Presentation on theme: "Active Clinical Decision Support in a RHIO. Introduction The Clinical Document Architecture has emerged as a means of making systems interoperable. Clinical."— Presentation transcript:
Active Clinical Decision Support in a RHIO
Introduction The Clinical Document Architecture has emerged as a means of making systems interoperable. Clinical data can cross barriers. We are approaching an era of Computable Semantic Interoperability. Decision Support works when complex information is available. It works for a community when that data is available across systems so that patients can be treated with quality wherever they are seen. Active decision support provides guidance and recommendations at the point of care. In a RHIO, decision support will support evidence based care using standards to obtain and manipulate information.
IHE … Industrializing Healthcare Clinical Workflow Structured Data Interoperability Security Privacy Decision Support
What is Active Decision Support? Decision support: any means of helping get the right thing done Passive Decision Support: documents or systems that can be searched or browsed to get answers Active Decision Support: can reason with its knowledge and likely can communicate or act on its recommendations
CDA Enables Active Decision Support 1.Active Decision Support depends on access to clinical and administrative data about patients. 2.CDA documents carry information that can be understood across systems. 3.So, Decision Support is enabled by CDA. Knowledge systems can operate in RHIOs, and as services in cooperation with clinical data systems. Computable Semantic Interoperability - Charlie Mead, 06
A collaborative project to develop a universal framework for sharing health knowledge in the form of computable clinical practice guidelines
Project Overview An R&D consortium to develop the technology infrastructure to enable computable clinical guidelines, that will be shareable and interoperable across multiple clinical information system platforms Scope: 5 year, $18 M, multi-site, collaborative project Partners in the project are: GE Healthcare (formerly IDX) Apelon, Inc. Intermountain Healthcare (IHC) Mayo Clinic Stanford Medical Informatics (SMI) University of Nebraska Medical Center (UNMC) Funded in part by: NIST Advanced Technology Program UNMC Mayo SMI Apelon GE Healthcare IHC Cooperative Agreement Number 70NANB1H3049 Standards-based S harable A ctive G uideline E nvironment
An R&D consortium to develop the technology infrastructure to enable computable clinical guidelines, that will be shareable and interoperable across multiple clinical information system platforms. A 5-year, industry-academic research collaboration Led by IDX Systems, now GE Healthcare In partnership with: –Apelon, Inc. –Intermountain Healthcare –Mayo Clinic –Stanford Medical Informatics –University of Nebraska Medical Center The SAGE Project
Guidelines are Active What If.... Guideline content became active, offering targeted, relevant guidance at the point of care? Patients were evaluated against proven guidelines -- automatically? Key data, care rationale and guidance were presented at critical decision points -- automatically?
A technology infrastructure that supports sharable, computable clinical practice guidelines -- augmenting clinical knowledge processing at the point of care. With SAGE Health experts can author and encode evidence- based clinical guidelines in a standard computable format. Organizations throughout the world can easily deploy those guidelines using any conforming clinical information system. The SAGE Project Vision
SAGE in a RHIO Environment Guidelines could execute at the RHIO level. Guideline execution could obtain patient EMR data from a central or distributed repository. Real-time, patient- specific recommendations could be provided via functions of the local CIS. CDA documents are the basis for exchanging information. Central Repository Model EMR Guideline File(s) SAGE Guidelin e Engine
Think of SAGE as guidelines good idea! tapping busy clinicians on the shoulder at just the right time. Active Guideline Environment
Gentle SAGE Recommendations Guideline recommendations integrated into a nurse care flowsheet View suggested orders Process suggested orders Real time access to reference information Shows history, and future plans
Order Sets as SAGE Recommendations HL7 Standard Order Set Open Here SAGE adds patient specific comments to orders, and chooses preferred orders.
How Classic SAGE Technology Works SAGE reads and executes an encoded guideline using standard terminology. It communicates with CIS via a Virtual Medical Record standard interfaces. SAGE detects events in the clinical workflow. Queries patient data from the electronic medical record. SAGE executes guideline logic based on patient specific data. Real-time, patient-specific recommendations are expressed by the local CIS. Your Clinical Information System Guideline File(s) SAGE Guidelin e Engine PAS Orders More… Labs Events EMR Data Queries Actions
RHIOs: Where is the patient record? EMR Central EMR (with distributed access) (cf. PeaceHealth) Central Repository (copy of local EMRs) (cf. INPC, UK Spine) Distributed EMR (no central EMR) (cf. Santa Barbara) EMR
SAGE reads and executes an encoded guidelines using standard terminology. It communicates with users and stores via CDA interfaces. SAGE responds to events or requests from clinical systems. Queries patient data from the RHIO or requester. The data are returned in CDA documents. SAGE executes guideline logic based on patient specific data. Patient-specific recommendations are expressed through CDA. How CDA SAGE Technology Works SAGE Guidelin e Engine Guideline File(s) CDA RHIO store CDA
Clinical Document Architecture CDA defines a document structure that contains medical information. CDA docs (XML) cross the wire. In CDA v2, coded admin and clinical data may be present for use by decision support systems.
