=Paper=
{{Paper
|id=Vol-2798/paper2.pdf
|storemode=property
|title=Employing Hybrid Reasoning to Support Clinical Decision-Making/span
|pdfUrl=https://ceur-ws.org/Vol-2798/paper2.pdf
|volume=Vol-2798
|authors=Sabbir M. Rashid
|dblpUrl=https://dblp.org/rec/conf/semweb/Rashid20
}}
==Employing Hybrid Reasoning to Support Clinical Decision-Making/span==
https://ceur-ws.org/Vol-2798/paper2.pdf
Employing Hybrid Reasoning to Support
Clinical Decision-Making
Sabbir M. Rashid1[0000−0002−4162−8334]
Rensselaer Polytechnic Institute, Troy, NY, 12180, USA
Abstract. Clinical reasoning, involving abstraction, abduction, deduc-
tion, and induction, is the primary tool that physicians use when making
clinical decisions. To support them, we focus on the creation of an AI
system that is able to emulate clinical reasoning. We leverage Semantic
Web technologies to perform a set of AI tasks involving the various forms
of inference associated with clinical reasoning strategies. In particular,
for the scope of this work, we focus on clinical problems that require dif-
ferential diagnosis techniques. For a given clinical scenario, overlapping
reasoning types and strategies may be employed by a physician in con-
junction, signifying the need for our AI system to perform hybrid reason-
ing. Therefore, we consider the construction of a hybrid reasoner that is
compatible with description logics. For medical scenarios where descrip-
tion logics may not have some needed expressivity, we consider possible
extensions that will allow for the representation of such a scenario. The
reasoning system, clinical rule representation, and the resulting recom-
mendations will be evaluated based on domain expert consultation in
order to determine whether the recommendation aligns with what the
expert would recommend.
Keywords: Hybrid Reasoning · Deduction · Abduction · Temporal Rea-
soning · Knowledge Representation · Diabetes · Ontology · Explainable
AI · Inference · Disease · Informatics · Differential Diagnosis · Clinical
Reasoning Strategies · Rule Representation
1 Problem statement
This thesis focuses on the design and implementation of a clinical decision sup-
port system that is able to perform hybrid reasoning by emulating how physi-
cians reason. Clinical reasoning is employed in many medical tasks, such as those
involving information comprehension, decision-making, and medical error iden-
tification. Approaches for clinical reasoning use four distinct types of inference:
abstraction, abduction, deduction, and induction [1, 15]. We base our approach
on the Select and Test Model (ST-Model), an epistemological framework for
medical reasoning in which an expert chooses a plausible hypothesis which is
subsequently confirmed or falsified through testing [19]. The cyclic nature of the
ST-Model demonstrates how the different types of reasoning can be applied in
conjunction during a clinical reasoning framework. Given a set of initial patient
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License
Attribution 4.0 International (CC BY 4.0).
2 Sabbir M. Rashid
data/information, abstraction is applied to identify problem features, which can
be used, through abduction, to determine a set of plausible hypotheses. Alter-
natively, inductive techniques can be applied to arrive at hypotheses directly
from the data. In applying this model for clinical reasoning, we deviate from the
traditional ST-Model and instead of including the induction step, we use the
observed data to validate diagnostic hypotheses. The resulting hypotheses are
then ranked in terms of likelihood as well as clinical relevance, and are used for
the deductive inference of expected outcomes or consequences. In order to sup-
port clinical decision-making, we note that three reasoning strategies commonly
employed by physicians include differential diagnosis, treatment planning, and
plan critiquing. In this paper, we focus primarily on differential diagnosis.
To illustrate the applicability of this revised ST-Model framework using a
simple example, consider a scenario where a patient gained a significant amount
of weight over a short period of time. The observed data that the patient gained
30 pounds over 2 months is abstracted to be a clinical problem. Abduction is
used to determine four likely hypotheses for the patient unintentionally gaining
weight, such as 1) a decrease in the amount of activity, 2) a change in the
patient’s diet, 3) a medicinal effect, or 4) a biological effect.1 These hypotheses
can be ranked in terms of importance, where medicinal or biological effects are
more clinically relevant than a decrease in activity or a change of diet. Existing
data in the system can be used to rule out or validate the hypotheses. For
example, if Internet of Things (IoT) data pertaining to step counts shows that
the patient’s amount of activity has not decreased, hypothesis 1 can be ruled out.
