Alzheimer’s disease (AD) is a neurodegenerative disorder that causes dementia, where in its early stage people cannot remember recent events, and gradually have more difficulty managing daily life tasks or even recognizing family and friends. AD is to date incurable (Alzheimer’s Association, 2015), although a great deal of resources are used to treat symptoms. The large number of sufferers from mild to severe cases creates a high social impact and tremendous costs for medical care that serves to manage symptoms instead of offering a cure. It is estimated that 4.7 million Americans have dementia, and the total number in 2050 is projected to be 13.8 million (Hebert et al., 2013). The economic costs of dementia were estimated to be $818 billion in 2015 (Prince et al., 2015). Due to its incurability, the costs for several sectors in the society, such as long-term care, home services, and non-professional caregivers, are greater than the cost of direct medical care (Bullock, 2004; Winblad et al., 2016; Yokoyama et al., 2016). Due to the severity and increasing number of people suffering from dementia, it is very important to promote further research on AD.

The current information available on the disease, however, is actually overwhelming. For example, simply searching “Alzheimer” in PubMed brings up 90,000+ articles⁽¹⁾（⁽¹⁾ https://www.ncbi.nlm.nih.gov/pubmed/?term=alzheimer）. Because no single researcher can read even a fraction of these papers, using computational techniques could be a partial solution. Toward this end, this paper presents a case study that uses machine reading to help gather data from the large amount of literature.

The machine reading technique of data mining is based on the idea that machines can integrate and summarize information for humans by reading and understanding large amounts of texts (Hirschberg & Manning, 2015). Previous work related to machine reading and AD used computational techniques such as topic modeling to read and take main points from a large number of papers, but its general purpose is to get overview information (Hughes et al., 2014; Lee et al., 2015; Song, Heo, & Lee, 2015; Sorensen, 2009; Sorensen, Seary, & Riopelle, 2010). Indeed, in order to understand the domain of AD, we first need an overview that will help to identify key details, such as what kind of major topics are in the literature. This will help determine what kind of specific information is needed. For instance, unless we are aware of a group or individuals that discuss AIDS within AD papers, we cannot understand how AIDS is related to AD (addressed in Section 4.2). This study first uses a topic modeling technique (Blei, Ng, & Jordan, 2003) to obtain major topics within AD literature.

Once the overview is obtained, specific questions are addressed with a focus on how AD is connected to AIDS/HIV. Answering these questions requires techniques to read the content of related papers, recognize key entities mentioned in the text, and identify the relations among these entities. Gathering entities and relations from texts is called information extraction (IE), which conventionally assumes pre-defined target information. For example, extracting gene-disease interactions information is a common IE task, but it requires that the target genes, diseases, and types of expected interactions among them are already identified. Yet it is not advisable to limit the types of information being sought in advance, as this weeds out potentially significant topics or details that can be helpful to the search. Moreover, even after the information being sought is fixed, it can change frequently depending on how we have understood the literature at that point, or due to shifts in perspectives on the topic. For example, we might be interested in which pathway contains a particular gene after a gene-disease extractor found that the gene is associated with AD. In this case, we need to build the pathway-gene extractor again if conventional IE techniques are employed. Therefore, an IE technique is used that does not require pre-defined targets, called open information extraction (Open IE) (Fader, Soderland, & Etzioni, 2011).

Open IE is an information extraction technique applied in natural language processing (Fader, Zettlemoyer, & Etzioni, 2014; Mausam, 2016) that gathers facts in the form of triples <subject, predicate, object>. For example, given the sentence, “Alzheimer is strongly correlated with the apoe genotype,” it extracts <Alzheimer, is strongly correlated with, the apoe genotype>. These extracted facts are used to answer specific questions based on Latent Dirichlet Allocation (LDA) results (Blei et al., 2003). Note that it is always possible to trace the data back to specific sentences mentioning the answer. This provides an advantage because the information can be confirmed from reliable sources, that is, specific sentences in scientific papers.

The combination of the two methods of topic modeling and Open IE is complementary, in that Open IE answers key questions provided by topic modeling overviews. Topic modeling, specifically LDA, has been applied to a wide range of fields to reveal hidden topics from textual data (DiMaggio, Nag, & Blei, 2013; Hall, Jurafsky, & Manning, 2008; Hu et al., 2015). It is often difficult to make sense of each topic, however, even with substantial domain knowledge. This is because LDA just outputs topics as a distribution over terms, and does not provide information on how terms in the topic are linked together. On the contrary, Open IE can indicate how terms are specifically linked in texts. It is developed as a natural language processing (NLP) technique, and is applied to NLP tasks such as question answering. Yet when trying to understand a large collection of texts, searchers do not always have specific questions to ask in advance. An overview is therefore needed to identify specific questions. Combining LDA and Open IE is complimentary, as LDA provides the overview, which is helpful to infer specific questions that are answered by Open IE.

The rest of this paper is organized as follows. Section 2 briefly summarizes the key related work. Section 3 describes the proposed machine reading approach using the two distinct methods of LDA and Open IE to better comprehend large collections of literature both at the overview and specific levels. Section 4 presents the results of this approach for the medical domain of Alzheimer’s disease, whose related papers are far beyond what a single researcher can read. Due to the high social and fiscal impact of the disease, the need for further research is urgent. Finally, Section 5 concludes the paper.

