The Rise of Technology in Health Data Research

Living with diabetes since the age of one, 34-year-old Londoner Manveer Sahota has always had a good understanding of his condition, its impact on his daily life and the long-term implications for his health.

While on vacation in India when he was 16, his parents accidentally injected him with too much insulin and he suffered severe hypoglycemia when his blood sugar dropped dangerously low. Luckily, they got his hypo under control, before he passed out, by injecting him with glucose.

A few days later, Manveer experienced his first panic attack, later resulting in anxiety, which he has battled ever since.


In an office at the University of Glasgow, HDR UK-UKRI researcher and fellow Dr Rona Strawbridge is studying the biological links that contribute to mental illness, diabetes, heart disease and obesity.

Dr Strawbridge moved to the University of Glasgow in 2017 and began using genetic data to explore the observed link between psychiatric disorders and cardio-metabolic diseases such as diabetes – and why these people have longer life expectancies. 10 to 20 years shorter than the general population.

“For a long time, lifestyle factors were thought to be responsible for these conditions that occur together in people with mental health problems – such as diet, physical activity levels and smoking; but in fact, genetic studies show there is more to it, and the same biological pathways could contribute to both mental and physical health issues,” she says.

Learning about the research facilitated by HDR UK, Manveer says: “I had always suspected there was a link between mental illness and diabetes. I knew that my diabetes made me anxious and that anxiety and depression affected the way I managed my diabetes. But I didn’t think there could be a genetic link to it.

Dr Strawbridge’s hope is that by identifying the links between mental and physical conditions, opportunities may arise “such as the repurposing of existing drugs for conditions such as heart disease and diabetes for people with health problems. Mental Health”.

Rona goes on to explain that another benefit of data linkage is that clinicians can intervene earlier to manage a patient’s mental and physical health.

“A person with mental illness might be more vulnerable to poorer health outcomes, which could impact a clinician’s treatment decisions,” she says. “For example, if someone with a mental illness is having trouble controlling their diabetes, perhaps they should be prioritized for more frequent blood pressure monitoring, as it is an indicator of heart disease, kidney function and eye health.”

“Because my anxiety is tied to my fear of low blood sugar,” says Manveer, “I sometimes kept my sugars too high. Unfortunately, it caused damage to my eyes, kidneys and nerves.

A family history of diabetes is often recorded when considering the likelihood of presenting with the condition. “Perhaps family history of mental illness should also be considered in monitoring risk and predicting physical conditions,” adds Dr Strawbridge with the caveat that earlier generations may not have any. not be spoken so freely.

Beyond linking existing data, HDR UK is working to improve the quality and diversity of UK data assets to improve the quality of datasets, enable new discoveries and better understand the disease. This in turn provides fairer and more equal access to the latest medical treatments and technologies, benefiting as many people as possible across the UK.

HDR UK’s mission to unite the UK’s diverse health data is welcomed by Dr Strawbridge, particularly as it considers the risk of drawing conclusions from existing data which is often collected from people of European.

“There is much less data on people of non-European ancestry for many conditions,” she says. “We need to operate in a healthcare system with diverse data that is truly integrated. The more data we have, the more we can isolate trends and tailor care to certain groups. »

Manveer says he’s never had a problem with the use of his data, but now that he understands how it’s being used to improve individual care as well as population health, he wants to get involved.

“I’m very happy to share my story and my data, but it makes sense that it’s anonymized in research,” he says. “And if research can lead to early intervention that can help people with certain conditions, shouldn’t we all be doing our part?” he says.

Mental illness affects almost everyone at some point in their life and is the leading cause of poor health for people living in the UK. People living with mental illness are less likely to participate in research studies and may also be actively excluded. Much of what is known about mental health is not based on the very people who are most affected.

To address this, HDR UK and the Medical Research Council (MRC) have helped support the creation of DATAMINDa collaborative mental health data hub that aims to improve the use of big data for mental health research.

DATAMIND Co-Director Ann John says: “The UK has a real opportunity to be the world leader in mental health data science, and the work of organizations like HDR UK and DATAMIND is making exciting progress. towards this ambition. By working with the public, patients, researchers, industry and the NHS, we are transforming both our understanding of mental health and the lives of people with mental health conditions. And we are creating a hub where researchers and others can find and use mental health data to benefit patients and the public and improve care.

Health data, collected by GPs through routine health records rather than specific clinical trials, represents a wealth of information that can help improve outcomes and address long-standing disadvantages faced by people with mental illness.

However, the clinical notes produced by mental health professionals are usually written in a descriptive manner, which means that data about mental disorders are not captured in a way that can be easily analyzed by computers. Until fairly recently, this precluded large-scale studies using this type of mental health record.

Technicians and researchers from South London and Maudsley NHS Foundation Trust, supported by HDR UK among others, have solved this problem by developing platforms to extract and analyze mental health records, as well as security and governance frameworks for data to keep the information anonymous and the patients involved in its monitoring. This Interactive clinical record search (CRIS) has been operational for 15 years and has supported more than 250 research publications.

The South London and Maudsley Trust is one of the largest mental health care providers in Europe, enabling researchers to analyze data from around 500,000 patients and 30 million clinical records.

Teams of bioinformaticians, biostatisticians and clinicians have designed a range of automated text mining tools to extract information alongside manual analysis. For example, this approach recently allowed the team to identify 21 physical health problems in the records of patients with mental disorders.

Richard Dobson, Professor of Medical Bioinformatics at King’s College London, who works in partnership with the Trust, says: “The key for us has been to accept the way data is collected and to adapt our style of research to that. . Instead of building new structured systems and trying to get clinicians to use them, we focus on finding ways to analyze existing health data.

“For example, our tool CogStack is able to extract data from these different systems and sources – like PDFs, Word documents, text fields and more – and is trained to understand and analyze the “natural language” they contain. It does this by transforming the data into something structured, like a spreadsheet, and coded in medical terms that machines can understand.

The result is data that can be discovered by researchers through a search engine, then linked and analyzed at scale to improve public health.

Since its creation, cutting-edge research in AI has required very specific technical expertise, a lot of computing resources and a substantial budget. Today, systems like CogStack and CRIS create user-friendly interfaces and easy downloads for healthy people with no computer experience to work with datasets.

This means healthcare analytics will continue to grow and evolve alongside the digitization of the NHS, although the impact is only beginning to be felt by Manveer and others of his generation.

However, with the rise of cutting-edge software allowing clinicians to develop tailored care plans alongside traditional methods of improving a patient’s health, today’s research will be tomorrow’s care for all. .


Sean N. Ayres