Fuzzy cognitive maps: a tool to improve diagnostic decisions

Abstract

Anticipating that the problem of diagnostic errors will not easily be solved through education, debiasing techniques or incentives-based systems, experts have proposed the systematic use of decision support tools (or decision aids) in medical practice. These tools are active knowledge resources that use patient data to generate case-specific advice to support clinical decision making. We argue that designing these decision support tools incorporates both discrete, analytical information as well as intuitive elements that would optimize their impact on clinical everyday activities. The use of fuzzy cognitive maps should allow developers to achieve this aim, by incorporating published evidence, intuition and qualitative assessment in a low-cost software program that could be implemented in various clinical settings.

Full text

Diagnosis 2014; aop
©2014, Claudio Lucchiari et al., published by De Gruyter.
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.
Opinion Paper Open Access
Claudio Lucchiari * , Raffaella Folgieri and Gabriella Pravettoni
Fuzzy cognitive maps: a tool to improve
diagnostic decisions
Abstract: Anticipating that the problem of diagnostic
errors will not easily be solved through education, debias-
ing techniques or incentives-based systems, experts have
proposed the systematic use of decision support tools (or
decision aids) in medical practice. These tools are active
knowledge resources that use patient data to generate
case-specific advice to support clinical decision making.
We argue that designing these decision support tools
incorporates both discrete, analytical information as well
as intuitive elements that would optimize their impact
on clinical everyday activities. The use of fuzzy cognitive
maps should allow developers to achieve this aim, by
incorporating published evidence, intuition and qualita-
tive assessment in a low-cost software program that could
be implemented in various clinical settings.
Keywords: decision support systems; diagnostic errors;
dual process theory; fuzzy cognitive maps.
DOI 10.1515/dx-2014-0026
Received May 6 , 2014 ; accepted July 8 , 2014
Problems in diagnostic decision
The diagnostic process is one of the main focuses of
medical decision making. Indeed, establishing a diagno-
sis is a complex task: A physician is expected to act as an
information processor, able to both collect information
and process it efficiently to produce hypothesis about the
clinical case and further examinations needed to evaluate
them. We could describe the diagnostic process using a
simple scheme (see Figure 1 ).
Substantial research has been devoted to this impor-
tant topic, but relatively little is known about the exact
mechanisms of the diagnostic process, both when it suc-
ceeds or fails. Indeed, diagnostic errors account for a sub-
stantial number of all medical errors and even though it
has recently received increasing attention [2, 3] it remains
an important patient safety concern [4, 5] .
Given the complexity of the diagnostic process,
experts have proposed that the systematic use of decision
support tools (or decision aids) in everyday clinical prac-
tice could improve diagnostic reliability and reduce the
likelihood of error.
A decision support system (DSS) is an active knowl-
edge resource that uses patient data to generate case-spe-
cific advice, which supports decision making by health
professionals, the patients themselves or others con-
cerned about them [6] .
A cognitive balanced model (CBM)
Several authors have described how experts typically
employ subconscious, intuitive, synthetic thinking
(System 1, S1) [7, 8] . In contrast, others have argued
that physicians should adopt exclusively analytical
approaches to problem-solving, which would be less
prone to intuitive bias and emotional contamination. In
this case, a good doctor would be a pure rational decision
maker, able to follow precisely step-by-step algorithms.
If errors should arise in this setting, it would indicate the
intrusion of heuristics and/or wrong procedures due to a
poor professional training, or to contingencies, such as
a negative mood, excessive stress, or distractions like a
noisy environment. Most DSSs are based on the idea that
physicians need help in enhancing their analytical think-
ing, encouraging users to abandon intuition in favor of
procedural reasoning. Unfortunately, this conceptual
architecture limits the actual use of DSSs, because most
*Corresponding author: Claudio Lucchiari, PhD, Via Festa del
Perdono 7, 20122 Milan, Italy, Phone: + 39 0250321288,
E-mail: claudio.lucchiari@unimi.it
Claudio Lucchiari and Gabriella Pravettoni: Health Sciences
Department, Universit à degli Studi di Milano, Milan, Italy ; and
Applied Research Unit for Cognitive and Psychological Science,
European Institute of Oncology (IEO), Milan, Italy
Raffaella Folgieri: Department of Economics, Management and
Quantitative Methods, Universit à degli studi di Milano, Milan, Italy
Unauthenticated | 10.248.254.158
Download Date | 8/18/14 7:49 AM

2Lucchiari etal.: FCM in diagnostic decisions
physicians, especially expert and skilled ones often rely
on, intuitive thinking, their “ clinical-eye ” .
