=Paper=
{{Paper
|id=Vol-448/paper-5
|storemode=property
|title=Controlled Natural Language for Clinical Practice Guidelines
|pdfUrl=https://ceur-ws.org/Vol-448/paper5.pdf
|volume=Vol-448
|dblpUrl=https://dblp.org/rec/conf/cnl/ShiffmanMKFKK09a
}}
==Controlled Natural Language for Clinical Practice Guidelines==
https://ceur-ws.org/Vol-448/paper5.pdf
Controlled Natural Language for
Clinical Practice Guidelines?
Richard N. Shiffman1 , George Michel1 , Michael Krauthammer1 , Norbert E.
Fuchs2 , Kaarel Kaljurand2 , and Tobias Kuhn2
1
School of Medicine, Yale University
{richard.shiffman,george.michel,michael.krauthammer}@yale.edu
http://gem.med.yale.edu/ergo/
2
Department of Informatics and Institute of Computational Linguistics,
University of Zurich
{fuchs,kalju,tkuhn}@ifi.uzh.ch
http://attempto.ifi.uzh.ch
Abstract. Clinicians would benefit from decision support systems in-
corporating the knowledge of clinical practice guidelines. However, the
unstructured form of the guidelines makes them unsuitable for formal
representation. To remedy this shortcoming we translated a set of pe-
diatric guidelines into Attempto Controlled English (ACE). An expe-
rienced pediatrician and a knowledge engineer assessed that ACE can
accurately represent the clinical concepts and the proposed actions of
the guidelines. Currently, we are developing a systematic and replicable
approach to authoring guideline recommendations in ACE.
1 Introduction
Clinical practice guidelines are defined as “systematically developed statements
to assist practitioner and patient decisions about appropriate healthcare for spe-
cific clinical circumstances” [2]. Guidelines are developed by teams of clinical ex-
perts who systematically review and appraise the relevant biomedical literature
and apply rigorous methods to link recommendations about appropriate care to
the supporting scientific evidence. More than 4000 guidelines have been pub-
lished by various organizations. The large number of guidelines impedes their
practical application by clinicians who would profit from computerized decision
support.
However, there is a mismatch between the unstructured narrative form of the
published guidelines and the formality that is necessary for the operationalization
of guideline knowledge [4]. Uncritical translation of such recommendations into
computable statements risks distortion of the guideline authors’ intent [8, 9].
In order to address this problem, we investigate writing guidelines in At-
tempto Controlled English (ACE) [3]. ACE is a controlled natural language, i.e.
?
This work was supported by the US National Library of Medicine and the Agency
for Healthcare Research and Quality (grant R01 LM007199).
guideline development guideline application
domain experts committee clinician
decisions &
feedback
expertise recommen-
dations
decision electronic
authoring tool support health record
formal patient
guidelines
system data
system
Fig. 1. This diagram shows the general architecture of our approach. It shows the
information and data flows between systems (in rectangular shapes) and users. The
focus of the ERGO project lies on the guideline development part.
a precisely defined subset of English with restrictions on vocabulary and gram-
mar. These restrictions result in increased terminological consistency, reduced
ambiguity, consistent vocabulary, potentially templated phrases, and a generally
simplified sentence and text structure. ACE has the additional benefit of being
supported by a parsing engine that translates ACE texts into first-order logic,
thereby providing a computable format and supporting automatic reasoning.
In the initial phases of the ERGO Project (Effective Representation of Guide-
lines with Ontologies)3 we will demonstrate the feasibility of translating guideline
knowledge into rules. We propose to use ACE as an intermediary representation
between the implicit knowledge contained in the minds of the domain experts and
the representation of that knowledge in an explicit computable form. Our goal
is to develop an authoring tool that helps guideline authors to reduce ambiguity,
vagueness, incompleteness, and inconsistency, and facilitates the translation of
guideline recommendations into logic statements that can be implemented in
decision support systems. These systems generally depend on production rules
derived from guideline recommendations to create a knowledge base. The de-
cision support system compares an individual patient’s characteristics (demo-
graphic descriptors and clinical findings) against these rules to guide a health
provider by offering patient-specific and situation-specific advice. A second goal
is to demonstrate that ACE is a good candidate controlled natural language
for writing recommendations. Figure 1 shows the general architecture of our
approach.
