=Paper=
{{Paper
|id=Vol-2427/paper13
|storemode=property
|title=Aero: An Evidence-based Semantic Web Knowledge Base of Cancer Behavioral Risk Factors
|pdfUrl=https://ceur-ws.org/Vol-2427/SEPDA_2019_paper_13.pdf
|volume=Vol-2427
|authors=Hansi Zhang,Xing He,Tyler Harrison,Jiang Bian
|dblpUrl=https://dblp.org/rec/conf/semweb/ZhangHHB19
}}
==Aero: An Evidence-based Semantic Web Knowledge Base of Cancer Behavioral Risk Factors==
https://ceur-ws.org/Vol-2427/SEPDA_2019_paper_13.pdf
Aero: An Evidence-based Semantic Web Knowledge Base
of Cancer Behavioral Risk Factors
Hansi Zhang1, Xing He1, Tyler Harrison1, and Jiang Bian1*
1 University of Florida, Gainesville FL 08544, USA
*Corresponding author: bianjiang@ufl.edu
Abstract. The general public’s awareness of cancer behavioral risk factors
(CBRFs) is poor; and even when they are aware, they lack the necessary
knowledge towards a healthy lifestyle. Given that 72% adult internet users in the
United States searched online for health information, the Internet is a great venue
to disseminate CBRF information. However, existing CBRF information online
is poorly organized, not evidenced-based, and confusing to health information
consumers. In this paper, we present a prototype semantic web cAncer bEhav-
ioral Risk knOwledgebase—Aero to (1) better organize and provide evidence-
based CBRF knowledge extracted from scientific literature (i.e., PubMed), and
(2) provide users with access to high-quality scientific knowledge, yet easy to
understand answers for their frequently encountered CBRF questions. Our cur-
rent prototype focuses on the top 4 types of CBRFs: smoking, alcohol drinking,
physical activity, and overweight. We manually annotated 59 high-quality Pub-
Med abstracts (i.e., review articles with impact factor >= 8) and created a prelim-
inary version of Aero with 787 triples. We built an interactive user interface with
graph-based visualization of the KB, where users can explore answers to com-
monly asked CBRF questions according to the cancer risk factor fact sheet of
National Cancer Institute. A preliminary evaluation of Aero was also conducted.
Keywords: Ontology, Semantic Web Knowledge Base, Cancer Behavioral Risk
Factors, Question Answering, Interactive Graph-based Visualization
1 Introduction
Cancer is the second leading cause of death worldwide and responsible for an estimated
9.6 million deaths in 2018 [1]. An immense amount of evidence from research studies
has linked the development of cancer to a wide range of risk factors [2]. Many of these
factors cannot be altered, such as age, sex and family history; while risky health behav-
iors (e.g., smoking and overweight) can be avoided and managed [3]. Recognized by
the integrated behavioral model (IBM) [4], an individual’s health behavior is deter-
mined by her intension, while intention is directly influenced by her knowledge, atti-
tudes, among many other factors. Nevertheless, research has shown that the public’s
awareness of these cancer behavioral risk factors (CBRFs) is poor, and the public lacks
the necessary knowledge towards a healthy lifestyle [5]. Given that 72% adults internet
users in the United States (US) searched online for health information [6], the Internet
is a great communication venue to disseminate CBRF-related health information. How-
ever, existing online information about CBRFs is not well-organized, not evidenced-
based, and of poor quality. Much of this online information consists of personal opin-
ion, salesmanship, testimonials, and claims that are not evidence-based (i.e., supported
by high-quality scientific literature and/or scientific consensus). Even in scientific lit-
erature, evidence describing the relationships between various cancers and CBRFs are
heterogenous ranging from pre-clinical models and case studies to mere hypothesis-
based arguments. In short, current wealth of online health information on CBRFs is
overwhelming and disorganized. We believe that a formal knowledge representation
model (e.g., ontology) along with associated Semantic Web technology stack can help
Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons
License Attribution 4.0 International (CC BY 4.0).
organize and present quality health information to the public.