However, others have pointed out the valuable role
of intuition in making good medical decisions [9, 10] . For
instance, Gabbay and Le May [11] , described how expert
physicians develop strategies based on the use of subtle
clues to quickly infer important judgments without a
complete information base. They called these strategies
“ mindlines ” as opposed to guidelines.
In previous works [12, 13] , we have defined a cognitive
balanced model (CBM) to describe how clinical decisions
should emerge from a functional balance between analy-
sis and intuition, guidelines and mindlines. The CBM
underlines the need for a doctor to develop both intuitive
and analytical skills, and the potential benefit of using a
decision support system that enables physicians to find
the balance needed case by case, adapting the thinking
style to fit the actual demands of the problem. Medical
practitioners must learn to trust their intuition, but also
know how to prevent heuristic-related fatal biases.
Fuzzy cognitive maps
The need to accommodate this dynamic balance and the
natural presence of uncertainty in most clinical settings
requires a decision support resource capable of handling
this complexity, such as one based on fuzzy cognitive
maps (FCM) [14] .
To build a FCM, doctors are not required to quantify the
importance of contributing information, they only need an
intuitive comprehension of a clinical scenario, and the rel-
evant factors that need to be considered. As shown in differ-
ent experimental studies, FCM can improve the diagnostic
process by incorporating a cognitive balanced decision [15,
16] . The great advantage of this approach is that it provides
the possibility to incorporate heuristics and intuitive knowl-
edge in a defined conceptual scheme [17] . This includes
both analytical (S2) and synthetic components (S1), often
described as divergent concepts in a decision process but
perfectly integrated in the FCM balanced model.
A formal model for clinical settings
As described before, a FCM is a graph modeling a dynamic,
complex system, consisting of nodes (C
i ) and interconnec-
tion (e
ij ) between concepts, expressing cause and effect
relations between them.
The general formula expressing the value of each
concept C
i is the following, in which the value of each
concept C
i is calculated computing the influence of other
concepts to the specific one, through the calculation rule
given by the equation:
()
=
≠
=−
∑1
() ( 1)
j
ji
n
ijji
xt f xt w
(1)
where x i ( t ) is the value of the concept C
i at time t; x j ( t – 1)
represents the value of the concept C
j at time t – 1; w ji is the
Data flow
Mental model activation
& update
Analytical thoughtSynthetic thought
Hypothesis generation
Test
Diagnosis-+
Procedures activation
Knowledge updating and sharing
Consultants
Figure 1  Mental model is the physician ’ s cognitive structure that incorporates and gives sense to the data flow coming from the environ-
ment (patients ’ symptoms, clinical tests and the like).
From this mental structure both analytical and synthetic thinking may be activated in order to generate and evaluate hypotheses. We use
the term synthetic thinking to indicate all those processes that do not require conscious data decomposition and representation. This kind
of thinking is generally defined as intuitive or heuristic [1] .
Unauthenticated | 10.248.254.158
Download Date | 8/18/14 7:49 AM

Lucchiari etal.: FCM in diagnostic decisions3
weight of the interconnection between C
j and C
i ; f repre-
sents the sigmoid function
λ−
=+
1
1x
f
e
The weights w ji characterize the interconnections.
They describe the degree of causality between two con-
cepts and can assume values in the interval [ – 1, 1]. The
sign of a weight respectively indicates positive causality
that is an increase in the value of the concept Ci will cause
an increase in the value of the concept Cj, or negative cau-
sality. In this latter case the increase of the value of the
concept Ci will cause the decrease in the value of Cj or the
decrease of Ci will cause the increase of Cj. If the weight
is equal to zero, there is no relationship between the
two concepts. In summary, the strength of the weight w
ji
reflects the degree of influence between concept C
i and C
j .
