algorithm blindness

In a new study, researchers have created an algorithm to predict the 10-year risk of amputation and blindness in people with diabetes.

The research, which was conducted at the University of Nottingham in the UK, found that most people have a much lower risk of these complications than they think.

How was the study conducted?

The researchers took data from two large databases and used a range of variables to get a sense of complications risk. Variables included:

  • Type of diabetes
  • Years since diagnosis
  • A1c
  • Age
  • Smoking status
  • Blood pressure
  • BMI

Using this data they developed their algorithm, then turned the algorithm into a web calculator. Users can input a number of details about their diabetes, and the calculator returns a percentage risk of amputation and blindness within 10 years.

“We have developed and externally validated risk prediction equations to quantify the absolute risks of blindness and lower limb amputation over 10 years in men and women with type 1 and type 2 diabetes,” the researchers wrote. “To our knowledge, these are the first tools for predicting the 10-year risk of both blindness and amputation, two of the complications that most concern patients with diabetes and affect quality of life.”

The calculator can be accessed here.

Algorithm to predict complications risk: how might these findings affect diabetes treatment?

The researchers hope that their findings will be used to inform diabetes management decisions. They also note that having a more realistic idea of blindness and amputation risk could reduce undue diabetes-related anxiety and depression.

“[M]ore accurate individualised information on the risk of complications may help patients to make more informed decisions about the balance of risks and benefits of treatment options reflecting their own values and choices,” the researchers wrote. “Overestimation of the risk of complications might lead to increased levels of anxiety and depression, which could negatively affect quality of life. This is especially important as patients with diabetes are more likely than the general population to experience anxiety and depression.

“[M]ore accurate methods for stratifying patients according to their absolute risk of complications could enable screening programs to be tailored to an individual’s level of risk and support the more rational use of scarce resources.”

The findings are published in the BMJ.