=Paper=
{{Paper
|id=Vol-3603/workshopOIIDDS2
|storemode=property
|title=Integrating Declarative and Procedural Knowledge in Infectious Disease Scenario for
Epidemiological Monitoring
|pdfUrl=https://ceur-ws.org/Vol-3603/workshopOIIDDS2.pdf
|volume=Vol-3603
|authors=Evellin Cardoso
|dblpUrl=https://dblp.org/rec/conf/icbo/Cardoso23
}}
==Integrating Declarative and Procedural Knowledge in Infectious Disease Scenario for
Epidemiological Monitoring ==
https://ceur-ws.org/Vol-3603/workshopOIIDDS2.pdf
Integrating Declarative and Procedural Knowledge in
Infectious Disease Scenario for Epidemiological
Monitoring⋆
Evellin Cardoso1
1
Federal University of Goias, Goias, Brazil
Abstract
Although promising, the synergies between declarative and procedural knowledge have been little
explored in Medicine [1]. To tackle this problem, this paper proposes an approach that combines
declarative and procedural knowledge. The approach uses ontologies as a knowledge artifact that
expresses medical declarative knowledge. This ontology is used as a starting point for an approach that
derives a BPMN procedural specification from the knowledge expressed in the ontology. The approach
is illustrated in a infectious disease scenario, in particular, it uses the Basic Formal Ontology (BFO) [2]
and the Infectious Disease Ontology (IDO) [3].
Keywords
Medical Knowledge, Knowledge Representation, Ontologies, Basic Formal Ontology (BFO), Business
Process Management (BPM)
1. Introduction
Expert systems have been used in Medicine successfully since 1990s [4, 5]. An important aspect
of the design of such systems regards the acquisition and representation of medical knowledge,
a problem that has been addressed by different communities in Computer Science. In medical
informatics, a lot of research has been conducted in the development of formalisms to capture
medical knowledge. Since late 1990s, many Knowledge Representation (KR) formalisms have
been developed, including ontologies, semantic web related formalisms and logics [6]. The focus
of medical informatics community is on the representation of (medical) declarative knowledge
that capture general, background medical knowledge, such as diseases, drugs and treatments [1].
Another strain of research in medical informatics considers the formalization of narrative
clinical guidelines into computer interpretable clinical guidelines (CIG) using formalisms such as
document models, decision trees, probabilistic models, task-network models [7]. Many domain-
specific languages to model CIGs have been proposed, such as Asbru, PROforma, GLIF, EON
and GUIDE [8]. More recently, boostered by business demands, Business Process Management
(BPM) techniques have been applied to healthcare organizations, in an attempt to streamline
Proceedings of the International Conference on Biomedical Ontologies 2023, August 28th-September 1st, 2023, Brasilia,
Brazil
*
Corresponding author.
$ evellin@ufg.br,evellinc@gmail.com (E. Cardoso)
0000-0001-6242-662X (E. Cardoso)
© 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
193
medical operations, thus achieving business goals of improving efficiency and reducing costs.
Medical processes have been captured as business processes using process languages such as
BPMN and DECLARE. Business processes and CIGs capture (medical) procedural knowledge
that consists of sequences of actions that must be followed by healthcare providers in certain
circumstances [1].
Although promising, the synergies between declarative and procedural knowledge have been
little explored in both medical informatics and BPM communities [1]. To tackle this problem,
this paper proposes an approach that combines declarative and procedural knowledge. The
approach uses ontologies as a knowledge artifact that expresses medical declarative knowledge.
This ontology is used as a starting point for an approach that derives a BPMN procedural
specification from the knowledge expressed in the ontology. The approach is illustrated in a
infectious disease scenario, in particular, it uses the Basic Formal Ontology (BFO) [2] and the
Infectious Disease Ontology (IDO) [3].
The rest of the paper is structured as follows: Section 2 briefly introduces the BFO and
IDO ontologies and procedural models in the medical sector, briefly introducing BPMN syntax.
Section 3 presents the approach for deriving a BPMN procedural model starting from the
ontologies, illustrating it in the scenario of infectious diseases. Section 5 concludes the paper
and outlines future work.
2. Preliminaries
2.1. Ontologies
Ontologies are a knowledge representation formalism that represent (or strive to represent)
reality in such way a group of stakeholders understand the terms that compose a certain domain
of discourse, and can thus learn about such domain [2]. They may be classified as top-level
ontologies (or formal) that contain highly general categories and relations of reality common to
all domains, defining concepts such as "process", "material object", etc., or domain ontologies that
capture a basic set of universal concepts pertinent to a specific scientific domain (e.g., geography,
medicine or law).