Hypothesis 3 regarding medicinal effects could be broken into sub-hypotheses,
such as due side-effects of a single medicine or contraindications between multiple
medications. This would cause the system to check for symptoms of the drugs
that the patient is prescribed. The biological effect of hypothesis 4 could be
a decrease in the patient’s metabolism, which in turn may be explained by a
disease like hypothyroidism, and would require more data for validation. Under
the open-world assumption, this hypothesis would not be ruled out, and instead
the system would recommend a test to gather more data, such as a TSH (thyroid-
stimulating hormone) test to check for thyroxine (a thyroid hormone) levels.
In order to implement the ST-Model framework into an Artificial Intelligence
(AI) system, our approach involves semantically annotating and transforming
patient data into Resource Description Framework (RDF), individually encoding
each reasoning technique as an agent that detects changes and reasons over
content in the knowledge graph, and validating ranked hypotheses through test
cases and expert consultation.
2 Importance
This work is geared towards aiding physicians during the clinical decision-making
process by creating an AI system that can reason in a way similar to how a physi-
cian reasons. Earlier work on medical expert systems use approaches involving
1
https://www.webmd.com/diet/ss/slideshow-weight-gain-shockers
Employing Hybrid Reasoning to Support Clinical Decision-Making 3
decision tree rules or the construction of knowledge bases by leveraging machine
learning techniques. Our approach differs from that earlier work in that we are
building an AI system using semantic web technologies in a manner that con-
forms with Description Logics (in particular, with OWL-DL). This allows us to
both leverage recent ontologies created in knowledge representation for health
care efforts and existing inference engines that reason over OWL-DL ontologies.
Furthermore, we note that by limiting expressivity, we can perform tractable rea-
soning over OWL-DL ontologies. Therefore, a challenge worth exploring involves
the representation of medical knowledge such that polynomial time reasoning can
be achieved while preserving important domain and patient details.
Furthermore, since part of this work involves the implementation of an abduc-
tive reasoning component, we are advancing semantic web techniques to allow
for non-monotonic reasoning (where conclusions can be validated or rejected as
more data is observed). As Chitsaz defines in her thesis [2], abductive reasoning
is “the process of inferring the best explanation from given observations [in ac-
cordance with] background knowledge.” In the example related to patient weight
gain presented in Section 1, abductive reasoning is used to generate several hy-
potheses. Non-monotonic reasoning allows for each of these hypotheses to exist
in a state in which they are not yet confirmed to be true or false, allowing for
acceptance or rejection once more data is leveraged for validation. This process,
which is necessary for emulating the way a physician reasons, can be recorded
through the use of provenance capturing. By creating a framework that is able
to perform abduction in this way, we promote traceability in reasoning and move
towards the goal of explainable AI systems.
3 Related Work
As early as the 1950s, Artificial Intelligence (AI) techniques were beginning to
be applied to model clinical reasoning and medical decision-making [8]. By the
end of the decade, work on the reasoning foundations for medical diagnosis, in
which Bayes’ formula was adapted to find conditional probabilities of a disease
given a set of symptoms [9], lead to the application of probabilistic approaches
for modeling clinical reasoning over the next decade. In addition to probabilistic
approaches for diagnostics, research around this time also focused on medical lit-
erature retrieval and indexing, such as MEDLARS (Medical Literature Analysis
and Retrieval System [21]).
By the 1970s, theoretical research on medical reasoning was beginning to be
applied towards the creation of medical expert systems. Approaches related to
the Newell-Simon methodology on how humans solve problems in different situa-
tions [12] were applied in the creation of expert systems [7]. Also around this time
period (1970s-80s) SUMEX-AIM (Stanford University Medical Experimental –
AI in Medicine [6]) arose, a computational infrastructure shared by multiple in-
stitutions. This lead to discussions and workshops related to biomedical problem
solving and clinical decision-making [8].
4 Sabbir M. Rashid
While work on expert systems continued into the 80s, the importance of having
these systems be explainable and justified became more apparent. Explainable
expert systems, developed in collaboration between knowledge engineers and
domain experts, represented a shift from procedural encoding to declarative
knowledge representation [20]. Relevant literature from this time period also
includes work on medical reasoning, including the ideas that physicians develop
hypotheses early in the diagnostic process [4] and experts differ from novices
in approaches involving hypothetico-deductive reasoning [16]. These differences
derive both from the features of a knowledge base [5] and highly automated
perceptual processes [10] that experts have in contrast with novices.