To model the mutual and reciprocal influence of S1
and S2 (intuitive and analytical thinking), these relation-
ships are described by the equations 1 and 2 (1) introduc-
ing a modification of the weight w
ji as follows. A panel of
experts is asked to consider all of the individual concepts,
attributes, interconnections and relative weights, repre-
senting the graphical display of a given clinical scenario
(a connected graph). The experts are then asked to express
two parameters: one formulated on the basis of their
experiences and intuitions (S1), the other deriving from
objective data and evidence-based analysis (S2). The new
weights w ′ ji in the formulas (1) and (2) will be so obtained
by the sum of the weights indicated by the experts, namely
S1 and S2, corresponding to the two thinking systems:
S1 S2
ji
w=+
′
The formulas will be:
()
=
≠
=−
′
∑1
() ( 1)
j
ji
n
ijji
xt f xt w
(1b)
=
≠
⎡⎤
=−+−
′
⎢⎥
⎣⎦
∑1
12
() ( 1) ( 1)
j
ji
n
ijjii
xt fk xt w kxt
(2b)
where w ′ ji = S1 + S2
We chose the sum because it is the simplest calcula-
tion and it preserves the meaning of the weights in the for-
mulas, both in the regard to direction (positive or negative
influence) and magnitude.
The different FCM resulting from the work of the
panel of experts will be evaluated by an automatic system
comparing the results with the expected ones. We are not
able to predict a priori which of the two formulations will
optimally converge, so we argue that both the presented
FCM mathematical formulations need to be tested.
An example
To illustrate how our model works, we propose here a sim-
plified, though realistic, model of a differential diagnosis
between psychogenic non-epileptic (PNES) and epileptic
seizures (ES) [18] . The differentiation of the two patho-
logical conditions is often not trivial, since the symptoma-
tology of both ES and PNES is particularly variable, the
behavioral features of PNES can simulate epileptic ones,
and both types of seizures may occur in the same patients.
The complexity of this problem fits our aim, because FCMs
are particularly useful in ambiguous contexts and when
incomplete or not completely reliable information must be
used. Figure 2 presents a simplified model of the problem:
Clouds indicate decision-concepts, that is the two diagno-
ses we are considering; ellipses describe the most impor-
tant factors (factor-concepts) involved in distinguishing
the two possibilities, the input of our FCM.
The following characteristics should be considered to
differentiate ES and PNES in ambiguous cases: Anamnes-
tic information (history of neurological and psychiatric
disorders, in particular the presence of significant psy-
chological trauma), clinical data (the presence of brain
pathology, a mood disorder, a neurological condition,
EEG abnormalities, and hormonal indices, e.g., post-ictal
serum level of prolactin), behavioral features (response
to antiepileptic drugs and/or placebo, provocation of sei-
zures, typicality of symptoms), psychological/psychiatric
aspects (assessment of personality) and demographic
data (e.g., PNES is more common in women). All this
information should be integrated to suggest a final con-
clusion [18, 19] because any single information source,
might, almost equally, suggest either ES and PNES. Fur-
thermore, some of these data are difficult to collect, being
not always available or reliable.
Following the simpler FCM model proposed by Geor-
gopoulos and Stylios [20] we could use the clinical data
alone to obtain a fuzzy-based decision aid. However, we
argue that the utility of the FCM would be strengthened
by incorporating both analytical and intuitive input. To
illustrate this process, we asked an expert neurologist to
consider the differentiation of ES from PNES based on his
expertise. The analytical and the intuitive differentiation
model obtained are the results of two different informa-
tion sources. The former is evidence-based and it should
be assembled by an independent expert (or panel of
Unauthenticated | 10.248.254.158
Download Date | 8/18/14 7:49 AM

4Lucchiari etal.: FCM in diagnostic decisions
experts) asked to consider only dedicated literature. This
generally (but not always) implies the construction of a
complex model where many factors and interactions are
considered. In cases where the evidence is strong and
clearly stated, this model should be the optimal one. The
second differentiation model is instead expertise-based,
and is generally simpler, since the actual experience of the
doctor guides the weighting process. Those factors previ-
ously found to efficiently discern ES and PNES in concrete
occurrences, despite strong scientific evidence, should
be, for example, overweighted.
