Landmark Model-based Individual Dynamic Prediction of Conversion from Mild Cognitive Impairment to Alzheimer's Disease using Cognitive Screening.

Abstract

Background: Identifying individuals with mild cognitive impairment (MCI) who are at increased risk of Alzheimer's Disease (AD) in cognitive screening is important for early diagnosis and prevention of AD.

Objective: This study aimed at proposing a screening strategy based on landmark models to provide dynamic predictive probabilities of MCI-to-AD conversion according to longitudinal neurocognitive tests.

Methods: Participants were 312 individuals who had MCI at baseline. The longitudinal neurocognitive tests were the Mini-Mental State Examination, Alzheimer Disease Assessment Scale-Cognitive 13 items, Rey Auditory Verbal Learning Test immediate, learning, and forgetting, and Functional Assessment Questionnaire. We constructed three types of landmark models and selected the optimal landmark model to dynamically predict 2-year probabilities of conversion. The dataset was randomly divided into training set and validation set at a ratio of 7:3.

Results: The FAQ, RAVLT-immediate, and RAVLT-forgetting were significant longitudinal neurocognitive tests for MCI-to-AD conversion in all three landmark models. We considered Model 3 as the final landmark model (C-index = 0.894, Brier score = 0.040) and selected Model 3c (FAQ and RAVLT-forgetting as neurocognitive tests) as the optimal landmark model (C-index = 0.898, Brier score = 0.027).

Conclusion: Our study shows that the optimal landmark model with a combination FAQ and RAVLTforgetting is feasible to identify the risk of MCI-to-AD conversion, which can be implemented in cognitive screening.