Difference between revisions of "Computer-interpretable guidelines"
(→Computer-Interpretable Guidelines) |
|||
| Line 2: | Line 2: | ||
Clinical practice guidelines aim to promote best medical practices through the reduction of medical errors and practice variation. Guidelines with a national scope concerning important medical issues or disease domains represent one of the highest forms of practice policies. In traditional form, guidelines have been narrative / textual in composition, and have typically been created under the control of medical specialty organizations. ''Narrative guidelines'' are time- and resource-intensive in their creation and maintenance, and are limited in value by failing to provide specific recommendations in a given clinical scenario.(1) On the other hand, ''computer-interpretable guidelines'' (CIGs) can produce personalized recommendations during patient encounters, which render them more likely to affect provider behavior than standard narrative guidelines.(2) | Clinical practice guidelines aim to promote best medical practices through the reduction of medical errors and practice variation. Guidelines with a national scope concerning important medical issues or disease domains represent one of the highest forms of practice policies. In traditional form, guidelines have been narrative / textual in composition, and have typically been created under the control of medical specialty organizations. ''Narrative guidelines'' are time- and resource-intensive in their creation and maintenance, and are limited in value by failing to provide specific recommendations in a given clinical scenario.(1) On the other hand, ''computer-interpretable guidelines'' (CIGs) can produce personalized recommendations during patient encounters, which render them more likely to affect provider behavior than standard narrative guidelines.(2) | ||
| − | The process of formally representing knowledge in CIGs is required to render the information computable.(3) Formal representation removes ambiguities that are present in the 'relaxed language' of narrative guidelines, and permit identification of for which information is lacking or missing. The formalization process that converts narrative guidelines to CIGs involves 'marking-up' narrative text and indicating relationships with certain structural components of the guideline, according to markup ontologies.(4) CIGs can also be created de novo using one of several modeling methods (ex. Asbru, EON, PRODIGY, GLIF, SAGE, PRO''forma'', Arden Syntax, GLARE, GASTON, OncoDoc).(4) A review by Peleg and colleagues identified eight components that define the architecture of CIGs.(5) These components can be divided into two groups - those functioning | + | The process of formally representing knowledge in CIGs is required to render the information computable.(3) Formal representation removes ambiguities that are present in the 'relaxed language' of narrative guidelines, and permit identification of for which information is lacking or missing. The formalization process that converts narrative guidelines to CIGs involves 'marking-up' narrative text and indicating relationships with certain structural components of the guideline, according to markup ontologies.(4) CIGs can also be created de novo using one of several modeling methods (ex. Asbru, EON, PRODIGY, GLIF, SAGE, PRO''forma'', Arden Syntax, GLARE, GASTON, OncoDoc).(4) A review by Peleg and colleagues identified eight components that define the architecture of CIGs.(5) These components can be divided into two groups - those functioning to create decisions and actions, and those linking the guideline to clinical data and medical concepts.(4) |
| − | However, CIGs, like traditional narrative guidelines, are subject to some limitations. Unlike the concept of ''standards'', where recommendations are so well-founded that the vast majority of clinicians would be expected to agree | + | However, CIGs, like traditional narrative guidelines, are subject to some limitations. Unlike the concept of ''standards'', where recommendations are so well-founded that the vast majority of clinicians would be expected to agree and adhere to them, guidelines allow a greater degree of allowance for interpretation and acceptance.(1) Consequently, guidelines are rendered less powerful in the mission to improve care through reducing practice variation. Other challenges include the debate over whether a standards-based approach might be helpful in the development of guidelines and their components. Another need exists for the development of workflow solutions to allow for guideline use within clinical information systems.(4) |
Although guideline recommendations and algorithms are based on evidence, they may not integrate well with the provider's cognitive processes or clinical flow characteristics during a patient encounter. Progress will need to be made in the challenge to encode complex medical thinking. | Although guideline recommendations and algorithms are based on evidence, they may not integrate well with the provider's cognitive processes or clinical flow characteristics during a patient encounter. Progress will need to be made in the challenge to encode complex medical thinking. | ||
| Line 17: | Line 17: | ||
5. Peleg M., Tu S., Bury J., et a. Comparing computer-interpretable guideline models: A case-study approach. JAMIA 2003; 10(1): 52-68. | 5. Peleg M., Tu S., Bury J., et a. Comparing computer-interpretable guideline models: A case-study approach. JAMIA 2003; 10(1): 52-68. | ||
| − | |||
| − | |||
Revision as of 02:59, 21 November 2008
Computer-Interpretable Guidelines Clinical practice guidelines aim to promote best medical practices through the reduction of medical errors and practice variation. Guidelines with a national scope concerning important medical issues or disease domains represent one of the highest forms of practice policies. In traditional form, guidelines have been narrative / textual in composition, and have typically been created under the control of medical specialty organizations. Narrative guidelines are time- and resource-intensive in their creation and maintenance, and are limited in value by failing to provide specific recommendations in a given clinical scenario.(1) On the other hand, computer-interpretable guidelines (CIGs) can produce personalized recommendations during patient encounters, which render them more likely to affect provider behavior than standard narrative guidelines.(2)
The process of formally representing knowledge in CIGs is required to render the information computable.(3) Formal representation removes ambiguities that are present in the 'relaxed language' of narrative guidelines, and permit identification of for which information is lacking or missing. The formalization process that converts narrative guidelines to CIGs involves 'marking-up' narrative text and indicating relationships with certain structural components of the guideline, according to markup ontologies.(4) CIGs can also be created de novo using one of several modeling methods (ex. Asbru, EON, PRODIGY, GLIF, SAGE, PROforma, Arden Syntax, GLARE, GASTON, OncoDoc).(4) A review by Peleg and colleagues identified eight components that define the architecture of CIGs.(5) These components can be divided into two groups - those functioning to create decisions and actions, and those linking the guideline to clinical data and medical concepts.(4)
However, CIGs, like traditional narrative guidelines, are subject to some limitations. Unlike the concept of standards, where recommendations are so well-founded that the vast majority of clinicians would be expected to agree and adhere to them, guidelines allow a greater degree of allowance for interpretation and acceptance.(1) Consequently, guidelines are rendered less powerful in the mission to improve care through reducing practice variation. Other challenges include the debate over whether a standards-based approach might be helpful in the development of guidelines and their components. Another need exists for the development of workflow solutions to allow for guideline use within clinical information systems.(4)
Although guideline recommendations and algorithms are based on evidence, they may not integrate well with the provider's cognitive processes or clinical flow characteristics during a patient encounter. Progress will need to be made in the challenge to encode complex medical thinking.
1. Emberton M. Clinical practice guidelines for the surgeon-how should they be understood and applied? BJU International 2001; 88(6):485-492.
2. Peleg M., Patel V.L., Tu S. et al. Support for guideline development through error classification and constraint checking. Proc AMIA Symp 2002:607-611.
3. Kaiser K., Akkaya C., and Miksch S. How can information extraction ease formalizing treatment processes in clinical practice guidelines? A method and its execution. Artificial Intelligence in Medicine 2007; 39:151-163.
4. Peleg M.(2007) Guidelines and Workflow Models. In R.A. Greenes (Ed.), Clinical Decision Support - The Road Ahead (p 282-303). Boston, MA: Elsevier.
5. Peleg M., Tu S., Bury J., et a. Comparing computer-interpretable guideline models: A case-study approach. JAMIA 2003; 10(1): 52-68.
