Artificial intelligence spots type 1 diabetes in children earlier, research finds

Artificial intelligence spots type 1 diabetes in children earlier, research finds

A predictive tool using artificial intelligence could provide hope for earlier diagnosis of type 1 diabetes in children across the UK, a new study has identified. 

Early research presented at the Diabetes UK Professional Conference 2022 has revealed that artificial intelligence reduces the risk of potentially fatal diabetes ketoacidosis (DKA) in children.

Type 1 diabetes is a serious auto-immune condition that cannot yet be prevented, and the gradual destruction of insulin-making beta cells can start months or even years before being diagnosed.

Symptoms usually start to appear much closer to diagnosis. Early diagnosis and awareness of the signs and symptoms of diabetes are crucial to ensure that both children and adults who develop it do not become critically ill. 

A quarter of children and young people are not diagnosed with type 1 diabetes until they are in DKA, a life-threatening condition that can lead to coma or even death. 

With funding from Diabetes UK, Dr Julia Townson, Senior Research Fellow at Cardiff University, and her team used artificial intelligence and electronic health records to develop a predictive tool. The tool was trained on data from one million children to detect patterns in their GP records that could signal they have undiagnosed type 1 diabetes. 

The team tested different combinations of factors from GP records to discover which could best predict a diagnosis of type 1 diabetes, including urinary infections or bedwetting, family history of type 1 diabetes and being prescribed antibiotics.

To see if the predictive tool could correctly spot children already diagnosed with type 1 diabetes, researchers then assessed how well it worked using GP and hospital records from another 1.5 million children.

When the researchers set the level to 10% (meaning 1 in 10 children under 15 consulting with a GP would raise an alert), the tool successfully identified 75% of children who would go on to develop type 1 in the following 90 days. On average, it would have allowed children to be diagnosed – and started on life-saving insulin therapy – 11 days earlier than they were, which could be the difference between life and death for someone.   

Dr Lucy Chambers, Head of Research Communications at Diabetes UK, said: “Type 1 diabetes isn’t currently preventable and is an extremely serious condition.

“If left undiagnosed, it can progress and lead to dangerous complications very quickly, so finding a way to catch the condition and treat it early could help to avoid emergency hospital treatment and save lives.”

She added: “This research, funded by Diabetes UK, could in the future be used by the NHS to help alert GPs to the possibility of a child developing type 1 diabetes, helping more children get an accurate and rapid diagnosis, and have the best possible start to life with type 1 diabetes.”

Dr Julia Townson, Senior Research Fellow at Cardiff University’s Centre for Trails Research, said: “We are now looking to see how this tool might work with primary care computer systems.

“If possible, this would enable us to carry out a feasibility study to assess the acceptability of the tool with GPs. Use of the tool may be some years away yet – but we are hopeful it will provide a vital new avenue for early diagnosis of diabetes which could save lives.”

Beth Baldwin tragically lost her 13-year-old son, Peter, to DKA in 2015. Peter was undiagnosed type 1 diabetes when he passed away.

Beth said: “Life without Peter is incredibly hard, but the potential to speed up diagnoses of type 1 diabetes for others in the future, and in doing so save lives in his memory, drives us and keeps us going.

“If our work stops even one family going through the experience of losing a child to type 1 diabetes, it will have been worth it.”

Beth has campaigned tirelessly to raise awareness of type 1 diabetes and its symptoms in memory of her son.

She added: “It’s so important that parents are aware of the 4 Ts – toilet, thirsty, tired, thin – so that they are able to spot symptoms of type 1 diabetes in their children as early as possible.

“Going to the toilet a lot, being excessively tired or thirsty and unexplained weight loss are all red flags, and if you spot them, it’s so important to act quickly and seek medical help.”

Photo by: Alexander Dummer

Author: Eileen Gilbert