The use of EHR data in quality improvement reports and clinical automatic calculators in ICU Jun 2014 Vitaly Herasevich, MD, PhD, MSs Assistant Professor of Medicine and Anesthesiology, Department of Anesthesiology, Multidisciplinary Epidemiology and Translational Research in Intensive Care (M.E.T.R.I.C.)
Disclosure 1) Mayo Clinic and I have Financial Conflict of Interest related to this research. 2) This research has been reviewed by the Mayo Clinic Conflict of Interest Review Board and is being conducted in compliance with Mayo Clinic Conflict of interest Policies 3) AWARE is patent pending (US 2010/0198622, 12/697861, PCT/US2010/022750) 4) AWARE is licensed to Ambient Clinical Analytics 5) Cloud AWARE funded by a Health Care Innovation Award (HCIA) granted to Mayo Clinic (Grant # 1C1CMS330964-01-00) from Centers for Medicare and Medicaid Services (CMS), Center for Medicare and Medicaid Innovation (CMMI) Patient Centered Cloud-based Electronic System: Ambient Warning and Response Evaluation (ProCCESs AWARE). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the Department of Health and Human Services (HHS) or any of its agencies. 2011 MFMER slide-2
Innovation Motivation
Healthcare 1920 2010
Historically It has been well documented that quality measurement has the ability to improve the quality of care delivered by providers. 2011 MFMER slide-5
Reports 1920 2010
Requirement Hospitals have been facing growing demands to participate in quality measurement for a number of purposes (e.g., accreditation and licensure). 2011 MFMER slide-7
Problem #1: What to measure? Quality of care is usually estimated: in structure, process, and outcome. The metrics describing those domains are often poorly defined and difficult to measure 2011 MFMER slide-9
Alphabetical Data Dictionary 451 pages 2011 MFMER slide-10
Problem #1 Association is not causation 2011 MFMER slide-11
Problem #2: Validity of administrative data for reports http://effectivehealthcare.ahrq.gov/ehc/products/40/359/upenn%20final%20report%20-%202005%20certs%20ce%20supplement.pdf 2011 MFMER slide-12
Problem #2: How are the AHRQ QIs structured? Definitions based on: ICD-9-CM diagnosis and procedure codes Often along with other measures (e.g., DRG, MDC, sex, age, procedure dates, admission type) Numerator = number of cases with the outcome of interest (e.g., cases with pneumonia) Denominator = population at risk (e.g., community population) Observed rate = numerator/denominator Some QIs measured as volume counts http://www.ahrq.gov/professionals/systems/hospital/qitoolkit/qitoolkit-allfiles.pdf 2011 MFMER slide-13
Problem #3: Meaningful metrics Does it change decision? Does it actionable? 2011 MFMER slide-14
Problem #3: Is it matters? The hospital where former President Bill Clinton awaits bypass surgery in the next few days has the highest death rate for the operation in New York State, according to the state's Health Department. While the death rate is quite low - fewer than 4 percent of all bypass operations - it is still nearly double the 2.18 percent overall death rate for coronary bypass operations in all 35 hospitals that perform the procedure in the state. http://www.nytimes.com/2004/09/06/health/06hosp.html?pagewanted=print&position=&_r=0
Is there are solution? - EMR may help With the current rate of growth and adoption of EHR, it present a tremendous opportunity for quality improvement projects (which is been done by manual data collection at a very large scale) This had been proven to be dissatisfactory and consumes time and human resources. 2011 MFMER slide-16
Problem 2011 MFMER slide-17
AWARE experience
AWARE - Provider built EMR enhancement Reduced cognitive load (happy clinicians) Reduced errors (happy patients) Reduced time (happy administrators) Standard Interface Novel Interface Ahmed A, Chandra S, Herasevich V, et al. The effect of two different electronic health record user interfaces on intensive care provider task load, errors of cognition, and performance. Critical Care Medicine 2011;39(7):1626-1634.
Some PROCESS AWARE components Tools for stage 3 meaningful EMR use Addresses time sensitive clinical interventions Group level population management Pertinent clinical information Resource planning, Quality improvement Resuscitation module Multipatient viewer Single patient viewer Administrative dashboard ED OR PACU ICU Floor Hand over Claim patient Task list Rounding tool (Checklist) Essential information at a glance Focused on patient problems Links provider and patients One stop communication Shared list of tasks Outside of clinical note Structured clinical assessment Generates clinical note 2011 MFMER slide-20
Technically
AWARE Administrative dashboard
Actionable real-time reports SCIP-4 glucose control metric
Are you AWARE sign posted in ICUs AWARE formal launch in ICU Critical Care Fellows 2 hour AWARE training Real-time providers feedback AWARE training mandatory to all Nurse Practitione rs Anesth esia Reside nts trained Pulmon ary Fellows trained One on one training for attendin gs Real time compliance reports become available New residents and fellows started
Main features AWARE administrative dasboard 1. No manual data collection 2. Use clinical data, not administrative 3. Validated scientifically (and technically) 4. Excellent usability and visualization 5. Actionable
Patient centered outcomes of interest Better care: Adherence to and appropriateness of processes of care Provider satisfaction Better health: Rate of ICU acquired complications, Discharge home, Hospital mortality, ICU and hospital readmission Lower cost: Resource utilization, Severity adjusted length of ICU and hospital stay Cost
Offline ICU Reports 1. Hospital Length of Stay for ICU Graduates Unadjusted 2. ICU Length of Stay Unadjusted 3. ICU Length of Stay Adjusted 4. ICU Readmission Rate 5. ICU Admissions 6. ICU Admission Source and Service 7. Duration of Mechanical Ventilation 8. ICU Mortality Rate Unadjusted 9. Hospital Mortality Rate Adjusted 10. ICU Admissions for Low-Risk Monitoring 11. ICU Census - Hourly Utilization Monthly reports Ad-hock reports Customized reports
Resources start here: 1. AHRQ - http://effectivehealthcare.ahrq.gov/ 2. The Joint Commission - http://www.jointcommission.org/performance_meas urement.aspx 3. CMS - https://www.cms.gov/research-statistics-data- and-systems/research-statistics-data-and- Systems.html Registries for Evaluating Patient Outcomes: A User's Guide: 2nd Edition - http://effectivehealthcare.ahrq.gov/index.cfm/search-for-guides-reviews-and-reports/?productid=531&pageaction=displayproduct Outcome Measure Framework (OMF) Design Document - http://effectivehealthcare.ahrq.gov/search-forguides-reviews-and-reports/?pageaction=displayproduct&productid=1916
Chest. 2012;142(1):14. doi:10.1378/chest.142.1.14
Ognjen Gajic, MD Vitaly Herasevich, MD, PhD Brian Pickering, MD gajic.ognjen@mayo.edu herasevich.vitaly@mayo.edu pickering.brian@mayo.edu Lacey Hart CMS grant program manager hart.lacey@mayo.edu Programming: Ing Tiong Lead developer Troy Neumann John Dyke Vitali Fedosov, MD, PhD Google Clinical informatics Mayo This message is part of Creating the Future