Background: The possible association between diabetes mellitus and dementia has raised concerns, given the observed coincidental occurrences.
Objective: This study aims to develop a personalized predictive model, utilizing artificial intelligence, to assess the 5-year and 10-year dementia risk among patients with Type 2 Diabetes Mellitus (T2DM) who are prescribed antidiabetic medications.
Methods: This retrospective multicenter study used data from Taipei Medical University Clinical Research Database, which comprises electronic medical records from three hospitals in Taiwan. This study applied eight machine learning algorithms to develop prediction models, including logistic regression (LR), linear discriminant analysis (LDA), gradient boosting machine (GBM), lightGBM (LBGM), AdaBoost, random forest, extreme gradient boosting (XGBoost), and artificial neural network (ANN). These models incorporated a range of variables, encompassing patient characteristics, comorbidities, medication usage, laboratory results, and examination data.
Results: This study involved a cohort of 43,068 patients diagnosed with T2DM, which accounted for a total of 1,937,692 visits. For model development and validation, 1,300,829 visits were utilized, while an additional 636,863 visits were reserved for external testing. The area under the curve (AUC) of the prediction models range from 0.67 for the logistic regression to 0.98 for the artificial neural networks. Based on the external test results, the model built using the ANN algorithm has the best AUC: 0.97 (5-year follow-up period) and 0.98 (10-year follow-up period). Based on the best model (ANN), age, gender, triglyceride, HbA1c, anti-diabetic agents, stroke history, and other long-term medications were the most important predictors.
Conclusions: We have successfully developed a novel computer-aided dementia risk prediction model that can facilitate the clinical diagnosis and management of patients prescribed with antidiabetic medications. However, further investigation is required to assess the model's feasibility and external validity.