Artificial Intelligence for Alzheimer's Disease: Promise or Challenge?

Abstract

Decades of experimental and clinical research have contributed to unraveling many mechanisms in the pathogenesis of Alzheimer's disease (AD), but the puzzle is still incomplete. Although we can suppose that there is no complete set of puzzle pieces, the recent growth of open data-sharing initiatives collecting lifestyle, clinical, and biological data from AD patients has provided a potentially unlimited amount of information about the disease, far exceeding the human ability to make sense of it. Moreover, integrating Big Data from multi-omics studies provides the potential to explore the pathophysiological mechanisms of the entire biological continuum of AD. In this context, Artificial Intelligence (AI) offers a wide variety of methods to analyze large and complex data in order to improve knowledge in the AD field. In this review, we focus on recent findings and future challenges for AI in AD research. In particular, we discuss the use of Computer-Aided Diagnosis tools for AD diagnosis and the use of AI to potentially support clinical practices for the prediction of individual risk of AD conversion as well as patient stratification in order to finally develop effective and personalized therapies.

Keywords: Alzheimer’s disease; artificial intelligence; diagnosis; machine learning.

Figure 1

The framework of AI in AD research. Single-modality or integrated data can be processed by several algorithms and tasks, leading to useful outcomes for early and accurate diagnosis, prediction of the course and progression of disease, patient stratification, and discovery of novel therapeutic targets and disease-modifying therapies.

Figure 2

Schematic representation of CAD tools functioning. After collection, data are elaborated, in order to be made ready for the analysis using AI-based techniques. The outcoming result is the assignment of a class, with potential value for diagnostic evaluation.

Figure 3

Predictive ML ensemble method for the conversion of MCI to AD based on multi-modal data (i.e., socio-demographics, clinical, NPS, biological fluids, and imaging data). The system uses a feature transformation and selection phase followed by data integration, allowing for more efficient use of variables. The final ensemble of several different ML models provides accurate final predictions of AD or AD conversion.

Figure 4

Clustering tools determine groups that share similar properties among populations. Each cluster defines a sub-phenotype with its own peculiar characteristics, providing fine-grained information for the stratification of patients; clustering minimizes the intra-cluster distance, while maximizing the inter-cluster distance. Clinician assessment is pivotal in the development of individually-tailored treatments.

Figure 5

The current cross-industry standard process for data mining (CRISP-DM). It illustrates the six phases of a data mining project, which do not follow a strict sequence. The arrows indicate only the most important and frequent relationships between phases; however, each transition depends on the outcome of each phase, defining the task to be performed next.