Presentation is loading. Please wait.

Presentation is loading. Please wait.

GreEd and its Rules Representation Hemant Shah M.D., M. Surg. Sr. Research Informatician, CSRI Henry Ford Health System (GreEd and its.

Similar presentations


Presentation on theme: "GreEd and its Rules Representation Hemant Shah M.D., M. Surg. Sr. Research Informatician, CSRI Henry Ford Health System (GreEd and its."— Presentation transcript:

1 GreEd and its Rules Representation Hemant Shah M.D., M. Surg. Sr. Research Informatician, CSRI Henry Ford Health System hshah2@hfhs.org (GreEd and its Creed)

2 What is GreEd? Graphical Rule Elements Editor A tool to author and edit rules  Easy to use graphical representation of rules  Drag and drop is all you need  Internal rule syntax inspired by LISP  Allows testing of rules from within the environment  Currently in use for Proteus based tools  Architecture extensible to support creation of rules in multiple languages (e.g., Arden Syntax, Gello Expressions, Java, RuleML, Jess, JBoss Rules etc.)  Source soon to be made available under a liberal Open Source License (LGPL or similar)

3 Rule – General Aspects Left Hand Side of a Rule is a boolean expression (e.g. Age more than 45 ) LHS expression may contain sub- expressions The Right Hand Side varies but LHS is similar in most rules Therefore suitable for standardization

4 45Age >= Operand OPERATOR The GreEd LHS (Criterion) Structure Rule Criterion structure similar to LISP syntax and First Order Predicate Expressions Age >= 45 >=(Age, 45) Expressed in a LISP-like Syntax As commonly expressed Represented as a Tree

5 LISP like structure allows: A tree like structure  Each branch is an operator/function which can be: Simple mathematical operation Boolean operation Complex function  A branch may have other branches or leaves  Each leaf is an operand (atom) which can be: Common data element or Variable A possible/permissible value for a CDE A constant/literal A common syntax for Operators & Functions 45Age >= Operand OPERATOR Age >= 45 >=(Age, 45) Expressed in a LISP-like Syntax As commonly expressed Represented as a Tree

6 AND( >=(Age, 45), OR( =(Polydipsia, true), >(FBS, 120), =(Race, Indian) ) ) (Age >= 45) AND ((Polydipsia = true) OR (FBS > 120) OR (Race = Indian)) Expressed in a LISP-like Syntax 45Age >= = truePolydipsiaFBS120 > RaceIndian = OR AND LHS LHS of A Rule

7 45Age >= = truePolydipsiaFBS120 > RaceIndian = OR AND LHS Adding the RHS makes it a Complete Rule = trueDiabetes Suspicion RHS Rule (Age >= 45) AND ((Polydipsia = true) OR (FBS > 120) OR (Race = Indian)) AND( >=(Age, 45), OR( =(Polydipsia, true), >(FBS, 120), =(Race, Indian) ) ) Diabetes Suspicion = trueThen ->Assign true to Diabetes Suspicion Expressed in a LISP-like Syntax

8 45Age >= = truePolydipsiaFBS120 > RaceIndian = OR AND LHS The Data Elements Can Be Standardized = trueDiabetes Suspicion RHS Rule ISO/IEC 11179 Data Elements

9 ISO/IEC 11179Standard Specifies standard structure for Common Data Elements (CDEs) and CDE Repositories Each part of a data element can be linked with a concept in a vocabulary/ontology, allowing the semantics also to be standardized Each data element can be part of an information model specified in UML Shows a possible way out of the ‘curly braces’ problem A cornerstone of interoperability in the caBIG program of NCI (caBIG has developed an open access, shared, data element repository – caDSR)caBIG caDSR A standard that Medical Informatics ignored – Deserves a closer look

10 Data Element Name Object ClassProperty Value Domain Representation Permitted Values Value Item 1 Value Item 2 Value Item 3 Value Item n Data Type Unit Definition ID Other Attribute 1 Other Attribute 2 Other Attribute n Qualifier 1 Qualifier 2 Qualifier n Qualifier 1 Qualifier 2 Qualifier n Qualifier 1 Qualifier 2 Qualifier n ISO/IEC 11179Data Element

