Clinical reasoning, involving abstraction, abduction, deduction, 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 differential diagnosis techniques. For a given clinical scenario, overlapping reasoning types and strategies may be employed by a physician in conjunction, signifying the need for our AI system to perform hybrid reasoning. Therefore, we consider the construction of a hybrid reasoner that is compatible with description logics. For medical scenarios where description 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 recommendations will be evaluated based on domain expert consultation in order to determine whether the recommendation aligns with what the expert would recommend.
This thesis focuses on the design and implementation of a clinical decision
support system that is able to perform hybrid reasoning by emulating how
physicians reason. Clinical reasoning is employed in many medical tasks, such as those
involving information comprehension, decision-making, and medical error
identi cation. Approaches for clinical reasoning use four distinct types of inference:
abstraction, abduction, deduction, and induction [
To illustrate the applicability of this revised ST-Model framework using a simple example, consider a scenario where a patient gained a signi cant 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 e ect, or 4) a biological e ect.1 These hypotheses can be ranked in terms of importance, where medicinal or biological e ects 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 e ects could be broken into sub-hypotheses, such as due side-e ects 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 e ect 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 (thyroidstimulating hormone) test to check for thyroxine (a thyroid hormone) levels.
In order to implement the ST-Model framework into an Arti cial 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
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 physician reasons. Earlier work on medical expert systems use approaches involving 1 https://www.webmd.com/diet/ss/slideshow-weight-gain-shockers decision tree rules or the construction of knowledge bases by leveraging machine learning techniques. Our approach di ers from that earlier work in that we are building an AI system using semantic web technologies in a manner that conforms with Description Logics (in particular, with OWL-DL). This allows us to both leverage recent ontologies created in knowledge representation for health care e orts and existing inference engines that reason over OWL-DL ontologies. Furthermore, we note that by limiting expressivity, we can perform tractable reasoning 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
abductive 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 de nes in her thesis [
As early as the 1950s, Arti cial Intelligence (AI) techniques were beginning to
be applied to model clinical reasoning and medical decision-making [
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 di erent
situations [
While work on expert systems continued into the 80s, the importance of having
these systems be explainable and justi ed 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 [
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 [
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 nd that
mentions of abstraction, deduction, induction, abduction, temporal reasoning,
and causal reasoning [
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)? Speci cally, we consider satis ability, consistency, and explainability. In terms of satis ability, we search for contradictions with respect to the ontologies that are used and between facts that are asserted to be true. To check for consistency, we determine if the facts in the knowledge base are satis able. 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 implementation 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 knowledge 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 statements made by physicians (captured in written transcripts) be represented as reasoning rules? As mentioned earlier, our approach is based on the ST-model. In terms of representing verbal statements, we consider representational simpli cation 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 recommendation 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 condition 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
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 [
In terms of implementation, a customizable deductive reasoner has been
incorporated into the Whyis [
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. In this section, we begin by discussing some of the evaluation that has been conducted for the aforementioned methodology. We continue by discussing additional 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
integration approaches, and mapping languages [
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 con dence scores. While the determination of the full evaluation pipeline is still work in progress, in addition to measuring hypothesis con dence, we plan to conduct a comparative evaluation against other hybrid reasoning systems. Additionally, for each individual reasoning component, 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 corresponds 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 hypotheses. 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
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 using semantic web technologies. Our approach di ers 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 e cient reasoners (for example, for performing deduction or temporal reasoning) that also conform with OWLDL 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 technologies 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 speci c challenges by aiding 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 leveraging CPGs to represent existing therapy plan recommendations and test physician conformance to CPGs. Additionally, medical information from biomedical resources that provide recommendations based on scienti c 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 su ciently challenging in itself. Future extensions may include leveraging existing machine learning techniques to incorporate induction capabilities into our framework.
I am advised by Professor Deborah L. McGuinness, Constellation Chair at Tetherless 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