Finally, we carried out a balanced weighting proce-
dure of each attribute, based both on literature data (S2)
and the doctor ’ s expertise (S1; see Table 1
). The values can
be summed to incorporate the final weight of a simple
syntax, we then summed the two values obtaining the
final weight of each attribute in the FCM software. In this
way, the ultimate output reflects both analytical and syn-
thetic considerations.
This Table is used to populate the FCM model, deter-
mining the relative importance of each of the m factor-
concepts with respect to the n possible (2 in our example)
decision-concepts. These fuzzy weights will be trans-
lated into numerical weights by the algorithm used. For
instance, very high corresponds to 90% of relevance
of a given factor and the weight assigned will be 0.9.
Cerebral pathology Atypical symptoms
Psychiatric
assessment
Hormonal markers
Continuous long
EEG indices
Interictal EEG
evidence
Gender
History of
neurological
disease
Mood disturbance
History of
psychological
trauma
PNES
ES
Figure 2  A simplified model of the ES/PNES differentiation problem.
Dashed lines indicate weak or uncertain connections. Clouds represent decision-concepts, and ellipses represent factor-concepts. Factor-
factor connections may be either positive (synergic) or negative (competitive).
Table 1  Weights attributed by the use of analytical and synthetic
thinking to decision attributes of the FCM.
Attributes Synthetic
weight (S)
Analytical
weight (S)
PNES ES PNES ES
Presence of cerebral pathology Low MediumMediumHigh
Gender (women) Low Low MediumLow
Interictal EEG alteration Medium High High
Long-term EEG monitoring Low High High
Hormonal indices Low High High
History of psychological traumaHigh Medium High 
Psychiatric assessment High MediumHigh Low
History of neurological
diseases
MediumHigh Low High
Mood disturbance High MediumHigh Low
Bizarreness of symptoms High Medium High Low
To sum related weights we used the following simple rules (S1 + S2):
0 + any Value = 0; Low + Low = Low; Low + Medium = Medium;
High + Low = High; Very high + Low = Medium; Medium + Medium =
Medium; Medium + High = High; Medium + Very High = High; High
+ High = High; Very High + Very High = Very High. In this case, we
decided to give equal weights to S1 and S2, but in a given situation
different weights should be assigned. Actually, these assignments
should be regarded as arbitrary and could be modified to fit specific
clinical contexts and/or to the confidence a doctor has with exper-
tise-based or evidence-based models. This means that clinicians
deciding to use this decision support tool could adapt it to his/her
decision style by appropriate adjustments to the weighting rules.
Unauthenticated | 10.248.254.158
Download Date | 8/18/14 7:49 AM

Lucchiari etal.: FCM in diagnostic decisions5
Consequently the FCM algorithm will work on two matri-
ces, W and X. Matrix W contains all the connection
weights, and may include negative values if competitive
connections between factors are present, while X contains
the values assigned in a specific case. To place values in
X, the decision maker will assign values to each attribute
present in the FCM-model, using the same fuzzy degrees
(0, low, medium, high or very high). Naturally, only data
actually available will be placed in X, while the input-fac-
tor not available will correspond to nodes not activated (0
values). For instance, in a specific case, a doctor could use
the FCM decision aid using only EEG signal abnormalities,
the history of neurological disorders and the presence of
mood disturbance, assigning respectively High, Medium
and Low as fuzzy degrees and 0 to all other model factors
(in this case the model would suggest a diagnosis of ES).
Conclusions
We argue that fuzzy cognitive maps, already recognized
and tested in the domain of medical diagnosis, have
received inadequate attention by researchers and doctors.
It is likely that in the near future more FCM-based deci-
sion aids will become available both during medical train-
ing and in everyday clinical practice, providing a better
balance of analytical and synthetic mental processes with
beneficial effects on decision making and patients ’ out-
comes. The FCM approach provides a method to handle
uncertainty in clinical decision-making when uncertainty
is expected to be high. The fuzziness of the maps allows
one to visualize the hazy degrees of causality between
concepts, and their graphic structure allows easy visuali-
zation of the relationship between concepts.
