Decision support systems aid in the useprocess of medications. Automatedhuman decision making, especially decision making that relies on expertise. Reasoning with rules from these combined sourcesis possible if the rules are first mapped to RIF. Here are two specific examplesan important part of such synergistic effects.this scenario discusses the fictitiousexpert systems AutoDoc and MEDIC. In the interest of readability and brevity, the information anddecision making. For complex decision support systems, it is expected that rules presented in the following scenario may not precisely capture the current state of medical knowledge and best practices in this field, but maywill be somewhat simplified. Originally Bob's diabetes was controlled through diet and moderate exercise. In time, however, Bob's blood glucose level began to rise, even under this regimen. Due to Bob's elevated HbA1c level (which indicates one's average blood sugar level over the last several months), Dr. Rosen prescribed oral medication for Bob. He was forced to change Bob's medicationfurnished by a number of times over the coursevariety of a year. He first prescribed Precose, an oral alpha-glucosidase inhibitor, but had to discontinue this medication due to undesired side effects. He then prescribed several sulfonylurea drugs, Micronasedifferent sources, including ontologies, knowledge bases, and Glucotrol,other expert systems. This use case illustrates how RIF makes it possible to no avail. Bob's lab results still indicated an elevated HbA1c level.merge rule sets from diverse sources in diverse formats into one rule-based system, thereby enabling inferences that might otherwise have remained implicit.
Medical decision support systems, such as the following ruleones discussed below, might use rules from thepharmaceutical knowledge bases, laboratory knowledge base suggests that Bob's treatment at that time was not effective: Ifbases, patient databases, and medical ontologies. For example, a Type II diabetes patient's current levellarge amount of HbA1c is high, then the patient's current treatmentinformation on therapeutic medications (drug taxonomies, indications, contraindications, and clearance times) and diseases (disease taxonomies, etiologies, and symptoms) is considered to be ineffective. Representationcontained in RIF BLD Presentation Syntax using relations and an event calculus axiomatization: Document( Prefix(pred http://www.w3.org/2007/rif-builtin-predicate# ) Prefix(func http://www.w3.org/2007/rif-builtin-function# ) Prefix(ex http://example.org/example#) Group ( Forall ?Patient ?Treatment ?Level ?T ( ex:holdsAt(ex:ineffective(?Patient ?Treatment) ?T) :- ex:holdsAt(ex:hasDisease(?Patient "diabetesTypeII") ?T) ex:holdsAt(ex:elevated(levelOf(?Patient "hbA1c" ?Level)) ?T) ex:holdsAt(ex:treatmentPlan(?Treatment ?Patient) ?T) ) ) ) Note, the example requires the formalization of changeable states which can be represented by an event calculus axiomatization. KS86 ] The EC axiomsexisting ontologies such as SNOMED Clinical Terms®. Rules can thenbe represented using RIF BLD.used to deal with this problem, Dr. Rosen wasexpress therapeutic recommendations, to formulate queries about relevant prescriptions for a patient, and to prescribe Glucophage (metformin, one ofassess the biguanides) 850 mg, 3 timeseffectiveness of a day, when as usual, he double checked his prescription with the AutoDoc system. The system, based ontreatment.
The following guidelines from the pharmaceutical knowledge base , informed Dr. Rosen that he should have prescribed an oral bitherapy (two medications, each of which controls blood sugar levels) instead of a monotherapy. If an oral monotherapy at recommended doses of a sulfonylurea or biguanide, combined with lifestyle changes, is ineffective, thenscenario illustrates how rule-interchange would be used in various medical decision support systems to support the monotherapy shouldfollowing functionalities:
- Improving situation assessment, e.g., determining when a patient needs to be
replaced by an oral bitherapy. Basedput on the recommendation from AutoDoc , Dr. Rosen switched Bob's prescription to Glucophage and Avandia (rosiglitazone, onemedication, or have his medication switched.
- Prescribing a course of
the thiazolidinediones). Bob recently sufferedaction, e.g., determining which drug is best for a concussion and has become increasingly forgetful. He went to seepatient in a neurologist, Dr. Cervello, who prescribedparticular circumstance.
- Improving event planning, e.g., determining whether a
contrast MRI (Magnetic Resonance Imaging). When asked about current medication, Bob told Dr. Cervellopatient can be scheduled for a procedure given the medication that he was taking Glucotrolis currently taking.
