CUHK develops tool for early hypoglycemia warnings amongst high-risk adults

The faculty analysed a dataset from the HADCL from 2013 to 2018.

The Chinese University of Hong Kong (CUHK)’s Faculty of Medicine (CU Medicine) has developed a machine learning model for early detection of severe hypoglycemia amongst high-risk adults.

In collaboration with the Hospital Authority Data Collaboration Laboratory (HADCL), the faculty’s research team analysed about 1.5 million records of more than 360,000 older adults with diabetes from 2013 to 2018.

The model utilised 258 predictors, including demographics, admissions, diagnoses, medications and routine laboratory tests in one year to predict severe hypoglycemia occurrences that require hospitalisation in the following 12 months.

ALSO READ: PolyU partners with ZEISS for myopia control tech advancement

“As the mortality gap between older adults with and without diabetes has not narrowed, we need to take action to address the excess mortality associated with diabetes by providing better and more precise management for patients.” Juliana Chan, Chair Professor of Medicine and Therapeutics at CU Medicine, said.

The new model, upon validation, achieved a positive predictive value of 85%.