1 / 29

GLARE: a Domain-Independent System for Acquiring, Representing and Executing Clinical Guidelines

GLARE: a Domain-Independent System for Acquiring, Representing and Executing Clinical Guidelines. Paolo Terenziani, Stefania Montani, Alessio Bottrighi, DI, Universita’ del Piemonte Orientale “Amedeo Avogadro”, Alessandria, Italy Gianpaolo Molino, Mauro Torchio

Download Presentation

GLARE: a Domain-Independent System for Acquiring, Representing and Executing Clinical Guidelines

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. GLARE: a Domain-Independent System for Acquiring, Representing and Executing Clinical Guidelines Paolo Terenziani, Stefania Montani, Alessio Bottrighi, DI, Universita’ del Piemonte Orientale “Amedeo Avogadro”, Alessandria, Italy Gianpaolo Molino, Mauro Torchio Laboratorio di Informatica Clinica, Azienda Ospedaliera S. Giovanni Battista, Torino, Italy - The GLARE system - Advances: support to decision making - Advances: management of temporal constraints (see AMIA06 poster T020) - Advances: contextualization facilities (see AMIA06 poster M010) - Advances: model-checking facilities (see AMIA06 presentation in session S52)

  2. Introduction Clinical guidelines are a means for specifying the “best” clinical procedures and for standardizing them Adopting (computer-based) clinical guidelines is advantageous Different roles: - support - critique - evaluation - education - …... Many different computer systems managing clinical guidelines (e.g., Asgaard, GEM, Gliff, Guide, PROforma,…)

  3. GLARE(GuideLine Acquisition Representation and Execution) - Joint project: Dept. Comp. Sci., Univ. Alessandria (It): P. Terenziani, S.Montani, A.Bottrighi Dept. Comp. Sci., Univ. Torino (It): L.Anselma,G.Correndo Az. Osp. S. Giovanni Battista, Torino (It): G.Molino, M.Torchio - Domain independent (e.g., bladder cancer, reflux esophagitis, heart failure) - Phisician-oriented & User-friendly Some recent pubblications: Terenziani et al., AIIMJ 01,07a,07b, AMIA 00,02,03, Medinfo 04, CGP’04a,04b, AI*IA 03,05, GIN 04,05, AIME 05a,05b,05c AMIA’06 posters T020 and M010 AMIA’06 paper in session S52

  4. CG D A B C B B1 B2 B1 B2.3 B1.2 B2.1 B1.1 B2.2 B2 Representation Formalism Tree of graphs Atomic actions Composite actions (plans) Control relations between actions: - sequence - “controlled” - alternative - repetition (e.g. “3 times each 2 days for a month”)

  5. Representation FormalismHierarchy of Action Types Action Plan Work action Query Decision Conclusion Clinical action Pharmacol. prescription Diagnostic decision Therapeutic decision

  6. Representation Formalismdescription of a work action

  7. Surgical treatment Treatment choice Expectant management Litholitic therapy Therapeutic decisions Fixed set of parameters (effectiveness, cost, side-effects, compliance, duration) Treatment choice for symptomless gallbladder stones

  8. Local information associated with treatment choice (in the symptomless gallbladder stones guideline)

  9. Diagnostic Decisions * Decision parameters <finding, attribute, value> * Decision criteria score-based mechanism For each alternative For each parameter  score  (additive) threshold range

  10. Diagnostic Decisions(Gastro Esophageal Reflux Disease) PARAMETERS: heartburn absent (“no-hb”), heartburn lasted not more than 3 months (“hb=<3”), heartburn r lasted more than 3 months (“hb>3m”); dysphagia absent (“no-dys”); dysphagia present (“dys”); occurrence of weight loss (“wl”) or non-occurrence (“no-wl”); hemathemesis absence (“no-hem”); hemathemesis presence (“hem”); postural reflux absent (“no-ref”), postural reflux lasted not more than 3 months (“ref=<3”); postural reflux lasted more than three months (“ref>3m”). THRESHOLD:>9. (One should conclude “no GERD” only if heartburn, dysphagia, weight loss, hematemesis and postural reflux are all absent.)

