic material of all the microbes that live in your gut – could play a role in the formation of endometriosis.

By looking at blood samples, we can access hormonal information to see how stress and sex hormones interplay with pain flare-ups, for example.  

Thanasis has worked in the past on a similar project involving Parkinson’s and my colleague and Chair of Reproductive Steroids in Edinburgh, Professor Philippa Saunders, introduced us after seeing this work. These data models are supporting both diagnosis and prognosis, as well as helping us understand the genetic component of the disease, which means eventually we could predict who might develop it.

Professor Saunders shared some of her work into endometrial disorders with healthandcare.scot at an event organised by the Academy of Medical Sciences.

Thanasis and his team will develop algorithms so that artificial intelligence can filter the huge amount of data collected far faster than a human ever could. In doing so, the machine learning system can identify the patterns waiting to be discovered within the data.

Together, we will then interpret those patterns and eventually turn them into tools clinicians can use to improve diagnosis and treatment. 

At the moment, the diagnosis of endometriosis usually requires surgery (laproscopy) under general anaesthetic. However, waiting lists for laproscopy are extremely long. 

Unfortunately, treatment delays have occurred due to the fact that many women (and even doctors) normalise their symptoms such as abdominal pain during menstruation, or feel stigmatised by their symptoms. Through this project we hope to be able to better understand symptoms and create a better test to support improved diagnosis and treatment.  

Treatment options for endometriosis include hormones, such as the combined pill, which are not ideal for all patients, particularly younger ones who want to have a family. The alternative is surgery to remove the endometriosis – but this is not effective for everyone – and symptoms often recur. But we hope our project will be able to identify different interventions than can work at different stages to provide better, personalised treatments. 

The data will also allow us to study sub-types of endometriosis, as endometriosis is actually an ‘umbrella’ term that refers to a range of potentially diverse symptoms under a single diagnosis. 

Given its prevalence, we should have already spent years studying endometriosis, as we have with cancer. Now it’s time to catch up.

Find out more about the Endo1000 project