Previously, Lossio-Ventura et al. created a natural language processing (NLP)-based
system to construct an obesity and cancer knowledge base [7–9]. However, the system
is limited by the performance of the NLP methods and it only focused on one risk factor.
In this paper, we present a prototype semantic web cAncer bEhavioral Risk
knOwledgebase—Aero to (1) better organize evidence-based CBRF-related knowledge
extracted from free-text scientific literature (i.e., PubMed abstract), and (2) provide us-
ers with high-quality, yet easy to understand answers to their commonly asked health
questions relevant to CBRFs. Our preliminary work of Aero consists of 787 triples
extracted from 59 annotated high-quality PubMed abstracts (i.e., impact factor >= 8).
We constructed semantic queries based on commonly asked questions in the National
Cancer Institute (NCI)’s cancer risk factor (CRF) fact sheet [10]; and evaluated Aero
by comparing its query results with the answers from the NCI fact sheet. We have also
built an prototype interactive user interface (UI) for Aero.
2 Methods
Fig. 1 illustrates our process of creating Aero. Rather than using an NLP system, we
manually extracted the triples from PubMed abstracts to ensure the quality of the KB.
Fig. 1. The process of creating Aero.
Step 1: Data collection. The initial Aero KB focused on 4 types of CBRFs: smoking,
alcohol drinking, physical activity, and overweight. For each risk factor, we searched
PubMed using risk factor keywords (e.g., “smoking”, “cigarette”) in combination with
cancer keywords (e.g., “cancer”, “neoplasm”) considering the synonyms for each key-
word. To ensure the quality of evidence, we only considered articles that were pub-
lished in high-quality journals (i.e., impact factors > 8). Two annotators screened each
abstract to filter out articles whose study results are not related to CBRFs. Note that an
article that discussed CBRF (e.g., in the introduction) but does not itself generate results
or evidence indicating the relationships between the CBRF and cancer is excluded.
Step 2: Knowledge extraction. Two annotators reviewed each abstract and extracted
information relevant to either cancer or CBRFs, paying more attention to the direct
relationships between the two. The extracted knowledge is represented as semantic
triples (i.e., “subject-predicate-object”). Our process and annotation guideline are as
follows: (1) for each abstract, identify all terms and sentences that related to cancer and
the CBRF of interest; (2) the terms and sentences must be identified as study results or
conclusion; 3) identify the relations between the extracted terms within the sentence;
and 4) construct individual triples using the extracted terms and relations.
Step 3: Concept and relation standardization. We built a CBRF Ontology (CBRFO)
to provide a controlled vocabulary to standardize the extracted terms (e.g., “alcohol
drinking”, “alcohol intake”) and relations (e.g., “significantly increased risk for”, “as-
sociated with a significantly increased risk of”). Following best practices in ontology
engineering, we first considered reusing concept classes and relations from existing
well-known ontologies if available and created new classes and relations only when it
was necessary. To do so, we first identified high-quality (widely used, regularly main-
tained) candidate ontologies related to the 4 CBRFs of interest and cancer using the
National Center for Biomedical Ontology BioPortal. An ontology is considered as a
candidate if it contains the terms relevant to the 4 CBRFs or cancer. The same concept
(or relation) may exist in multiple ontologies; thus, we used an ontology alignment tool
(i.e., LogMap [11]) to link the same concept across different ontologies. We selected
3 main ontologies: National Cancer Institute Thesaurus (NCIt), Relation Ontology
(RO), and Time Event Ontology (TEO) as the foundation for creating CBRFO.
Step 4: Triple and associated provenance data management. We organized ex-
tracted semantic triples and corresponding provenance data in the form of a nanopubli-
cation [12]. Provenance data of the extracted triples are important and can facilitate
consumers of the KB to form assessments of its quality. A nanopublication has three
basic elements: (1) an assertion; (2) the provenance (e.g., extraction time, annotator);
and (3) associated publication information (e.g., author, title, and published time of the
article where the triple is extracted from). We then used a python library, RDFLib, to
serialize all nanopublications into Resource Description Framework (RDF) using TriG
syntax [13]. We stored all serialized RDF triples in GraphDB—a popular graph data-
base with inference and SPARQL query support.
