Development and validation of a prediction model for self‐reported hypoglycemia risk in patients with type 2 diabetes: A longitudinal cohort study

Abstract

Abstract Aims/Introduction To develop and validate a simple prediction model for hypoglycemia risk in patients with type 2 diabetes. Materials and Methods We prospectively analyzed the data of 1,303 subjects in a third‐class hospital in Tianjin and followed up their hypoglycemia events at 3 and 6 months. The hypoglycemia risk prediction models for 3 and 6 months were developed and the model performance was evaluated. Results A total of 340 (28.4%) patients experienced hypoglycemia within 3 months and 462 (37.2%) within 6 months during the follow‐up period. Age, central obesity, intensive insulin therapy, frequency of hypoglycemia in the past year, and hypoglycemia prevention education entered both model3month and model6month. The area under the receiver operating characteristic curve of model3month and model6month were 0.711 and 0.723, respectively. The Youden index was 0.315 and 0.361, while the sensitivities were 0.615 and 0.714, and the specificities were 0.717 and 0.631. The calibration curves showed that the models were similar to reality. The decision curves implied that the clinical net benefit of the model was clear. Conclusions The study developed 3 and 6 month hypoglycemia risk prediction models for patients with type 2 diabetes. The discrimination and calibration of the two prediction models were good, and might help to improve clinical decision‐making and guide patients to more reasonable self‐care and hypoglycemia prevention at home.

Keywords

• Diabetes mellitus
• Hypoglycemia
• Prediction model