=Paper=
{{Paper
|id=Vol-2042/paper39
|storemode=property
|title=Fuzzy Knowledge Base for Medical Training
|pdfUrl=https://ceur-ws.org/Vol-2042/paper39.pdf
|volume=Vol-2042
|authors=Ray Dueñas Jimínez,Andrí Santanchè,Roger Vieira Horvat,Marcelo Schweller,Tiago de Araujo Guerra Grangeia,Marco Antonio Carvalho-Filho
|dblpUrl=https://dblp.org/rec/conf/swat4ls/JiminezSHSGC17
}}
==Fuzzy Knowledge Base for Medical Training==
https://ceur-ws.org/Vol-2042/paper39.pdf
Fuzzy Knowledge Base for Medical Training
Ray Dueñas Jiménez1 Roger Vieira Horvat2 , Marcelo Schweller2 ,
Tiago de Araujo Guerra Grangeia2 , Marco Antonio de Carvalho Filho2 , and
André Santanchè1
1
Institute of Computing University of Campinas (Unicamp)
{ray.jimenez, santanche}@ic.unicamp.br
2
Emergency Medicine Department, Faculty of Medical Sciences
University of Campinas (Unicamp)
{roger.horvat.48, mschweller, tiagoguerra35, macarvalhofilho}@gmail.com
Abstract. There are several approaches for representing medical knowl-
edge and reasoning, which are able to be interpreted by machines. They
are the basis for applications like expert systems, clinical support sys-
tems, etc. The medical diagnostics context, on one hand, involves loosely
delimited or intuitive characterization of some manifestations, on the
other hand, the occurrence of manifestations and causal effects among
them have grades of uncertainty. A representation approach that em-
braces both aspects is still an open challenge and it is the main problem
addressed in this research. We propose here a model to represent medical
knowledge for diagnosis, combining Fuzzy Logic– to express the loosely
delimited concepts – with probabilistic networks. In this work, we are in-
terested in the application of such knowledge base to support a medical
training system.
Keywords: medical training,fuzzy logic, knowledge base, medical diag-
nosis
Over the last 20 years, several research groups have looked for efficient ways
of representing medical knowledge, as well as technologies and tools to support
decision making and knowledge management. One key aspect is how to map the
medical knowledge – which sometimes involves loosely delimited characteriza-
tions – to a machine interpretable format. Consider the following example of a
diagnostics statement:
Hypotension can be related to arrhythmia in a patient.
The goal of this research is to produce a model interpretable by machines to
represent medical knowledge encompassing three complementary aspects, illus-
trated in Figure 1:
Loose delimited concepts: Decisions of physicians vary according to their
experience, skills, and perception. A decision on the same problem can vary
from one physician to another and, therefore, it is necessary to deal with loose
delimited and sometimes vague concepts, as in the case of hypotension. This
Fig. 1. Aspect of a diagnostic statement.
problem is treated in our model by the fuzzy logic approach, which addresses
also linguistic concepts of medical texts, as well as imprecision in knowledge.
Uncertain Causal Relations:
Our model will be based on two other approaches. The Markov Logic Network
approach [1], which maps first-order logic rules to Markov networks, adding
uncertainty to them . The Prade approach [2] associates probabilities to fuzzy
logic rules.
Network Effect: The CASNET representation for expert systems establishes
relations among observations, pathophysiological states and diseases as a causal
network, which is the basis to support diagnostic decisions. Barabasi et al. [3]
extracted information from large-scale biomedical literature database (PubMed)
to produce a network relating symptoms and diseases.
Combining the Aspects: As far as we know, related work addresses only
part of these three aspects. Therefore, the main contribution of this work is the
propo- sition of an approach that articulates the three mentioned aspects. This
proposal focuses on the study and development of a medical knowledge base.
This project is part of a bigger project and will serve as a basis for the creation
of a game for Medical training. The next step is to create the model based on
clinical data. We will test different ways to infer fuzzy rules for heart disease,
based on works as Anooj, Khatibi [4] and more recent work as Animesh [5].
The present work will support the production of clinical cases. The fuzzy
logic, which uses rules with linguistic terms, facilitates the medical understanding
of the models.
References
1. Domingos, P., Lowd, D.: Markov logic: An interface layer for artificial intelligence.
Synthesis Lectures on Artificial Intelligence and Machine Learning 3(1) (2009) 1–155
2. Prade, H., Richard, G., Serrurier, M.: Learning first order fuzzy logic rules. In:
International Fuzzy Systems Association World Congress, Springer (2003) 702–709
3. Zhou, X., Menche, J., Barabási, A.L., Sharma, A.: Human symptoms–disease net-
work. Nature communications 5 (2014)
4. Khatibi, V., Montazer, G.A.: A fuzzy-evidential hybrid inference engine for coronary
heart disease risk assessment. Expert Systems with Applications 37(12) (2010)
8536–8542
5. Paul, A.K., Shill, P.C., Rabin, M.R.I., Murase, K.: Adaptive weighted fuzzy rule-
based system for the risk level assessment of heart disease. Applied Intelligence
(2017) 1–18