  11. Clinical DB Expert Physician User Physician Pharmac. DB Acquisition Interface Execution Interface Resource DB Knowledge Manager Execution Module ICD DB Guidelines DB Guidelines Instantiation DB Patient DB Architecture of the system

  12. Acquisition Strict interaction with DB’s Clinical DB  hierarchically organized vocabulary  Standardization  Data sharing  Support for semantic checks (e.g., legal attribute values) NOTE: the organization (schema) of Patients DB is equal to the one of the Clinical DB  During acquisition, GLARE gets the information used at execution-time to retrieve automatically the patient’s data (via automatically generated dynamic-SQL queries)

  13. Acquisition“Intelligent” helps (syntactic & semantic checks) - “legal” names & “legal” values for attributes - “logical” design criteria (no unstructured cycles, well-formed alternatives & decisions) - “semantic” checks: consistency of temporal constraints

  14. AcquisitionGraphical Interface

  15. Agenda-based execution In the agenda - next actions to be executed - execution time (earliest and latest e.t.)  “On-line” execution: wait until the next e.t. (support physician in clinical activity)  “Simulated” execution: jump to the next e.t. (education, critique, evaluation)

  16. Executing atomic actions Work actions: - evaluate pre-conditions - execute action within its range of time - delete from the agenda Query actions: - retrieve data from patient’s DB - wait for data not already in the DB, or for the update of “expired” data Conclusion actions: - insert conclusion into the patient’s DB Decision actions: (see alternatives)

  17. Executing composite actions Sequence: - evaluate next action e.t. (given current time and delay) - execute it Concurrent actions: - execute actions according with the temporal constraints Decision + alternative actions (e.g., diagnostic decision): - evaluate parameter values for each alternative, using patient’s DB - determine the score for each alternative - compare the score with the threshold - show the alternatives to the user-physician (distinguishing between “suggested” and “not suggested” ones, and showing parameters and scores) - execute the alternative chosen by the physician (warning available)

  18. Executing Clinical Guidelines: other issues  Repeated actions and user-defined periodicities - expressive language for user-defined periodicities [IEEE TKDE, 97] - computing next execution time  Exits  Failures return to previous decisions (chronological vs. guided backtracking)  A user-friendly graphical interface

  19. Implementation & Testing Prototypical version (Java + Access) under revision TESTS (1) Using GLARE to build guidelines from scratch take advantage of grafical and “intelligent checks” facilities - bladder cancer algorithm (2) Converting guidelines on paper to GLARE inconsistencies/ambiguities detected! - reflux esophagitis, heart failure, ischemic stroke

  20. Advanced features in GLARE:Supporting medical decision making “local information”: considering just the decision criteria associated with the specific decision at hand “global information”: information stemming from relevant alternative pathways in the guideline

  21. Advanced features in GLARE:Supporting medical decision making:the “What if” facility Facility for gathering the chosen parameter (e.g, resources, costs, times) from the “relevant” alternative paths on the guideline It provides an idea of what could happen in the rest of the guideline if the physician selects a given alternative for the patient, and supports for comparisons of the alternatives Enhanced with an application of “Decision Theory” methodology, to provide an advanced tool to consider costs (money, time, resources) and utility of alternative sequences of actions (QALYs)

  22. Laparoscopy Surgical treatment Laparoscopy Choice of surgical appr. Treatment choice Expectant management Laparotomy Laparotomy Litholitic therapy Litholitic treatment Syntomless gallbladder stonestreatment choice: “global information”

  23. Laparoscopy Surgical treatment Laparoscopy Choice of surgical appr. Treatment choice Expectant management Laparotomy Laparotomy Litholitic therapy Litholitic treatment Syntomless gallbladder stonestreatment choice: “global information” Duration min:2 days Max:3 days

  24. Laparoscopy Surgical treatment Laparoscopy Choice of surgical appr. Treatment choice Expectant management Laparotomy Litholitic therapy Litholitic treatment Syntomless gallbladder stonestreatment choice: “global information” Laparotomy Duration min:6 days Max:8 days

  25. Laparoscopy Surgical treatment Laparoscopy Choice of surgical appr. Treatment choice Expectant management Laparotomy Laparotomy Litholitic therapy Litholitic treatment Syntomless gallbladder stonestreatment choice: “global information” Duration min:1 day Max: all life long

  26. Laparoscopy Surgical treatment Laparoscopy Choice of surgical appr. Treatment choice Expectant management Laparotomy Laparotomy Litholitic therapy Litholitic treatment Syntomless gallbladder stonestreatment choice: “global information” Duration min:2 months Max:1 year

  27. Local information associated with treatment choice (in the symptomless gallbladder stones guideline)

  28. Digression 2Why don’t we put “global info (about paths)” locally in the decision actions? Given “local info” in each node, collecting & storing might be automatic HOWEVER: - exponential space in each node - data duplication (consistency after updates?) - not user friendly (too many data!) - not all aternatives are “relevant” - data not always necessary >> global data only at execution time, on request

  29. Advanced features in GLARE Management of temporal constraints >>>>> AMIA06 poster T020 Session S50 Terenziani et al., Proc. AMIA’03 Terenziani et al., Artificial Intelligence in Medicine Journal, to appear Contextualization facilities >>>>>> AMIA06 poster M010 Session S13 Terenziani et al., Proc. Medinfo’04, AIME’05 Model-checking facilities >>>>> AMIA06 paper, session S52 Terenziani et al., ECAI’06 Guidelines worshop

More Related