The model has the potential to be built-in into digital well being document choice help system
In Hong Kong, one in three adults over the age of 65 have diabetes. To enhance the administration of this group of older adults, The Chinese University of Hong Kong (CUHK)’s Faculty of Medicine (CU Medicine) carried out a territory-wide evaluation of the massive dataset from the Hospital Authority Data Collaboration Laboratory (HADCL).
Severe hypoglycemia is a standard acute complication in sufferers with diabetes, which is related to an elevated risk of falls, heart problems, dementia and all-cause mortality. Using knowledge from HADCL, CU Medicine developed a novel machine learning model that may predict the risk of severe hypoglycemia in the following 12 months amongst older adults with diabetes.
With a excessive optimistic predictive worth of 85%, the model has the potential to be built-in into digital well being document choice help techniques for pre-emptive intervention in older adults on the highest risk.
Dr Elaine Chow, Associate Professor, CU Medicine’s Department of Medicine and Therapeutics and lead investigator for the analysis, mentioned, “The newly developed model will be built-in into the native digital well being document system to establish high-risk adults for pre-emptive intervention – for instance, by switching to diabetes drugs with decrease hypoglycemic potential or correcting the timing and dosage of insulin injections.”
Professor Juliana Chan, Chair Professor of Medicine and Therapeutics at CU Medicine, concluded, “As the mortality hole between older adults with and with out diabetes has not narrowed, we want to take motion to deal with the surplus mortality related to diabetes by offering higher and extra exact administration for sufferers. Our machine learning model gives a extremely environment friendly and low-cost strategy to figuring out older adults with a really excessive risk of hospitalisation due to severe hypoglycemia, enabling corrective motion for this group of sufferers with out compromising the glycemic management in low-risk aged sufferers.”
https://www.biospectrumasia.com/news/98/24117/hong-kong-develops-machine-learning-model-to-predict-risk-of-severe-hypoglycemia-in-diabetics.html