An approach that builds on this work uses propositional analysis to build rules
from knowledge that abstracts medical problem solving into steps involving data
gathering, diagnosis, therapeutic planning, and patient management [16]. An-
other important idea from this work is that medical reasoning often involves both
forward and backward reasoning. This direction of research continued through-
out the 90s to show that propositional and semantic analyses can improve the
validity, usability, and comprehension of Clinical Practice Guidelines (CPGs),
mental models could be used as a cognitive framework for how people reason,
and reasoning approaches were often data and hypothesis driven [14].
4 Research questions
In conducting this work, we focus on several research questions. We begin by
determining the following: Which forms of reasoning should be incorporated into
a clinical decision support system in order to emulate how a physician reasons?
When consulting related literature in order to determine the forms of reasoning
that should be incorporated into a clinical decision support system, we find that
mentions of abstraction, deduction, induction, abduction, temporal reasoning,
and causal reasoning [1, 19, 15]. Since our approach for replicating physician
reasoning is based on the ST-Model [19], we focus on the abstraction process to
formulate observed data into a representative problem space. For observations
occurring over a period of time, we leverage existing approaches for temporal
reasoning [13, 18]. Through abduction, we determine potential hypotheses that
can be used to explain the clinical problem at hand. We incorporate probabilistic
reasoning techniques when ranking abductive hypotheses in order to first address
more clinically relevant hypotheses. From each hypothesis, we deductively de-
termine a set of predictions corresponding to expected patient data. While using
existing semantic technology for deduction, we do consider the writing of custom
inference rules when necessary. While we do not focus on induction, we attempt
to validate abductive hypotheses by comparing the expected and observed data.
The next research question we consider relates to design requirements: What
are the necessary implementation considerations for building a hybrid reasoner
that conforms with OWL Description Logics (OWL-DL)? Specifically, we con-
sider satisfiability, consistency, and explainability. In terms of satisfiability, we
search for contradictions with respect to the ontologies that are used and between
Employing Hybrid Reasoning to Support Clinical Decision-Making 5
facts that are asserted to be true. To check for consistency, we determine if the
facts in the knowledge base are satisfiable. Inconsistencies within the knowledge
base result in instances of the owl:Nothing class. If the reasoner does not return
such instances, we conclude that the knowledge base is consistent. Finally, we
require an explanation for facts derived from inference processes. In order to
guarantee that our hybrid reasoner conforms with DL, initially the implementa-
tion is limited to Semantic Web compliant technologies. We consider the extent
to which the expressivity of the ontologies that we use can be limited in order
to allow for tractible reasoning while still allowing the necessary medical knowl-
edge to be accurately represented. As additional functionalities are incorporated,
such as non-monotonic abductive reasoning, tests will be written to ensure that
the systems is constrained to the bounds of DL. Boundary limit testing will be
conducted to determine which scenarios break this constraint.
For our considered usage scenarios, we ask the following: How can verbal state-
ments made by physicians (captured in written transcripts) be represented as rea-
soning rules? As mentioned earlier, our approach is based on the ST-model. In
terms of representing verbal statements, we consider representational simplifica-
tion by abstracting out mentions of conditions, treatments, diseases/diagnoses,
risks/symptoms, and goals. In doing so, we must ensure that the resulting rule
is both semantically consistent and representative of the original recommen-
dation or statement. For example, in the use case of Section 1, the symptom
of weight gain may point to a diagnosis for hypothyroidism under the condi-
tion that thyroxine levels are low. A diagnosis of hypothyroidism may result in
treatment in the form of a levothyroxine prescription (commonly used to treat
hypothyroidism) in order obtain the goal of decreasing the patient’s weight.
5 Preliminary results
In order to apply our approach on patient data, we represent the data as RDF in
a semantic structure consistent with the execution of the reasoning rules derived
from physician transcripts. The Semantic Data Dictionary (SDD) approach [17]
has been applied for annotating and converting patient data to RDF from several
publicly available biomedical datasets. Additionally, we have received permission
to annotate data from two private datasets, StepUp and Limited Claims EHR
Dataset (LCED). StepUp contains data about its user’s physical activities, in-
cluding step count, so it can be used to test for hypothesis 1 of the use case of
Section 1. LCED contains administrative claims information as well as Electronic
Health Record (EHR) data, including information about patient demographics,
habits, and prescriptions [3]. Therefore, it can be used for patient characteristic
representation for testing using real patient data.