Bob, 62 years old and reasonably healthy, has been going to his internist, Dr. Rosen, for several years for control of his diabetes, forgetting that he hadType II diabetes. Dr. Rosen has been switched to Glucophage. This was potentially problematic, since Glucophage should not be taken close tousing the administration of a contrast injection. Fortunately,AutoDoc system to help him decide when Bob wentto the labswitch to schedule his MRI, the medical receptionist pulled up MEDIC (Medical Eventmedications and Drug Interaction Consultant), the hospital's new automated system,which checks for incompatible medical events and/ordrugs (e.g., liposuction scheduled during pregnancy, blood thinners prescribed before surgery, etc.). MEDICto prescribe. The AutoDoc system uses a variety oftwo sources in its reasoning, including: the pharmaceutical knowledge base, described above the patient databases, which gives the patient record, including the medications a patient is currently taking the hospital medical event protocolwhen making its recommendations: a laboratory knowledge base, which details the protocol usedbase giving particular results for different medical procedures In this case, MEDIC uses all three sources,patients and pulls up the following information: Metformin is contraindicated with contrast dye. Metformin is the generic formspecifying when these results are out of Glucophage. Bob is taking Glucophage.normal range, and a pharmaceutical knowledge base giving guidelines for the contrast MRI requires as oneuse of its steps injecting the patientmedications. Automated reasoning with contrast dye. MEDIC therefore determines that Bob should not be taking the contrast MRI at this time. For MEDIC to work, therules from these differentcombined sources must beis possible if the rules are first mapped to a unified interchange format. 4.7 Interchanging Rule Extensions to OWL RulesRIF. Here are often used in conjunction with other declarative knowledge representation formalisms,two specific examples of such as ontology languages (e.g. RDFsynergistic effects.
This scenario discusses the fictitious expert systems AutoDoc and OWL),MEDIC. In order to provide greater expressive power than is provided by either formalism alone. Ontology languages, for example, typically provide a richer language for describing classes (unary predicates). Rules, onthe other hand, typically provide a richer language for describing dependencies between properties (binary predicates),interest of readability and brevity, the information and may also support higher-arity predicates. Rich domain models combining bothrules presented in the following scenario may not precisely capture the current state of medical knowledge and ontologies are often neededbest practices in domains such as medicine, biology, e-Sciencethis field, but may be somewhat simplified.
Originally Bob's diabetes was controlled through diet and Web services.moderate exercise. In such domains,time, however, Bob's blood glucose level began to rise, even under this regimen. Due to Bob's elevated HbA1c level (which indicates one's average blood sugar level over the last several actors and/or agents are involved that havemonths), Dr. Rosen prescribed oral medication for Bob. He was forced to interchangechange Bob's medication a number of times over the data, ontologies,course of a year. He first prescribed Precose, an oral alpha-glucosidase inhibitor, but had to discontinue this medication due to undesired side effects. He then prescribed several sulfonylurea drugs, Micronase and rules that they work with.Glucotrol, to no avail. Bob's lab results still indicated an example iselevated HbA1c level. The use of suchfollowing rule from the laboratory knowledge base suggests that Bob's treatment at that time was not effective:
If a domain modelType II diabetes patient's current level of HbA1c is high, then the patient's current treatment is considered to be ineffective.
Representation in RIF BLD Presentation Syntax using relations and an application that aims at assistingevent calculus axiomatization:
Document(
Prefix(pred http://www.w3.org/2007/rif-builtin-predicate#)
Prefix(func http://www.w3.org/2007/rif-builtin-function#)
Prefix(ex http://example.org/example#)
Group
(
Forall ?Patient ?Treatment ?Level ?T (
ex:holdsAt(ex:ineffective(?Patient ?Treatment) ?T) :-
ex:holdsAt(ex:hasDisease(?Patient "diabetesTypeII") ?T)
ex:holdsAt(ex:elevated(levelOf(?Patient "hbA1c" ?Level)) ?T)
ex:holdsAt(ex:treatmentPlan(?Treatment ?Patient) ?T)
)
)
)
Note, the labelingexample requires the formalization of brain cortex structures in MRI images. In this case,changeable states which can be represented by an OWL ontology is used to capture knowledge aboutevent calculus axiomatization. KS86] The most important brain cortex anatomical structures, and a rule base is usedEC axioms can then be represented using RIF BLD.