XML Body: two types of content Human readable (usually HTML) - required Machine readable which can drive automated processes including decision support - optional except when doing decision support
Major Components Thanks to Bob Dolin, MD Kaiser Permanente Major Comp- onents of a CDA Documen t DOCUMENTDOCUMENT BODYBODY Header SECTIONSSECTIONS Narrative Block ENTRIESENTRIES External References
21 Allergies and Adverse Reactions Penicillin - Hives Aspirin - Wheezing Codeine - Itching and nausea Example CDA v2 for an Allergy List CDA, Release Two Thanks to Bob Dolin, MD Kaiser Permanente
Two Emerging Standards for Clinical Summaries CCR Sponsors – ASTM, AAFP, MMS,… Goal – create an electronic clinical snapshot to support inter-operability Format – XML Summary – physician driven standard with early traction due to Massachusetts activity CDA Sponsor – HL7 Goal – document standard that specifies the structure and semantics of clinical documents for the purpose of exchange Format – XML Summary – vendor driven standard that is focusing on a medical summary based on CRS
1st Scenario: Consultation on Request Small medical office, part of RHIO network Patient goes to the office. Patient has some previous history of hypertension. MD requests a consultation on medications for hypertension management. Office VERY SIMPLE!
Small Practice in a RHIO 40 y.o. seen in clinic: BP checked, Hypertension already known
SAGE reasons Sources SAGE Guideline Engine Central EMR CDA SAGE analyzes data Central DB contains several visit histories from multiple institutions 1.Is ACE Inhibitor at max dose? 2.Any contraindications to Ca Channel Blocker? 3.Is Average Systolic BP over last 5 measurements > 150 mmHg 4.etc. Sources CDA Office CDA
Recommendations Delivered BP Not under Control. Consider one of the following: 1) increase dose of lisinopril to 20mg qd 2) add felodipine 3) add thiazide diuretic, monitor K+ 4) add atenolol Recommends SAGE replies:
Why is SAGE not just an Expert System? Recommends Context (a series of events) State (enrollment) Sharable (across institutions) Active (influence on care)
Where are the data? SAGE uses –CDA data submitted with consultation request, AND –Stored centrally in RHIO for this patient Central store is CDA XML documents –Past history, Problem list, Allergies, Current Meds, History of Meds, Vital Signs, Laboratory work, etc.
For Example, Current Medications include Digoxin 0.125mg, 1 PO qDay, #30, 5 refills. This SNOMED-CT Coded entry is thus available for for SAGE to use in reasoning to make recommendations.
2 nd Scenario: SAGE helps out at the Cancer Clinic RHIO/SAGE is sent a patient list before the clinic opens on Friday morning. List is actually 47 CDA docs with up to date labs and findings for those patients who will appear in clinic that day. 05:30 Patient list sent to SAGE SAGE Guideline Engine CDA Central EMR
Other Systems SAGE assesses each patient against protocol Decision logic possibly requires additional historical, or missing patient data SAGE can look for trends, specific alert levels, recent posted warnings, … SAGE executes decision logic SAGE Guideline Engine Central RHIO EMR Other Systems
SAGE Guideline Provides Advice for Each Patient When each patient is first seen by a clinician, that person is notified of any recommendations. The clinician may act on some of those recommendations directly. Each recommendation comes with literature and logic references. SAGE publishes recommendations SAGE Guideline Engine John Abelson, # F5, DOB: has a very low platelet count (5240). Other Labs: Na 134 K 14 WBC 10,100 Recommend 1.D/C Heparin 2.Reduce Met to 3.4g qd 3.Repeat count in 24 hr
Recommendations may be comprehensive SAGE may suggest –new diagnoses –new interventions –changes in schedules –adjustments in current treatments –additional studies –all with explanations and literature references. MRN: 60946T3NAME: Frederick T. Withers Recent BP: /86 Enter Todays BP: Goal: SBP < 135, DBP < 95 [diabetes, chf, renal insuffiency] Stage 1 Hypertension. BP out of control. Systolic trend upwards. Patient may benefit from 1 or more additional medication(s). Recommendations: Consider one of: ACE lisinopril 10mg qd ARB spironolactone 25mg qd BB atenolol 25mg qd