In this paper, (medical) declarative knowledge is represented as ontologies. The Basic Foun-
dational Ontology (BFO) [2] is the top-level ontology chose due to its wide accceptance as an
international standard ISO/IEC 21838–2, while the Infectious Disease Ontology (IDO) [3] is
the chosen domain ontology. IDO extends the Ontology for General Medical Science (OGMS),
which in its turn extends BFO.
2.2. Procedural Models in Healthcare
The BPM discipline is concerned with the formalization and analysis of the activities conducted
by an enterprise to produce goods and services to its customers [9]. In healthare organizations,
medical processes can be divided as administrative processes (concerned with administrative
practices like handling of medical order and lab procedures) or knowlege-intensive processes
which are concerned with the intensive usage of domain specific knowledge in diagnose and
treament processes.
194
Figure 1: A BPMN specification of knowledge-intensive process in healthcare
Both types of processes can be typically captured by a procedural process language, such as
the Business Process Modeling Notation (BPMN). Fig. 1 depicts a knowledge-intensive business
process in healthcare. Rounded rectangles denote activities (e.g., verify the existence of infectious
process), while circles represent events (patient’s temperature > 38 degrees). Diamonds represent
decisions (presence or absence of infectious process?), while arrows denote diferent results of
decisions.
3. The Approach
This section depicts the approach of building process models based on the knowledge extracted
from ontologies. As ontologies are commonly structured into foundational ontologies ℱ and
domain ontology 𝒟, our approach starts from a set of ontologies 𝒪 = ⟨ℱ, 𝒟⟩, where ℱ is the set
of foundational ontologies and 𝒟 the set of domain ontologies. The approach is composed by
the following steps:
Step 1. The knowledge engineer starts by investigating the concepts of 𝒪 for a preliminary
understanding of the domain.
Step 2. As the size of ontologies may be significant, the knowledge engineer selects the subset
𝒟′ from 𝒟 that is relevant for her modeling purposes. 𝒟′ may be sub-ontologies or even portions
of 𝒟.
Step 3. The knowledge engineer explores the semantics of each particular concept to grasp
about the domain.
Step 4. The knowledge engineer builds the procedural representation. To perform such step,
s/he considers the following sub-steps (not necessarily in this order):
• One must take into account that activities are performed to react to events happening in
the world. The hint is to look for the relevant events {𝑒1 , 𝑒2 , ..., 𝑒𝑛 } taking place within
the domain
• To express such events in the procedural specification, consider that the occurrence of
events is captured by changes in the states of entities of the domain (concepts of the
ontology). By searching for the concepts in the ontology and which changes in the state
of these concepts are relevant, one can express the relevant events.
195
• Order the relevant events. Include the events and the activity that has to be performed to
address the event (change), including them all the procedural specification.
Step 5. As procedural and declarative knowledge present a complementary view of reality, it is
possible that all knowledge required to build the procedural specification is not found in the
declarative specification (and vice-versa). In this case, the knowledge engineer will have to
complement the procedural specification with the help of domain experts.
Next section illustrates our approach in a infectious disease scenario.
4. Applying the Approach in an Infection Disease Scenario
This section illustrates the approach from Sec. 3 applied in a infectious disease scenario [3]. The
infectious disease scenario represents the domain of infectious diseases. It includes different
biological scales (gene, cell, organ, organism and population), complementary disciplinary
perspectives (biological, clinical, epidemiological), and successive phases of an infectious process
(host, reservoir, vector, pathogen). With the recent breakthrough of Covid-19, the availabillity
of such ontology is important to integrate heteregenous data sources. Such integration will
enable the establishment public policies to contain the disease by public health organizations
using statistical data.
Step 1. Starting the approach, the set of ontogies 𝒪 related to the IDO have been investigated
for a basic understanding of the infectious disease domain. Three ontologies (BFO, OGMS and
IDO) have been identified. In this way we have 𝒪 = ⟨ℬℱ 𝒪, 𝒟⟩, where 𝒟 = ⟨ℐ𝒟𝒪, 𝒪𝒢ℳ𝒮⟩.
Step 2. Multiple possibilities for selecting parts 𝒟′ of 𝒟 exist, given that IDO captures many
distinct dimensions (biological scales, disciplinary perspectives and different phases). The
disciplinary perspective of epidemiology has been chosen.
Step 3. The semantics of each particular concept relative to epidemiology has been investigated
at Table 5 and section "Epidemiology and surveillance" from [3].
Step 4. Fig. 2 depicts the BPMN specification built in our approach (the three traces inside
the first activity denotes that the activity is performed multiple times, in this case, for each
geographic region).
This specification has been built by analyzing the semantics of three IDO concepts (infectious
disease incidence, infectious disease pandemic and infectious disease epidemic) that are highlighted
in boldface in BPMN. On top of identifying the concepts, we have identified the relevant events.