Step 5: User interface (UI) design. We created a prototype UI with interactive graph-
based visualizations. Previously, we have shown that graph-based visualizations stim-
ulating visual thinking and help end-users better comprehend the presented information
[14, 15]. The UI consists of two main parts: (1) a top bar for users to select a set of pre-
defined question templates (i.e., common questions related to CBRF and cancer, sum-
marized from NCI’s CRF fact sheet), and (2) a canvas for graph-based interactive vis-
ualization of the query results. We have also implemented a number of other conven-
ient functions (e.g., visualization options such as zooming and filtering).
3 Results
3.1 An Aero prototype
We first identified 169 articles published in journals with impact factors equal or greater
than 8. Two annotators reviewed the these articles and retained 59 articles that are
relevant based on the inclusion criteria (i.e., inter-rater agreement: 0.8421). The two
annotators further extracted 126 concept classes, 53 relations, and 787 triple statements
(i.e., inter-rater agreement: 0.7241). Out of the 787 triples, 374 are assertions of
CBRFs, 118 are associated provenance data, and 295 are used to describe the publica-
tion information. Out of the 126 concept classes and 53 relations, we obtained 119
unique classes and 44 unique relations. The selected 3 ontologies (i.e., NCIt, RO, TEO)
for creating the CBRFO cover 88.23% of the 119 concept classes and 27.27% of the 44
relations. New classes and relations were created in CBRFO to provide full coverage.
Then, for each article, we represented the extracted triple statements and associated
provenance data in the form of a nanopublication and imported into GraphDB.
3.2 Question answering with graph-based interactive visualization in Aero
We extracted 53 questions related to the 4 CBRFs from the NCI CRF fact sheet and
summarized them into 3 categories: (1) “What is known about the relationship between
X and cancer?”; (2) “Does X cause cancer and other disease?”; and (3) “What re-
search being done related to X and cancer?”, where the X refers to a specific CBRF
and “cancer” can refer to cancer in general or a specific type of cancer (e.g., lung can-
cer, oral cancer). We then created 3 SPARQL query templates for these 3 categories
of questions. Fig 2 shows an example SPARQL query for the question “What is known
about the relationship between obesity and cancer?”. We simply used the parent class
“cancer” (i.e., ncit:C9305) in the query and the reasoner will automatically consider all
subclasses of cancer associated with obesity (Fig 2).
Fig. 2. An example SPARQL query (left) and the interactive visualization of the query results
(right) for question “What is known about the relationship between obesity and cancer?” *In
SPARQL queries, variables are prefixed with “?”, where “?s” represents a CBRF (i.e., obesity
[ncit:C3283] and childhood obesity [ncit:C84449]), “?o” represents cancer (i.e., NCIt id
ncit:C9305), and “?p” represents the relation.
We manually evaluated the query results of Aero in terms of whether the retrieved tri-
ples accurately (i.e., precision) and comprehensively (recall) cover the answers on the
NCI risk factor fact sheet, focusing on one CBRF (i.e., obesity).
Table 1. Aero query result performance in terms of its ability to answer consumer questions.
Question Precision Recall F-score
Question type 1: “What is known about the re- 1 0.29 0.45
lationship between obesity and cancer?”
Question type 2: “Do smoking cause cancer 0.5 0.43 0.46
and other diseases?”
Question type 3: “What research being done 0.1 0.33 0.15
related to obesity and cancer”
4 Discussion and conclusion
We curated a semantic web KB (i.e., Aero) to better organize high-quality evidence
extracted from scientific literature on the relationships between various behavioral risk
factors and cancer. To build Aero, we created the CBRFO ontology to standardize the
terms and relations used across different articles. Further, we experimented with inter-
active graph-based visualizations to provide consumers with an easy to understand vis-
ual representation of the answers to commonly asked CBRF questions, stimulating their
visual thinking. Given how frequent that the general public searches online for health
information, our ultimate goal for Aero is to provide evidence-based CRBF information
that can lead to behavioral change towards a healthy lifestyle.