In terms of implementation, a customizable deductive reasoner has been in-
corporated into the Whyis [11] knowledge management framework. Preliminary
work on traceability within this framework has commenced and is being lever-
aged to aid in the abductive reasoning component. Initial work related to clinical
decision support and rule representation includes the categorization of reasoning
6 Sabbir M. Rashid
types and strategies from physicians transcripts, as well as discussions on how
to adapt the ST-Model for use within the framework of this thesis.
6 Evaluation
In this section, we begin by discussing some of the evaluation that has been
conducted for the aforementioned methodology. We continue by discussing addi-
tional evaluation of our clinical decision-making system that we plan to conduct.
The SDD approach, which is leveraged to semantically convert tabular data
into RDF, has been evaluated against traditional data dictionaries, data in-
tegration approaches, and mapping languages [17]. Reasoning component im-
plementations have been validated using unit tests to check for the expected
functionality. As further components are incorporated, additional tests will be
written accordingly, including tests of efficiency when reasoning over large data.
In addition to testing the functionality of the implementation, we will use
background biomedical knowledge to evaluate clinical reasoning processes. By
providing a clinical expert with sets of test patient data and asking them to walk
through their diagnostic process, we will evaluate the set of hypotheses that the
system generates through comparison with the physician’s hypotheses, which we
will measure through the use of confidence scores. While the determination of
the full evaluation pipeline is still work in progress, in addition to measuring hy-
pothesis confidence, we plan to conduct a comparative evaluation against other
hybrid reasoning systems. Additionally, for each individual reasoning compo-
nent, we will evaluate capabilities against other special purpose reasoners that
are able to do the associated reasoning task. The complete set of metrics for such
an evaluation is yet to be determined. Abductive explanations will be ranked
in terms of likelihood using appropriate heuristic metrics. One such metric cor-
responds to whether the hypotheses are accurately ranked in terms of clinical
importance (such as medicinal implications being more relevant than a change
in the patient’s diet). The accuracy of these rankings will be evaluated based
on importance assigned by a domain expert who is provided the same set of hy-
potheses. Initially, the clinical expert we will consult is a member of the author’s
thesis committee who holds both Ph.D. and M.D. degrees in relevant areas.
7 Reflections
We have discussed the creation of a decision support system that is similar to
some of the expert systems that we encountered during the literature review.
While these systems used various AI techniques, they were not implemented us-
ing semantic web technologies. Our approach differs from earlier methods as we
are creating a system that conforms with OWL-DL. We are able to integrate
various forms of inference by leveraging existing efficient reasoners (for example,
for performing deduction or temporal reasoning) that also conform with OWL-
DL semantics. Additionally, semantic knowledge resources, such as biomedical
ontologies and patient data, can be incorporated into our knowledge base that
can be used during the decision-making processes. The use of semantic technolo-
gies allows us to capture provenance, detect inconsistencies, integrate multiple
knowledge resources, and leveraging existing tools for performing deductive and
temporal reasoning. Our application can help address specific challenges by aid-
ing physicians with clinical problems involving reasoning strategies.
Future work includes the incorporation of other reasoning strategies, such as
therapy planning and plan critiquing. Extensions in this direction include lever-
aging CPGs to represent existing therapy plan recommendations and test physi-
cian conformance to CPGs. Additionally, medical information from biomedical
resources that provide recommendations based on scientific evidence, as well as
clinical opinions on whether or not to follow guideline recommendation, can be
used to model plan critiquing. We mention in Section 4 that the incorporation of
inductive reasoning is beyond the scope of this thesis, as the implementation of
an abductive component will be sufficiently challenging in itself. Future exten-
sions may include leveraging existing machine learning techniques to incorporate
induction capabilities into our framework.
Acknowledgements
I am advised by Professor Deborah L. McGuinness, Constellation Chair at Teth-
erless World Constellation (TWC), RPI. I am thankful for the members of TWC
who have helped me edit this paper. This work is done as part of the Health
Empowerment by Analytics, Learning, and Semantics (HEALS) project and is
supported by IBM Research AI through the AI Horizons Network.
