From the Bench All the Way to Bedside Clinical Decision Support: The Role of Semantic Technologies in a Knowledge Manag

Slide1 l.jpg
1 / 14
0
0
914 days ago, 280 views
PowerPoint PPT Presentation

Presentation Transcript

Slide 1

From the Bench All the Way to Bedside Clinical Decision Support: The Role of Semantic Technologies in a Knowledge Management Infrastructure for Translational Medicine Tonya Hongsermeier, MD, MBA Corporate Manager, Clinical Knowledge Management and Decision Support Clinical Informatics R&D Partners Healthcare System

Slide 2

Current State of Translational Medicine 17 year advancement selection bend from disclosure into acknowledged measures of practice Even if a standard is acknowledged, patients have a 50:50 possibility of getting proper care, a 5-10% likelihood of bringing about a preventable, anticipatable antagonistic occasion The market is recoiling from human services swelling, new diagnostics and therapeutics will discover expanding resistance for repayment

Slide 3

The Volume and Velocity of Knowledge Processing Required for Care Delivery Medical writing multiplying like clockwork Doubles like clockwork for AIDS mind 2 Million truths expected to practice Genomics, Personalized Medicine will build the issue exponentially Typical medication arrange today with choice bolster represents, best case scenario, Age, Weight, Height, Labs, Other Active Meds, Allergies, Diagnoses Today, there are 3000+ atomic analytic tests available, normal HIT frameworks can't bolster complex, multi-various leveled anchoring clinical choice support Covell DG, Uman GC, Manning PR. Ann Intern Med. 1985 Oct;103(4):596-9

Slide 4

Today's Health IS Vendor Knowledge Management Capabilities: Knowledge "hardwired" or organized in exclusive modes into applications, not effortlessly upgraded or shared Little or no institutionalization of HIT sellers on SNOMED, no mutual interface wordings for perception catch, no standard request indexes Most EMRs have an errand meddling way to deal with choice support, imperfect convenience Knowledge-building instruments commonly alter into exchange, no support for provenance, forming, life-cycle, engendering, revelation or upkeep Consequently, clinical frameworks usage are under-resourced with satisfactory learning to meet momentum work process and quality needs Labor of changing over information into Clinical Decision Support is boundlessly thought little of Doesn't look good for customized pharmaceutical

Slide 5

Knowledge Management and Decision Support Intersection Points in Translational Medicine Diagnostic Test requesting and documentation direction Patient Encounter (coordinate care or clinical trial) Clinical Trials Referral Personalized Medicine Decision Support Knowledge Repository Structured Test Result Interpretations Tissue-bank Therapeutic Intervention Ordering and documentation direction Knowledge Discovery, Acquisition & Management Structured Research Annotations Bench R&D Integrated Genotypic Phenotypic Databases Clinical Trials 1-4 Pharmacovigilance

Slide 6

Composite Decision Support Application: Diabetes Management Guided Data Interpretation Guided Observation Capture Guided Ordering

Slide 7

What human services needs from Semantic Web Technologies… Reduce the cost, span, danger of medication discovery Data reconciliation, Knowledge incorporation, Visualization Knowledge representation ��  New Knowledge Discovery Reduce the cost/term/danger of clinical trial administration Patient distinguishing proof and referral Trial outline (ie to catch better wellbeing reconnaissance) Data quality and clinical results estimation Post-advertise observation Reduce the cost/length/obligation of information obtaining and support for clinical choice support and clinical execution estimation Knowledge provenance and representation Conversion of "disclosure calculations" into "clinical practice calculations" Event-driven change administration and spread of progress

Slide 8

KM for Translational Medicine: Functional/Business Architecture R&D DIAGNOSTIC Svs LABs CLINICAL TRIALS CLINICAL CARE PORTALS LIMS EHR APPLICATIONS ASSAYS ANNOTATIONS DIAGNOSTIC TEST RESULTS ASSAY INTERPRETATIONS ORDERS AND OBSERVATIONS KNOWLEDGE and WORKFLOW DELIVERY SERVICES FOR ALL PORTAL ROLES Genotypic Phenotypic DATA REPOSITORIES AND SERVICES State Management Services Semantic Inferencing And Agent-based Discovery Services KNOWLEDGE ACQUISITION AND DISCOVERY SERVICES Knowledge Asset Management and Repository Services Workflow Support Services Data Analysts and Collaborative Knowledge Engineers Collaboration Support Services Logic/Policy Domains Meta Knowledge Domains Data Domains NCI Metathesaurus, UMLS, SNOMED CT, DxPlain, ETC other Knowledge Sources Decision Support Services INFERENCING AND VOCABULARY ENGINES

Slide 9

Example: Diabetes Epidemic, connected with stoutness Quality measures drive repayment of doctor's facilities and doctors Maintain HbA1c <7 (consume less calories, oral operators or potentially insulin) If Renal Disease and no contraindication, ought to be on ACE inhibitor or ARB If lipid issue and no contraindication, ought to be on a Statin National issue of resistance with these gauges of care ��  traded off patient life span, personal satisfaction, capacity to keep up business ��  CMS and manager budgetary hazard

Slide 10

Imagine this CDS Rule: If Renal Disease and DM and no contraindication, ought to be on ACE inhibitor or ARB Renal malady = Chronic Renal Failure Nephropathy, ceaseless renal disappointment, end-arrange renal sickness, renal inadequacy, hemodialysis, peritoneal dialysis on Problem List (SNOMED) Creatinine > 2 Calculated GFR < 50 Malb/creat proportion test > 30 Diabetes Many variations on the issue list On Insulin or oral hypoglycemic medication Contraindication to ACE inhibitor Allergy, Cough on ACE on unfriendly response rundown, or Hyperkalemia on issue list, Pregnant (20 sub tenets to characterize this state) K test result > 5

Slide 11

Composite Decision Support Application: Diabetes Management Guided Data Interpretation Guided Observation Capture Guided Ordering

Slide 12

The Maintenance and Propagation Challenge… These "perplexing" definitions must be indistinguishable in guidelines (if that is the way "acknowledgment" is taken care of), documentation layouts for organized information catch, and in reporting frameworks that drive payor repayment The rate of progress for contraindication definition today is moderate, yet clinical choice emotionally supportive networks are not keeping up… When sub-atomic diagnostics remove, this rate of progress could be "day by day" or "hourly" Further, when a patient has a sub-atomic indicative test result in the EMR that is at present of "obscure centrality" and later, with new learning, the elucidation of the previous result is "contraindication" to a medication, then this "understanding" must be redesigned to guarantee legitimate CDS working…

Slide 13

Role of Semantic Technologies… Data/Knowledge Integration and Visualization Ontology based methodologies Integration over different information sources: Genotypic/Phenotypic information from LIMS/HER Knowledge Repositories for information elucidation Clinical Decision Support Inference motors - SWRL Description rationales for "acknowledgment" - OWL Knowledge representation Etc. Information Acquisition, Maintenance and Evolution Ontology-based Definitions Management Versioning, life-cycle, engendering into "ward" protests, for example, rules, layouts orders/documentation, reporting frameworks Knowledge Provenance Reconciling information representation among various partners (parental figures, payors, execution estimation, clinical trials, R&D)

Slide 14

Market Drivers Will Make Semantic Web Technologies an Imperative for Translational Medicine Genomics: customized drug will require choice bolster models that can proactively bolster complex basic leadership – noting 1,000,000 of inquiries before run-time These frameworks will require self-versatile, machine learning methods of learning securing, absolutely human ward information obtaining won't scale Pharma will require helpful associations with HIT merchants to make speed the translational solution life-cycle

SPONSORS