Docstoc

Information systems in Health Care_ Clinical

Document Sample
Information systems in Health Care_ Clinical Powered By Docstoc
					INFORMATION SYSTEMS IN HEALTH CARE:
Clinical Decision
Support Systems




         Matt Simko, EMT-B
What is a Clinical Decision Support
System (CDSS)?
   A type of expert system, often connected with an
    electronic medical record

   “Provide[s] clinicians, staff, patients, and other
    individuals with knowledge and person-specific
    information, intelligently filtered and presented at
    appropriate times, to enhance health and health care”1

   An avenue for better health care delivery-but is not
    itself a health care process

1BernerES. (2009). Clinical decision support systems: State of the art (AHRQ Publication No. 09-0069-EF).
      Rockville, MD: Agency for Healthcare Research and Quality.
What are some functions of CDSSs?2

   Alerts and reminders
   Diagnostic assistance
      DXplain           (1984: Massachusetts General Hospital3)
   Therapy critiquing and planning
   Prescribing decision support
   Information retrieval
   Image recognition and interpretation
2Coiera,E. (2003). Clinical decision support systems. In Guide to health informatics (2nd ed.) (pp 333-343).
     London, UK: Hodder Arnold.
3General Hospital Corporation. (2011). DXplain diagnostic decision support. Retrieved from

     http://dxplain.org/dxp/dxp.pl
3General Hospital Corporation. (2011). DXplain diagnostic decision support. Retrieved from
http://dxplain.org/dxp/dxp.pl
The CDSS Business
   Systems are developed within both health care
    organizations (Ex. MGH’s DXplain) and corporations ( Ex.
    Hospira’s TheraDoc)

   Electronic medical record products often include decision
    support tools (Epic, McKesson)

   Systems may be web-based (Ex. VisualDx) or installed on
    hospital/clinic computers & networks

   Systems are (and must be) highly customizable, so
    implementation services are an essential part of the product
Trends Promoting CDSS Usage
   Need to improve patient safety and
    quality of care2,4
      Between  44,000 and 98,000 Americans are killed
       each year by medical errors
      Using the lower estimate makes medical error the 8th
       leading cause of death in the US
      770,000 people are injured or killed by adverse drug
       events
      Preventable medical errors cost the US economy
       roughly $17 billion annually
2Coiera,  E. (2003). Clinical decision support systems. In Guide to health informatics (2nd ed.) (pp 333-343).
      London, UK: Hodder Arnold.
4Kohn L., Corrigan J.M., & Donaldson M. (Eds.). (1999). To err is human: Building a safer health system.

      Washington, DC: National Academy Press.
Trends Promoting CDSS Usage

   Rising cost of care5,6
      In 2006, the US spent an estimated $2.1 trillion on
       health care
      The average American currently spends $6,000, which
       is 2.5 times the median for the rest of the industrialized
       world
      By 2016, the annual cost of health care in the US will
       hit $4.1 trillion (roughly 20% of GDP)

5Schoen, C., Davis, K., How, S.K.H., & Schoenbaum, S.C. (2006). U.S. health system performance: A national
      scorecard. Health Affairs, 25, no.6 (2006):w457-w475. Retrieved from
      http://content.healthaffairs.org/content/25/6/w457.full.pdf+html
6Brownlee, S. (2007). Overtreated: Why too much medicine is making us sicker and poorer. New York, NY:

      Bloomsbury USA.
Trends Promoting CDSS Usage

   Payer Incentives1
     “Recently      passed legislation related to pay for
          performance and e-prescribing (electronic prescribing
          systems that usually include CDS related to drug
          interactions) shift payment incentives to make use of
          CDS more attractive”