11 Examples

12 = 18 Age >= = true More than 1 outpatient visits with ICD9 = 250.x true = = OR AND Age appropriate Candidate suitable Data suggests diabetes 1 or more admissions with ICD9 = 250.x 1 or more pharmacy claims with diabetes therapeutic class Not enrolled false Enrolled Diabetes care provider available true Has Primary Care Physician = OR true More than once seen by Endocrinologist (s) in 2 years = HFHS Diabetes Example

13 x / 3 + 2 Diastolic Systolic Mean Arterial Pressure = Example of Calculation: Mean Arterial Pressure (MAP) ((2 x Diastolic) + Systolic) / 3)

14 Before the Demo… A caveat: Still in Development A word about the Input for GreEd: Context What is a GreEd Context?  A collection of Inputs and Outputs (as data elements) for which the rules are to be created  Each context has enough information for GreEd to allow creating rules

15 Example: “Symptoms of Diabetes” Context A Context Symptoms of Diabetes OutputInputs Data Elements Polydipsia True False Unexplained Weight Loss True False Polyuria True False Symptoms of Diabetes True False

16 Example: “Symptoms of Diabetes” Rule If Polydipsia = True AND Polyuria = True AND Unexplained Weight Loss = True  Symptoms of Diabetes = True

17 HgbA1c Rule HgbA1c Rule 1 If Months since HgbA1c >= 6  Overdue for HgbA1c HgbA1c Rule 2 If Months since HgbA1c <= 6 AND Months since HgbA1c > 5  Almost due for HgbA1c HgbA1c Rule 3 If Months since HgbA1c <= 5 AND Months since HgbA1c > 3 AND HgbA1c > 7 %  HgbA1c is high and overdue for HgbA1c HgbA1c Rule 4 If Months since HgbA1c < 3 AND HgbA1c > 7 %  HgbA1c is done within 3 months but is high

18 GreEd Syntax as XML (simplified) patient months_since_HgbA1c 3 patient months_since_HgbA1c 5 patient HgbA1c 7 eligibility status true ArdenML - Level 4 Encoding (Matt Sailors) Level 4 encoding structures Arden Syntax down to the level of operators and operands. Operators Operands

19 Diabetic Foot Screening Rule Foot Exam Rule If Double Amputee = false AND Months since Foot Complete Exam > 12 OR Months since Foot Pulses Exam > 12 OR Months since Foot Sensation Exam > 12 OR Months since Foot Visual Exam > 12  No diabetic foot exam in past year

20 Literals/Values Operators/Functions Data Elements

21 Class Diagram for Rule ( Simplified ) Each rule has a LHS and RHS Each LHS is an expression Each expression consists of an operator and more than one expression units, which may be expressions or CDE values pair. Each Value is one of the values permitted for the CDE. Value is one of the possible or permissible values

22 Advantages of the GreEd Approach Human and Machine Interpretable Scalable, Hierarchical Representation Reusable Criteria Editability Eliminate the need for Expert-Engineer- Developer collaboration cycles

23 Advantages of the GreEd Approach Standardization - The structure allows translating into different formats.  Examples: Arden Syntax GELLO RuleML Programming language code Morningside Syntax?

24 The GreEd syntax as Standard RuleML own person object buy person merchant object keep person object Imp = Implies = Rule Head = RHS of Rule Body = LHS of Rule Rel = Relation = Function/Operator

25 Advantages of the GreEd Approach Semantic Organization: Use of ISO/IEC 11179 standard based data elements makes possible:  Dynamic Semantic Organization of Rules Examples:  Grouped by clinical subject areas like Neurology, Ophthalmology, Gastroenterology etc.  Grouped by clinical categories, e.g., symptoms, signs, lab results etc.  Semantic Searches Example Queries:  Give me all the rules that: Conclude presence of diabetes Determine patient eligibility = true Use weight loss as an antecedent Utilize ‘disease = papillary serous adenocarcinoma of ovary’ and ‘duration of disease’ as facts Utilize Eye conditions (returns rules that use diabetic retinopathy, cataract, corneal ulcer etc.)