Our current study is still limited. Only 59 articles were annotated limiting the coverage
of the KB. Manual annotation is labor-intensive and time-consuming. Thus, we are
actively investigating a crowdsourcing solution that can improve the efficiency of the
KB curation process at scale. Further, the usability of the Aero UI needs to be assessed,
and any usability issues raised should be addressed with inputs from stakeholders es-
pecially the lay consumers following a user-centered design process.
References
1. Word Health Organization. Cancer - key facts. 2018. https://www.who.int/news-
room/fact-sheets/detail/cancer. Accessed 3 Jul 2019.
2. National Cancer Institute. Risk Factors for Cancer. 2015. https://www.can-
cer.gov/about-cancer/causes-prevention/risk. Accessed 20 Jun 2019.
3. Cancer Resaerch UK. The causes of cancer you can control. 2011. https://science-
blog.cancerresearchuk.org/2011/12/07/the-causes-of-cancer-you-can-control/. Ac-
cessed 3 Jul 2019.
4. Glanz K, Rimer BK, Viswanath K, editors. Health behavior and health education:
theory, research, and practice. 4th ed. San Francisco, CA: Jossey-Bass; 2008.
5. Ryan AM, Cushen S, Schellekens H, Bhuachalla EN, Burns L, Kenny U, et al. Poor
Awareness of Risk Factors for Cancer in Irish Adults: Results of a Large Survey and
Review of the Literature. The Oncologist. 2015;20:372–8.
6. Susannah Fox. The social life of health information. 2014. https://www.pewre-
search.org/fact-tank/2014/01/15/the-social-life-of-health-information/. Accessed 25
Apr 2019.
7. Lossio-Ventura JA, Hogan W, Modave F, Hicks A, Hanna J, Guo Y, et al. Towards
an Obesity-Cancer Knowledge Base: Biomedical Entity Identification and Relation De-
tection. Proc IEEE Int Conf Bioinforma Biomed. 2016;2016:1081–8.
8. Lossio-Ventura JA, Hogan W, Modave F, Guo Y, He Z, Hicks A, et al. OC-2-KB:
A software pipeline to build an evidence-based obesity and cancer knowledge base.
Proc IEEE Int Conf Bioinforma Biomed. 2017;2017:1284–7.
9. Lossio-Ventura JA, Hogan W, Modave F, Guo Y, He Z, Yang X, et al. OC-2-KB:
integrating crowdsourcing into an obesity and cancer knowledge base curation system.
BMC Med Inform Decis Mak. 2018;18 Suppl 2:55.
10. National Cancer Institute. NCI Fact Sheets - Risk Factors and Possible Causes.
2019. https://www.cancer.gov/publications/fact-sheets. Accessed 3 Jul 2019.
11. Jiménez-Ruiz E, Cuenca Grau B. LogMap: Logic-Based and Scalable Ontology
Matching. In: Aroyo L, Welty C, Alani H, Taylor J, Bernstein A, Kagal L, et al., editors.
The Semantic Web – ISWC 2011. Berlin, Heidelberg: Springer Berlin Heidelberg;
2011. p. 273–288.
12. Paul Groth, Erik Schultes, Mark Thompson, Zuotian Tatum, Tobias Kuhn, Christine
Chichester. Nanopublication Guidelines. 2018. http://nanopub.org/guidelines/work-
ing_draft/. Accessed 3 Jul 2019.
13. Chris Bizer, Richard Cyganiak. RDF 1.1 TriG. 2014. https://www.w3.org/TR/trig/.
Accessed 3 Jul 2019.
14. Bian J, Xie M, Hudson TJ, Eswaran H, Brochhausen M, Hanna J, et al. Collabora-
tionViz: interactive visual exploration of biomedical research collaboration networks.
PloS One. 2014;9:e111928.
15. He X, Zhang R, Rizvi R, Vasilakes J, Yang X, Guo Y, et al. Prototyping an Inter-
active Visualization of Dietary Supplement Knowledge Graph. In: 2018 IEEE Interna-
tional Conference on Bioinformatics and Biomedicine (BIBM). Madrid, Spain: IEEE;
2018. p. 1649–52. doi:10.1109/BIBM.2018.8621340.