Furthermore, we argue that training doctors to
balance intuitive and analytical thinking will enable them
to increase their cognitive awareness about how they
reason, decide and solve problems and sensitize them the
consequences of medical decisions, both and negative. In
this way, doctors will strengthen their ability to learn from
practice, developing a easily adaptable expertise, par-
ticularly useful in situations of high complexity or rapid
evolving evidence.
Acknowledgments: We thank the reviewers for their help-
ful suggestions and for the time and effort provided to
review and improve our original manuscript.
Author contributions: All the authors have accepted
responsibility for the entire content of this submitted
manuscript and approved submission.
Research funding: None declared.
Employment or leadership: None declared.
Honorarium: None declared.
Competing interests: The funding organization(s) played
no role in the study design; in the collection, analysis, and
interpretation of data; in the writing of the report; or in the
decision to submit the report for publication.
References
1. Croskerry P. Clinical cognition and diagnostic error: applications
of a dual process model of reasoning. Adv Health Sci Educ
2009;14.1:27 – 35.
2. Elstein AS. Thinking about diagnostic thinking, a 30-year
perspective. Adv Health Sci Educ Theory Pract 2009;1:7 – 18.
3. Newman-Toker DE, Pronovost PJ. Diagnostic errors – the next
frontier for patient safety. J Am Med Assoc 2009;301:1060 – 2.
4. Wachter RM. Why diagnostic errors don ’ t get any respect – and
what can be done about them. Health Aff 2010;29:1605 – 10.
5. Graber ML, Wachter RM, Cassel CK. Bringing diagnosis into the
quality and safety equation. J Am Med Assoc 2012;308:1211 – 2.
6. Wears RL, Berg M. Computer technology and clinical work. J Am
Med Assoc 2005;293:1261 – 3.
7. Stanovich K. Who Is Rational, Studies of Individual Differences in
Reasoning. Mahwah, NJ: Lawrence Erlbaum Associates, 1999.
8. Normann G. Dual processing and diagnostic errors. Adv Health
Sci Edu 2009;14:37 – 49.
9. Gigerenzer G, Gaissmaier W. Heuristic decision making. Ann Rev
psychol 2011;62:451 – 82.
10. Croskerry P. From mindless to mindful practice-cognitive bias
and clinical decision making. N Engl J Med 2013;368:2445 – 8.
11. Gabbay J, Le May A. Practice-based evidence for healthcare:
Clinical mindlines. London, New York: Routledge, 2010.
12. Lucchiari C, Pravettoni G. Cognitive balanced model: a concep-
tual scheme of diagnostic decision making. J Eval Clin Pract
2012;18:82 – 8.
13. Lucchiari C, Pravettoni G. The role of patient involvement in the
diagnostic process in internal medicine: a cognitive approach.
Eur J Intern Med 2013;24:411 – 5.
14. Iakovidis DK, Papageorgiou E. Intuitionistic fuzzy cognitive
maps for medical decision making. Inform Tech Biomed, IEEE
Trans 2011;15:100 – 7.
15. Kok K. The potential of Fuzzy Cognitive Maps for semi-quantita-
tive scenario development, with an example from Brazil. Glob
Env Change 2009;19:122 – 33.
16. Papageorgiou EI, Spyridonos PP, Glotsos DT, Stylios CD, Rava-
zoula P, Nikiforidis GN, etal. Brain tumor characterization using
the soft computing technique of fuzzy cognitive maps. App Soft
Comp J 2008;8:820 – 8.
17. Kosko B. Cognitive Fuzzy Maps. Int J Man-Machines Stud
1986;24:65 – 75.
18. Kuyk J, Leijten F, Meinardi H, Spinhoven, Van Dyck R. The diag-
nosis of psychogenic non-epileptic seizures: a review. Seizure
1997;6:243 – 53.
19. Reuber M, Elger CE. Psychogenic nonepileptic seizures: review
and update. Epilepsy Behavior, 2003;4:205 – 16.
20. Georgopoulos V, Stylios C. Complementary case-based reason-
ing and competitive fuzzy cognitive maps for advanced medical
decisions. Soft Comp 2008;12:191 – 9.
Unauthenticated | 10.248.254.158
Download Date | 8/18/14 7:49 AM