Prediction of transition from mild cognitive impairment to Alzheimer's disease based on a logistic regression–artificial neural network–decision tree model

Aim To develop a logistic regression model, artificial neural network (ANN) model and decision tree (DT) model for the progression of mild cognitive impairment (MCI) to Alzheimer's disease (AD) to compare the performance of the three models. Methods A total of 425 patients with MCI were screened from the original cohort. The actual follow up included 361 patients, with AD as the outcome variable. Three kinds of prediction models were developed: a logistic regression model, ANN model and DT model. The performance of all three models was measured with accuracy, sensitivity, positive predictive value and area under the receiver operating characteristic curve. Results A total of 121 patients with MCI developed AD, and the average conversion rate was 9.49% per year. The ANN model had higher accuracy (89.52 ± 0.36%), area under the receiver operating characteristic curve (92.08 ± 0.12), sensitivity (82.11 ± 0.42%) and positive predictive value (75.26 ± 0.86%) than the other two models. The first five important predictors of the ANN model were, in order, ADL score, age, urine AD‐associated neuronal thread protein, alcohol consumption and smoking. For the DT model, they were age, activities of daily living score, family history of dementia, urine AD‐associated neuronal thread protein and alcohol consumption. For the logistic regression model, they were age, sex, activities of daily living score, alcohol consumption and smoking. Conclusion The logistic regression, ANN and DT models performed well at predicting the transition from MCI to AD with ideal stability. However, the ANN model had the best predictive value. Increased age, activities of daily living score, urine AD‐associated neuronal thread protein, alcohol consumption, smoking and sex were important factors. Geriatr Gerontol Int 2021; 21: 43–47 .