3
http://gem.med.yale.edu/ergo/
Table 1. A comparison of three of the eleven original natural language guidelines
together with their ACE equivalents
Original guideline Attempto Controlled English
The presence of UTI should be considered If
in infants and young children 2 months to 2 the patient is a young child who has an unexplained fever
years of age with unexplained fever (strength then
of evidence: strong). the clinician must consider UTI.
In infants and young children 2 months to 2 If
years of age with unexplained fever, the de- the patient is a young child who has an unexplained fever
gree of toxicity, dehydration, and ability to then
retain oral intake must be carefully assessed the clinician must assess the degree of Toxicity and
(strength of evidence: strong). must assess the degree of Dehydration and
must assess the Ability-to-retain-oral-intake.
If an infant or young child 2 months to 2 If
years of age with unexplained fever is assessed the patient is a young child who has an unexplained fever and
as being sufficiently ill to warrant immedi- the patient is sufficiently-ill
ate antimicrobial therapy, a urine specimen then
should be obtained by SPA or transurethral the clinician should analyze a culture of a urine-specimen
bladder catheterization; [...] (strength of evi- that is obtained-by SPA or
dence: good). that is obtained-by Transurethral-catheterization.
2 Expressing Clinical Practice Guidelines in ACE
We plan to use ACE to encode the summary recommendation statements that
form the backbone of guideline documents. Often published in boldface, these
recommendation statements embody the critical knowledge about appropriate
practice that is amplified by supporting text. A first critical step is to establish
whether clinical guidelines can be adequately expressed in ACE, and to identify
potential barriers to the effective translation. To answer this question we decided
to manually “ACE’ify” the set of recommendations contained in the guideline
“Diagnosis, Treatment, and Evaluation of the Initial Urinary Tract Infection
in Febrile Infants and Young Children” (UTI) [1]. UTI was chosen because (1)
it includes a sufficient number of recommendations to exercise the translation
process, (2) its recommendations involve a variety of action types and levels
of obligation, (3) some recommendations incorporate a temporal sequence, (4)
while others contain sentences related by anaphoric references. This guideline
demonstrates many challenges in translating recommendations in spite of its
small size. All eleven UTI guidelines could be successfully translated into ACE.
Table 1 shows three of the original natural language guidelines together with
their ACE equivalents.
The recommendations were translated by 3 members of the ACE team at
the University of Zurich. Once translated into ACE, the recommendations were
reviewed by a pediatrician with expertise in clinical guidelines and by a knowl-
edge engineer. Judgements were made regarding the accuracy of translation,
the naturalness of the ACE statements, and potential solutions to encountered
impediments of the translation. Altogether, the reviewers concluded that ACE
is capable of accurately stating the clinical concepts and the actions described
in the guideline’s recommendations. Nevertheless, the reviewers identified some
problem areas.
The example guidelines use specialized medical terms that are not part of
the basic lexicon of the ACE parser. Though many of these terms can be found
in lexicons like UMLS and SNOMED, the problem remains that terms — such
as “ability to retain oral intake,”, “sufficiently ill” and “SPA” — require clear
and consistent specifications by guideline authors. We plan to solve this problem
by providing an authoring tool that accepts only terms that are known to the
system and that have a clearly defined meaning.
Considerable uncertainty accompanies most medical decision making. Evi-
dence validity as well as the accuracy of clinical observations and measurements
contribute to this uncertainty. Guideline authors express the uncertainty by us-
ing deontic modals and by including coded representations of evidence quality
and recommendation strength with their recommendations. Strength of recom-
mendation is a judgment based on the anticipated benefits, risks, harms, and
costs of the proposed actions.
The modals “can” and “must” originally offered by ACE are not sufficient
to capture the levels of obligation imposed by recommendations. In guideline
recommendations “should” is the most frequently used modal with a level of
obligation between “can” and “must”. To adequately represent the required
levels, ACE was extended by the modal “should”. This is already reflected in
the examples of table 1.