Computational techniques have been extensively used to understand a scientific domain, and applications for the topic of AD has also gathered a great deal of attention (Hughes et al., 2014; Lee et al., 2015; Song, Heo, & Lee, 2015; Sorensen, 2009; Sorensen et al., 2010). Sorensen (2009), for instance, investigated the productivity and impact of the top 100 AD researchers using citation analysis, and identified the role of AD within the field of neurodegenerative diseases. In defining an AD-specific h-index ranking to obtain an overview of the whole domain, Sorensen et al. (2010) focused on co-authorship networks and revealed major author communities. Chen et al. (2014) studied cholinesterase inhibitors within AD research, and analyzed research trends. Hughes et al. (2014) explored collaboration networks using papers from the Alzheimer Disease Center to reveal the impact of this organization. Lee et al. (2015) analyzed networks of medical entities to provide an overview of AD research, but did not investigate specific relations between entities. Song et al. (2015) studied AD literature both at the topic and entity levels; To our knowledge, this research is the only one that considers relations between entities, yet they only used 54 pre-defined relations defined in the Unified Medical Language System⁽²⁾（⁽²⁾ https://www.nlm.nih.gov/research/umls/）. Overall, the related studies introduced so far mainly address overview information of the field of AD, while this paper has another purpose of obtaining specific information without specifying specific information searches in advance.

Obtaining specific information from texts has been well studied as information extraction in natural language processing. Information extraction (IE) is a task that automatically extracts structured information from texts. For example, many IE systems can extract entities such as genes, diseases, drugs, and relations between them from the medical literature (e.g. Song et al., 2015). However, because pre-defined relations are required, they are not effective when no relations are extracted in advance. Open IE systems (Mausam, 2016) overcome this issue and use raw textual phrases as relations, which has been applied to several NLP tasks such as question answering (Fader et al., 2014). To the best of our knowledge, this paper is the first to use Open IE to understand large amounts of literature in a specific medical domain in combination with topic modeling methods.

The methodology of this paper is visually summarized in Figure 1. First, we collected literature with a focus that can be specified by key terms, specific periods, and/or target journals. After consulting domain experts, we collected a set of PubMed papers relevant to AD⁽³⁾（⁽³⁾ The query was performed in October, 2015.） using search terms Alzheimer, Mild cognitive impairment, Dementia, Significant memory concern, and Subjective memory complaint without any constraint of publication year. The earliest paper obtained was published in 1945. The data set collected includes 160,091 papers with MeSH terms, which are the index terms given to the PubMed articles and abstracts. Second, we applied LDA to keywords. Two types of keywords were employed: MeSH terms and genes mentioned in the abstracts. These genes were extracted from a dictionary-based extractor using LingPipe⁽⁴⁾（⁽⁴⁾http://alias-i.com/lingpipe/index.html） with the NCBI human gene list⁽⁴⁾（⁽⁴⁾ https://www.ncbi.nlm.nih.gov/gene）. In addition, we applied LDA to subsets of the papers with a narrower focus by year range, hoping to obtain more interesting observations than by looking at all papers. Specifically, we made two subsets of papers published in the last decade (2005-2014) and the previous decade (1995-2004). Having referred to some previous papers such as those of Zhang et al. (2017), we set the number of topics as five when using LDA because the purpose is to get a macro-level overview. Next, we applied Open IE, specifically Reverb (Fader et al., 2011), to textual content (e.g. abstracts or full text) of the papers. Each extracted triple is linked to a specific sentence in a paper. We then examined the topic modeling results and obtained some questions based on the results. Finally, we answered these questions using extracted triples. This part can be iterative because an answer to a question could raise new questions.

This paper provides a case study of using the machine reading method to understand the domain of Alzheimer’s disease (AD), and its relation to other diseases such as HIV and AIDS. AD is a field whose number of the related papers is overwhelmingly high, although there is a vital need for further research that may actually help find the causes of the disease as well as a cure. We demonstrate that machine reading helps identify specific information that offers a better understanding via overviews provided by topic modeling. The use of both methods of LDA and Open IE in a mutually complementary way reveals how the topic modeling technique connects AD and HIV/AIDS. Based on this observation, when querying the Open IE extractions, the two diseases are found to have different mechanisms but share some symptoms such as dementia.

This study has several implications. First of all, it shows that the literature on a topic can answer specific questions relating to it, which has not been attempted in the literature to date. From the perspective of Alzheimer’s disease, the approach provided in this article could help domain experts find important relations between entities in a similar manner as this study identified relations between AD and HIV/AIDS. Methodologically, this approach can serve as a preliminary knowledge extraction step for literature-based knowledge discovery if future researchers hope to construct a curated knowledge base for a specific purpose.

One limitation of this approach is that we need to manually clean the data, such as remove false extractions. Moreover, this study is not able to answer abstract questions when these answers are not written explicitly in texts. In the future, it would be helpful to develop a method to automate the process to detect false extractions. We could also integrate existing medical knowledge bases to answer more complex or nuanced questions.