The invention relates to the technical field of medical
artificial intelligence, and particularly discloses a method for establishing a
disease prediction model of GCK-MODY in
gestational diabetes population based on
machine learning. The model takes five clinical characteristics as input variables: a
body mass index before
pregnancy, fasting blood glucose and glycosylated
hemoglobin levels during GDM diagnosis, continuous multi-generation diabetes family history and a newly discovered
predictive factor, namely GDM diagnosis week of
pregnancy. A classification model is constructed through a
support vector machine algorithm, and a SHapley additive interpretation method is adopted to provide global and local interpretation of a prediction result, so that model transparency is enhanced. The area of the model under a curve in a test is obviously superior to that of an existing screening standard. The invention also provides an electronic device, a storage medium and a
prediction system comprising the model, which can assist clinicians in early recognition of GCK-MODY high-risk patients, provide decision support for targeted
gene detection, avoid unnecessary enhanced hypoglycemic treatment of pregnant women, reduce the risk of maternal and infant complications, and promote precise medical development of
gestational diabetes mellitus.