Inferring recommendation interactions in clinical guidelines

Veruska Carretta Zamborlini, Rinke Hoekstra, Marcos Da Silveira, Cedric Pruski, A.C.M. ten Teije, F.A.H. van Harmelen

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

The formal representation of clinical knowledge is still an open research topic. Classical representation languages for clinical guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking for ways to re-use, combine, and reason over existing clinical knowledge. These limitations are especially problematic in the context of multimorbidity; patients that suffer from multiple diseases. To overcome these limitations, this paper proposes a model for clinical guidelines (TMR4I) that allows the re-use and combination of knowledge from multiple guidelines. Semantic Web technology is applied to implement the model, allowing us to automatically infer interactions between recommendations, such as recommending the same drug more than once. It relies on an existing Linked Data set, DrugBank, for identifying drug-drug interactions. We evaluate the model by applying it to two realistic case studies on multimorbidity that combine guidelines for two (Duodenal Ulcer and Transient Ischemic Attack) and three diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with existing methods.
Original languageEnglish
Pages (from-to)421-446
Number of pages26
JournalSemantic Web
Volume7
Issue number4
DOIs
Publication statusPublished - 2016

Fingerprint

Drug interactions
Medical problems
Semantic Web

Keywords

  • Clinical knowledge representation
  • OWL
  • SPARQL
  • SWRL
  • combining medical guidelines
  • multimorbidity
  • reasoning
  • rules

Cite this

Carretta Zamborlini, Veruska ; Hoekstra, Rinke ; Da Silveira, Marcos ; Pruski, Cedric ; ten Teije, A.C.M. ; van Harmelen, F.A.H. / Inferring recommendation interactions in clinical guidelines. In: Semantic Web. 2016 ; Vol. 7, No. 4. pp. 421-446.
@article{4d178cf0055f4dd1acf70f17b8d01a25,
title = "Inferring recommendation interactions in clinical guidelines",
abstract = "The formal representation of clinical knowledge is still an open research topic. Classical representation languages for clinical guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking for ways to re-use, combine, and reason over existing clinical knowledge. These limitations are especially problematic in the context of multimorbidity; patients that suffer from multiple diseases. To overcome these limitations, this paper proposes a model for clinical guidelines (TMR4I) that allows the re-use and combination of knowledge from multiple guidelines. Semantic Web technology is applied to implement the model, allowing us to automatically infer interactions between recommendations, such as recommending the same drug more than once. It relies on an existing Linked Data set, DrugBank, for identifying drug-drug interactions. We evaluate the model by applying it to two realistic case studies on multimorbidity that combine guidelines for two (Duodenal Ulcer and Transient Ischemic Attack) and three diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with existing methods.",
keywords = "Clinical knowledge representation, OWL, SPARQL, SWRL, combining medical guidelines, multimorbidity, reasoning, rules",
author = "{Carretta Zamborlini}, Veruska and Rinke Hoekstra and {Da Silveira}, Marcos and Cedric Pruski and {ten Teije}, A.C.M. and {van Harmelen}, F.A.H.",
year = "2016",
doi = "10.3233/SW-150212",
language = "English",
volume = "7",
pages = "421--446",
journal = "Semantic Web",
issn = "1570-0844",
publisher = "IOS Press",
number = "4",

}

Carretta Zamborlini, V, Hoekstra, R, Da Silveira, M, Pruski, C, ten Teije, ACM & van Harmelen, FAH 2016, 'Inferring recommendation interactions in clinical guidelines' Semantic Web, vol. 7, no. 4, pp. 421-446. https://doi.org/10.3233/SW-150212

Inferring recommendation interactions in clinical guidelines. / Carretta Zamborlini, Veruska; Hoekstra, Rinke; Da Silveira, Marcos; Pruski, Cedric; ten Teije, A.C.M.; van Harmelen, F.A.H.

In: Semantic Web, Vol. 7, No. 4, 2016, p. 421-446.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Inferring recommendation interactions in clinical guidelines

AU - Carretta Zamborlini, Veruska

AU - Hoekstra, Rinke

AU - Da Silveira, Marcos

AU - Pruski, Cedric

AU - ten Teije, A.C.M.

AU - van Harmelen, F.A.H.

PY - 2016

Y1 - 2016

N2 - The formal representation of clinical knowledge is still an open research topic. Classical representation languages for clinical guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking for ways to re-use, combine, and reason over existing clinical knowledge. These limitations are especially problematic in the context of multimorbidity; patients that suffer from multiple diseases. To overcome these limitations, this paper proposes a model for clinical guidelines (TMR4I) that allows the re-use and combination of knowledge from multiple guidelines. Semantic Web technology is applied to implement the model, allowing us to automatically infer interactions between recommendations, such as recommending the same drug more than once. It relies on an existing Linked Data set, DrugBank, for identifying drug-drug interactions. We evaluate the model by applying it to two realistic case studies on multimorbidity that combine guidelines for two (Duodenal Ulcer and Transient Ischemic Attack) and three diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with existing methods.

AB - The formal representation of clinical knowledge is still an open research topic. Classical representation languages for clinical guidelines are used to produce diagnostic and treatment plans. However, they have important limitations, e.g. when looking for ways to re-use, combine, and reason over existing clinical knowledge. These limitations are especially problematic in the context of multimorbidity; patients that suffer from multiple diseases. To overcome these limitations, this paper proposes a model for clinical guidelines (TMR4I) that allows the re-use and combination of knowledge from multiple guidelines. Semantic Web technology is applied to implement the model, allowing us to automatically infer interactions between recommendations, such as recommending the same drug more than once. It relies on an existing Linked Data set, DrugBank, for identifying drug-drug interactions. We evaluate the model by applying it to two realistic case studies on multimorbidity that combine guidelines for two (Duodenal Ulcer and Transient Ischemic Attack) and three diseases (Osteoarthritis, Hypertension and Diabetes) and compare the results with existing methods.

KW - Clinical knowledge representation

KW - OWL

KW - SPARQL

KW - SWRL

KW - combining medical guidelines

KW - multimorbidity

KW - reasoning

KW - rules

UR - http://www.scopus.com/inward/record.url?scp=84971500460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971500460&partnerID=8YFLogxK

U2 - 10.3233/SW-150212

DO - 10.3233/SW-150212

M3 - Article

VL - 7

SP - 421

EP - 446

JO - Semantic Web

JF - Semantic Web

SN - 1570-0844

IS - 4

ER -