To capture knowledgedeal with this problem, Dr. Rosen was about mereological and spatial dependencies between properties. For example, a rule is usedto expressprescribe Glucophage (metformin, one of the dependency betweenbiguanides) 850 mg, 3 times a day, when as usual, he double checked his prescription with the ontology properties isMAEConnectedTo and isMAEBoundedBy, in particular (a simplified form of)AutoDoc system. The system, based on the following guidelines from the pharmaceutical knowledge base, informed Dr. Rosen that two Material Anatomical Entities havinghe should have prescribed an oral bitherapy (two medications, each of which controls blood sugar levels) instead of a shared boundary are connected:monotherapy.
If MAE X is bounded by Z and MAE Yan oral monotherapy at recommended doses of a sulfonylurea or biguanide, combined with lifestyle changes, is also bounded by Zineffective, then X is connected to Y. Benefits of interchange via RIF includethe ability to collaboratively develop and share valuable knowledge,monotherapy should be replaced by an oral bitherapy.
Based on the ability to integrate anatomical images, possiblyrecommendation from distributed image sources, and the abilityAutoDoc, Dr. Rosen switched Bob's prescription to use large-scale federated systems for statistical analysis of brain images of major brain pathologies. 4.8 Vocabulary Mapping for Data Integration This use case concerns the integrationGlucophage and Avandia (rosiglitazone, one of information from multiple data sources.the Semantic Web providesthiazolidinediones).
Bob recently suffered a common data representationconcussion and query language, which greatly simplifies accesshas become increasingly forgetful. He went to see a neurologist, Dr. Cervello, who prescribed a contrast MRI (Magnetic Resonance Imaging). When asked about current medication, Bob told Dr. Cervello that he was taking Glucotrol to diverse sources but does not directly address the problemcontrol his diabetes, forgetting that independent data sources may have rather divergent information models. Rules are an effective wayhe had been switched to express mappings between such information models. However, rules locked within local proprietary systems cannotGlucophage. This was potentially problematic, since Glucophage should not be reused. Withtaken close to the administration of a common rule representation, such mappings can be published acrosscontrast injection.
Fortunately, when Bob went to the Semantic Web, enabling an enterprise or communitylab to progressively buildschedule his MRI, the medical receptionist pulled up MEDIC (Medical Event and Drug Interaction Consultant), the hospital's new automated system, which checks for incompatible medical events and/or drugs (e.g., liposuction scheduled during pregnancy, blood thinners prescribed before surgery, etc.).
MEDIC uses a rich networkvariety of mappings unifying the information models. Information mapping and integration problems like this arisesources in many diverse domainsits reasoning, including:
- the pharmaceutical knowledge base, described above
- the patient databases, which gives the patient record, including
health care, travel planning, IT managementthe medications a patient is currently taking
- the hospital medical event protocol knowledge base, which details the protocol used for different medical procedures
In this case, MEDIC uses all three sources and customer information management.pulls up the following scenario comes frominformation:
- Metformin is contraindicated with contrast dye.
- Metformin is the
worldgeneric form of IT systems management. Vlad has been givenGlucophage.
- Bob is taking Glucophage.
- The contrast MRI requires as one of its steps injecting the patient with contrast dye.
MEDIC therefore determines that Bob should not be taking the job of analyzing how exposed his division's business processes arecontrast MRI at this time.
For MEDIC to changes in their IT maintenance contracts. He has threework, the rules from these different sources of informationmust be mapped to combine: a report on application services and associated servers, databases and networks (from the IT department)a maintenance contracts database (fromunified interchange format.
Supported by RIF-PRD
The finance department) a registry indicating which business processesuse which IT services (fromcase requires the business planning group) Eachformalization of these sources is in a different form butchangeable states (fluents) which can be mapped into RDF to simplify access.represented by e.g. an event calculus axiomatization [KS86]. However, they all have different information models.to formulate the classical event calculus as a set of Horn clause rules so that it reportcould be run as a Prolog program, negation as failure is too fine-grained: it talks about routersneeded, which is not supported by RIF-BLD or Core.
The use case can be represented in RIF-PRD which supports changeable states (modifications) and interface cards whereas Vlad only needsassertions and retractions of knowledge.