26 Advantages of the GreEd Approach CDE based expressions will facilitate:  Maintenance – any change in a CDE can be quickly recognized and the criteria/rules can be modified and vice versa  Automation Examples: Alerts from the applications in which CDEs are used to automatically detect and grade adverse events Automatically Generated Processes and Forms to lead the user to the Inference  Natural language translation of rules

27 Future Plans: Full Use of ISO/IEC 11179 data elements for conditions and inferences, including accessing repositories like caDSR Semantic organization and search capabilities Completeness checks on rules Semantic aids and constraints to create rules Rule repository related features New operators like “n of m” Extensibility  New logical or math operations can be added  New Languages plug ins

28 Menu Bar Main Toolbar + main information about KC / Context etc Rule Panel Toolbar Rule Tree Toolbar Info Panel Main (editing) Panel Code Panel Editing panel ToolbarOperators/Functions palette ArdenJavaRuleMLUser Contains Toggle button Other 1 Contains Toggle button MaintainTriggerLogicOther 2 Alerts Zone (2 lines of text)Status Zone (2 lines of text)

29 GRE CDEs Rules Repository Translator Rule - Format A ________ __ -_____ ____ _______ _____ _____ ____ ___ ___ ____ Rule - Format A ________ __ -_____ ____ _______ _____ _____ ____ ___ ___ ____ Rule - Format B ________ __ -_____ ____ _______ _____ _____ ____ ___ ___ ____ Rule - Format B ________ __ -_____ ____ _______ _____ _____ ____ ___ ___ ____ ISO/IEC 11179 based CDE Repository GreEd Architecture and Components GreEd Context OutputInputs Menu Bar Main Toolbar + main information about KC / Context etc Rule Panel Toolbar Rule Tree Toolbar Main (editing) Panel Editing panel ToolbarOperators/Functions palette ArdenJavaRuleMLUser Other 1MaintainTriggerLogicOther 2 Alerts Zone (2 lines of text)Status Zone (2 lines of text)

30 Proteus Environment Accepts KCs with Standard DEs (ISO/IEC 11179) Returns Proteus Inferences Proteus GreEd Inference Tool BeanShell Open source tool Allows treating Java as a scripting language GreEd Rule Engine - Current Environment

31 Accepts Generic Data Elements Returns result as Generic Data Elements GreEd Environment GreEd Rule Engine Accepts KCs with Standard DEs (ISO/IEC 11179) Returns Proteus Inferences Proteus GreEd Inference Tool Proteus Environment BeanShell Open source tool Allows treating Java as a scripting language GreEd Rule Engine - MI Modification

32 Thanks

33 Additional Slides (Examples, Screenshots)

34 CDEs Rules Engine Rules Repository Clinical System Standard Interface Extended Interface Access Reference Rules System Rule Editing Environment ISO/IEC 11179 based CDE Repository

35 All Rules for the Context Selected Rule as a Tree (note organization by operators) Description Operators/functions Available to Drop in Rule Criteria Editing Panel Displaying the Selected Rule Output Panel Displaying the Selected Rule as Java Code Tabs for Other Views of the Selected Rule GreEd Interface Context Information

36 New GUI framework (very early)

37 Common Data Elements That form the LHS of the Rule Diarrhea The Common Data Element For the RHS of the Rule Possible Values of RHS data element

38

39 Increase of 4 - 6 stools per day over baseline IV fluids indicated <24hrs moderate increase in ostomy output compared to baseline not interfering with ADL Increase of 4 - 6 stools per day over baseline IV fluids indicated <24hrs moderate increase in ostomy output compared to baseline not interfering with ADL Diarrhea AE Grade 2


Download ppt "GreEd and its Rules Representation Hemant Shah M.D., M. Surg. Sr. Research Informatician, CSRI Henry Ford Health System (GreEd and its."

Similar presentations


Ads by Google