After understanding the semantics of the three concepts, following with the identification
of the events, if the incidence of an infectious disease in a population (in a certain geographic
region) is above a certain threshold1 (infection disease incidence > threshold1), this may indicate
the existence of an epidemics in that region. With that, the public administrator has to check the
existence of epidemics in other regions as well. If other regions have not surpass the acceptable
threshold1 of infectious disease, then the number of regions with infectious disease is below
threshold2 (#regions < threshold2), no signal of epidemics is found and the surveillance process
finishes.
On the contrary, if a number of regions that population has infectious disease surpass a
certain threshold (#regions > threshold2), this indicates a pandemics. In this case, the public
administrator proceeds with the monitoring and two situations may happen. One is when
196
Figure 2: Procedural Specification (BPMN) built from an infectious disease ontology [3]
we continuosly have a pandemics (#regions > threshold3). The second one happens when the
number of regions drop and we no longer have a pandemics, but we may still have an epidemics
(#regions < threshold3).
Step 5. Notice that the ontology captures only knowledge about the domain, but not the
real-time data relative to the incidence of infectious diseases in population or the thresholds for
epidemics and pandemics. In this case, public admnistrators have to provide such numbers.
5. Conclusion
This paper proposed a preliminary approach to derive a BPMN procedural specification from
the knowledge expressed in an ontology. The approach is illustrated in an infectious disease
scenario, using BFO (top-level ontology) and IDO (domain specific ontology). As the integration
between declarative and procedural knowledge is generally challenging in many domains (not
only Medicine), I hope that this preliminary approach provides an initial insight on how to
solve this problem.
In particular, an advantage of this approach in the infectious disease scenario is the possibility
of integrating data to the overall approach presented in this paper. Two types of data may
be integrated, together with two distinct monitoring perspectives. One perspective considers
the usage of the values of incidence of infectious diseases in population and the thresholds
for epidemics and pandemics. With these values, it is possible to use epidemic simulators in
public health monitoring [10]. The second monitoring approach considers the usage of process
mining [9] to monitor the BPMN procedural process, and thus, to monitor in which stage of the
process we are (if we have a epidemics, pandemics or no abnormal public health event).
As future work, I consider this integration with data, together with the usage of more concepts
from the ontology to derive more information for the procedural specification. Further, I also
want to explore the synergy between declarative and procedural knowledge in the other way
round, such as, can we derive the ontology from a procedural specification?
197
References
[1] S. Bragaglia, F. Chesani, P. Mello, M. Montali, Conformance Verification of Clinical Guide-
lines in Presence of Computerized and Human-Enhanced Processes, Springer International
Publishing, 2015, pp. 81–106.
[2] R. Arp, B. Smith, A. D. Spear, Building Ontologies with Basic Formal Ontology, The MIT
Press, 2015.
[3] S. Babcock, J. Beverley, L. Cowell, B. Smith, The infectious disease ontology in the age of
covid-19, 2021. doi:10.31219/osf.io/az6u5.
[4] P. Windyga, D. Almeida, G. Passariello, F. Mora, J. Coatrieux, Knowledge-based approach
to the management of serious arrhythmia in the ccu, Medical and Biological Engineering
and Computing 29 (1991) 254–60. doi:10.1007/BF02446707.
[5] A. Batarekh, A. D. Preece, A. Bennett, P. Grogono, Specifying an expert system, Ex-
pert Systems with Applications 2 (1991) 285–303. doi:https://doi.org/10.1016/
0957-4174(91)90036-E.
[6] D. Riaño, M. Peleg, A. ten Teije, Ten Years of Knowledge Representation for Health Care
(2009–2018): Topics, Trends, and Challenges, Artificial Intelligence in Medicine 100 (2019).
[7] M. Peleg, Computer-Interpretable Clinical Guidelines: A Methodological Review, Journal
of Biomedical Informatics 46 (2013) 744–763.
[8] D. Isern, A. Moreno, Computer-Based Execution of Clinical Guidelines: A Review, Inter-
national Journal of Medical Informatics 77 (2008) 787–808.
[9] W. M. P. van der Aalst, Business Process Management: A Comprehensive Survey, ISRN
Software Engineering 2013 (2013).
[10] W. Hogan, M. Wagner, M. Brochhausen, J. Levander, S. Brown, N. Millett, J. DePasse,
J. Hanna, The apollo structured vocabulary: an owl2 ontology of phenomena in infectious
disease epidemiology and population biology for use in epidemic simulation, Journal of
Biomedical Semantics 7 (2016) 50. doi:10.1186/s13326-016-0092-y.
198