During the last 30 years, Alzheimer's disease (AD) research, aiming to understand the pathophysiology and to improve the diagnosis, management, and, ultimately, treatment of the disease, has grown rapidly. Recently, some studies have used simple bibliometric approaches to investigate research trends and advances in the field. In our study, we map the AD research field by applying entitymetrics, an extended concept of bibliometrics, to capture viewpoints of indexers, authors, or citers. Using the full-text documents with reference section retrieved from PubMed Central, we constructed four types of networks: MeSH-MeSH (MM), MeSH-Citation-MeSH (MCM), Keyphrase-Keyphrase (KK), and Keyphrase-Citation-Keyphrase (KCK) networks. The working hypothesis was that MeSH, keyphrase, and citation relationships reflect the views of indexers, authors, and/or citers, respectively. In comparative network and centrality analysis, we found that those views are different: indexers emphasize amyloid-related entities, including methodological terms, while authors focus on specific biomedical terms, including clinical syndromes. The more dense and complex networks of citing relationships reported in our study, to a certain extent reflect the impact of basic science discoveries in AD. However, none of these could have had clinical relevance for patients without close collaboration between investigators in translational and clinical-related AD research (reflected in indexers and authors' networks). Our approach has relevance for researches in the field, since they can identify relations between different developments which are not otherwise evident. These developments combined with advanced visualization techniques, might aid the discovery of novel interactions between genes and pathways or used as a resource to advance clinical drug development.