Using data science to diagnose and characterize heterogeneity of Alzheimer's disease

Abstract

Introduction: Despite the availability of age- and education-adjusted standardized scores for most neuropsychological tests, there is a lack of objective rules in how to interpret multiple concurrent neuropsychological test scores that characterize the heterogeneity of Alzheimer's disease.

Methods: Using neuropsychological test scores of 2091 participants from the Framingham Heart Study, we devised an automated algorithm that follows general diagnostic criteria and explores the heterogeneity of Alzheimer's disease.

Results: We developed a series of stepwise diagnosis rules that evaluate information from multiple neuropsychological tests to produce an intuitive and objective Alzheimer's disease dementia diagnosis with more than 80% accuracy.

Discussion: A data-driven stepwise diagnosis system is useful for diagnosis of Alzheimer's disease from neuropsychological tests. It demonstrated better performance than the traditional dichotomization of individuals' performance into satisfactory and unsatisfactory outcomes, making it more reflective of dementia as a spectrum disorder. This algorithm can be applied to both within clinic and outside-of-clinic settings.

Keywords: Alzheimer's disease; Decision tree; Dementia; Dementia screening; Machine-learning; Neuropsychological assessment.

Fig. 1

Clinical cognitive screen decision tree based on all NP tests in total population. Each rectangle represents a branch node, which is a decision step where participants are divided into different subgroups based on the designated NP test score. Each pie chart represents a terminal node and is divided into color-coded slices to illustrate the probability of the three cognitive outcomes (AD, NAD, and HC). The outcome with the highest probability is indicated alongside each pie chart. Abbreviations: AD, Alzheimer's disease; BNT30, Boston Naming Test (30-item Even Version); HC, healthy control; NP, neuropsychological; LMd, Logical Memory (Delayed Recall); LMi, Logical Memory (Immediate Recall); NAD, non-Alzheimer's dementia; PASd_h, Hard score of Paired Associate Learning (Delayed Recall); PASi, Paired Associate Learning (Immediate Recall); PASi_h, Hard Score of Paired Associate Learning (Immediate Recall); SD, standard deviation; SIM, Similarities Test; VRd, Visual Reproductions (Delayed Recall); VRi, Visual Reproductions (Immediate Recall).

Fig. 2

Clinical cognitive screen decision tree based on optimal NP profiles (five tests) in total population. Abbreviations: AD, Alzheimer's disease; BNT30, Boston Naming Test (30-item Even Version); HC, healthy control; NP, neuropsychological; LMd, Logical Memory (Delayed Recall); LMi, Logical Memory (Immediate Recall); NAD, non-Alzheimer's dementia; PASd_h, Hard score of Paired Associate Learning (Delayed Recall); PASi, Paired Associate Learning (Immediate Recall); PASi_h, Hard Score of Paired Associate Learning (Immediate Recall); SD, standard deviation; SIM, Similarities Test; VRd, Visual Reproductions (Delayed Recall); VRi, Visual Reproductions (Immediate Recall).