Bibliography
[1] Arocha, J.F., Wang, D., Patel, V.L.: Identifying reasoning strategies in med-
ical decision making: a methodological guide. Journal of biomedical infor-
matics 38(2), 154–171 (2005)
[2] Chitsaz, M.: Approaches to Abductive and Inductive Reasoning in
Lightweight Ontologies. Ph.D. thesis, Griffith University (2015)
[3] Choudhury, O., Gkoulalas-Divanis, A., Salonidis, T., Sylla, I., Park, Y., Hsu,
G., Das, A.: Differential privacy-enabled federated learning for sensitive
health data. arXiv preprint arXiv:1910.02578 (2019)
[4] Elstein, A.S., Shulman, L.S., Sprafka, S.A.: Medical problem solving an
analysis of clinical reasoning (1978)
[5] Feltovich, P.J.: Knowledge based components of expertise in medical diag-
nosis. Tech. rep., PITTSBURGH UNIV PA LEARNING RESEARCH AND
DEVELOPMENT CENTER (1981)
[6] Freiherr, G.: The seeds of artificial intelligence: SUMEX-AIM. No. 80, US
Department of Health, Education, and Welfare, Public Health Service . . .
(1980)
8 Sabbir M. Rashid
[7] Hayes-Roth, F., Waterman, D.A., Lenat, D.B.: Building expert system
(1983)
[8] Kulikowski, C.A.: Beginnings of artificial intelligence in medicine (aim):
Computational artifice assisting scientific inquiry and clinical art–with re-
flections on present aim challenges. Yearbook of medical informatics 28(01),
249–256 (2019)
[9] Ledley, R.S., Lusted, L.B.: Reasoning foundations of medical diagnosis. Sci-
ence 130(3366), 9–21 (1959)
[10] Lesgold, A.M., Feltovich, P.J., Glaser, R., Wang, Y.: The acquisition of
perceptual diagnostic skill in radiology. Tech. rep., PITTSBURGH UNIV
PA LEARNING RESEARCH AND DEVELOPMENT CENTER (1981)
[11] McCusker, J., Rashid, S.M., Agu, N., Bennett, K.P., McGuinness, D.L.: The
whyis knowledge graph framework in action. In: International Semantic Web
Conference (P&D/Industry/BlueSky) (2018)
[12] Newell, A., Simon, H.A., et al.: Human problem solving, vol. 104. Prentice-
Hall Englewood Cliffs, NJ (1972)
[13] O’Connor, M.J., Das, A.K.: A method for representing and querying tem-
poral information in owl. In: International joint conference on biomedical
engineering systems and technologies. pp. 97–110. Springer (2010)
[14] Patel, V.L., Arocha, J.F., Diermeier, M., Greenes, R.A., Shortliffe, E.H.:
Methods of cognitive analysis to support the design and evaluation of
biomedical systems: the case of clinical practice guidelines. Journal of
biomedical informatics 34(1), 52–66 (2001)
[15] Patel, V.L., Arocha, J.F., Zhang, J.: Medical reasoning and thinking. The
Oxford handbook of thinking and reasoning pp. 736–754 (2012)
[16] Patel, V.L., Groen, G.J.: Knowledge based solution strategies in medical
reasoning. Cognitive science 10(1), 91–116 (1986)
[17] Rashid, S.M., McCusker, J.P., Pinheiro, P., Bax, M.P., Santos, H.O., Stin-
gone, J.A., Das, A.K., McGuinness, D.L.: The semantic data dictionary – an
approach for describing and annotating data. Data Intelligence pp. 443–486
(2020)
[18] Rospocher, M., van Erp, M., Vossen, P., Fokkens, A., Ald-
abe, I., Rigau, G., Soroa, A., Ploeger, T., Bogaard, T.: Build-
ing event-centric knowledge graphs from news. Web Seman-
tics: Science, Services and Agents on the World Wide Web
(2016). https://doi.org/10.1016/j.websem.2015.12.004, http://www.
sciencedirect.com/science/article/pii/S1570826815001456
[19] Stefanelli, M., Lanzola, G., Ramoni, M.: Knowledge acquisition based on
an epistemological model of medical reasoning. In: 1992 14th Annual In-
ternational Conference of the IEEE Engineering in Medicine and Biology
Society. vol. 3, pp. 880–882. IEEE (1992)
[20] Swartout, W.R.: Xplain: A system for creating and explaining expert con-
sulting programs. Artificial intelligence 21(3), 285–325 (1983)
[21] Taine, S.: The medical literature analysis and retrieval system (medlars)
of the us national library of medicine. Methods of information in medicine
2(02), 65–69 (1963)