While “ACE’ifying” UTI, we noticed that a systematic approach is needed
to consistently author clinical guidelines, and to adequately support clinicians in
the use of guidelines. All knowledge should be made explicit, all terms should be
used consistently, and guidelines should be rendered operational to be executed
under the control of the responsible clinician — who ultimately must decide
whether, or not, to follow the recommendations of a guideline.
To make all knowledge explicit and to enforce a consistent use of this knowl-
edge we introduce a domain-specific lexicon and a background ontology. Here is
a sample of the UTI background ontology:
Every child is a person.
SPA is a method.
No analysis confirms X and excludes X.
Every antimicrobial-therapy is a therapy.
...
To make the guidelines operational we express them as linked rules that are
executed under the control of the clinician. Every rule (see Table 1) consists
of preconditions that must be fulfilled to trigger the rule, and conclusions that
are true after the rule fired, and that can be used as preconditions for other
rules. To get the rule machinery running, a number of initial facts are asserted
that originate from the patient’s electronic health record or that are manually
asserted by the clinician, for instance:
The patient is a young child.
The patient’s age is 1.5 years.
The patient has an unexplained fever.
...
The firing of a guideline rule can enable other rules, so that potentially every
rule can be fired at some point.
3 Conclusions and Future Work
We showed that ACE can be used to adequately express clinical practice guide-
lines. Furthermore, we prototypically developed a systematic approach to author
and to transparently use clinical practice guidelines stated in ACE.
Our immediate plan is to build a “look-ahead” editor for clinical practice
guidelines expressed in ACE that dynamically displays the knowledge defined so
far and the specific options available for extending or revising it, similiar to the
existing ACE Editor4 . This approach was described by Scott et al. [6], and has
been used by Schwitter [7] and by Kuhn [5] working with controlled language
grammars. Furthermore, in the future, we plan to embed rules created with the
ACE editor in a decision support system that advises clinicians. That system will
combine the rules with clinical observations derived from an electronic health
record system to provide guidance about best practices for care.
References
1. American Academy of Pediatrics. Practice Parameter: The Diagnosis, Treatment,
and Evaluation of the Initial Urinary Tract Infection in Febrile Infants and Young
Children. In Pediatrics, 1999;103:843-52.
2. M. J. Field, K. N. Lohr (eds.). Guidelines for Clinical Practice: From Development
to Use, National Academy Press, 1992.
3. Norbert E. Fuchs, Kaarel Kaljurand, and Tobias Kuhn. Attempto Controlled En-
glish for Knowledge Representation. In Reasoning Web, 4th International Summer
School 2008, Tutorial Lectures, 2008.
4. R. A. Greenes, M. Peleg, A. Boxwala, S. Tu, V. Patel, E. H. Shortliffe Sharable
Computer-Based Clinical Practice Guidelines: Rationale, Obstacles, Approaches,
and Prospects. In Medinfo, 2001.
5. T. Kuhn. AceWiki: Collaborative Ontology Management in Controlled Natural
Language. In 3rd Semantic Wiki Workshop, CEUR Workshop Proceedings, 2008.
6. R. Power, D. Scott, R. Evans. What You See Is What You Meant: Direct Knowledge
Editing with Natural Language Feedback. In Proc. 13th European Conference on
Artificial Intelligence (ECAI 98), 1998.
7. R. Schwitter, A. Ljungberg, D. Hood. ECOLE: A Look-ahead Editor for a Con-
trolled Language. In Proc 8th European Association for Machine Translation and
the 4th Controlled Language Applications Workshop (EAMT-CLAW 03), 2003.
8. R. N. Shiffman, G. Michel, A. Essaihi, E. Thornquist. Bridging the Guideline
Implementation Gap: A Systematic, Document-centered Approach to Guideline
Implementation. J Am Med Informatics Assoc, 2004; 5:418-26.
9. Y. Sun, F. J. van Wingerde, C. J. Homer. The Challenges of Implementing a
Real-Time Clinical Practice Guideline. Clin Perform Quality Health Care, 1999.
4
http://attempto.ifi.uzh.ch/aceeditor