1BernerES. (2009). Clinical decision support systems: State of the art (AHRQ Publication No. 09-0069-EF).
      Rockville, MD: Agency for Healthcare Research and Quality.
   CDSS Potential
>Provide real-time tools for reducing complexity and uncertainty
 in the care process




http://www-03.ibm.com/innovation/us/watson/watson-for-a-smarter-planet/industry-perspectives/healthcare.html
   CDSS Potential
>Ensure patient safety and comprehensive care through the use
 of diagnostic & therapeutic critique and reminder systems




http://www-03.ibm.com/innovation/us/watson/watson-for-a-smarter-planet/industry-perspectives/healthcare.html
   CDSS Potential
>Provide optimal care by the use of the most current, evidence-
 based care algorithms delivered in a user-oriented fashion




http://www-03.ibm.com/innovation/us/watson/watson-for-a-smarter-planet/industry-perspectives/healthcare.html
   CDSS Potential
>Provide individualized care that includes personal, probabilistic
 & epidemiological data




http://www-03.ibm.com/innovation/us/watson/watson-for-a-smarter-planet/industry-perspectives/healthcare.html
Benefits 2


   Improve patient safety
     A      1998 study found a 55% reduction in adverse drug
           events following the implementation of a physician
           order entry system at Brigham and Women’s Hospital in
           Boston, MA
   Enhancing prescribing behavior
      Another      study found “compliance with the generic drug
           choice changed from around 14% pre-implementation
           to over 80% 2 months post system implementation and
           to 97% compliance at 1 and 2 year follow-up”
2Coiera,E. (2003). Clinical decision support systems. In Guide to health informatics (2nd ed.) (pp 333-343).
      London, UK: Hodder Arnold.
Benefits 2


   Improved compliance with clinical pathways and
    guidelines
     A      1997 randomized trial showed a 30% reduction in
           the rate of prescription of vancomycin compared to the
           control group
   Improved efficiency and lower cost of care
      “At     Brigham and Women’s Hospital…order entry
           systems are estimated to save about $5-10 million per
           year largely due to the increased use of less expensive
           tests and drugs”
2Coiera,E. (2003). Clinical decision support systems. In Guide to health informatics (2nd ed.) (pp 333-343).
      London, UK: Hodder Arnold.
Challenges
   The best CDSS is limited to the totality of current
    medical knowledge
       If a treatment does not exist or is misguided, a CDSS may
        not help and may even hurt the patient

   Perceived benefits can be can lead to the
    inappropriate use of technology
       A 2001 study of 63,750 appendectomies performed
        between 1987 and 1998 showed no change in the rate of
        misdiagnosis (15.5%) despite the introduction of CT
        scanning6
6Brownlee,S. (2007). Overtreated: Why too much medicine is making us sicker and poorer. New York, NY:
      Bloomsbury USA.
  Appropriate Tool Selection

The superiority of
advanced technologies can
sometimes be specious.




CT scanning often fails to
reduce the number of
negative appendectomies.
http://www.ispub.com/journal/the_internet_journal_of_oncology/volume_6_number_1_36/article_printable/appen
       diceal_adenocarcinoma_arising_after_bone_marrow_transplantation_for_non_hodgkin_lymphoma_an_unusu
       al_treatment_dilemma.html
Challenges


    The use of any medical technology is only
appropriate if it can be shown to yield statistically-
  significant improvements in patient outcomes.
Challenges
   Much of the data on benefits achieved has been anecdotal

   A 2005 review of 100 studies on the effect of CDSSs on
    patient outcomes found that “to date, the effects on patient
    outcomes remain understudied and, when studied, inconsistent”7

   A 2007 study found that “In spite of the cited merits of
    enhancing safety and reducing costs, published evaluation
    studies do not provide adequate evidence that CPOE systems
    provide these benefits in outpatient settings”8
7Adhikari,
         N.K., Beyene , J., M.P., Devereaux, P.J., Garg, A.X., Haynes, R.B., McDonald, H., Rosas-Arellano, &
     Sam, J. (2005). Effects of computerized clinical decision support systems on practitioner performance and
     patient outcomes: a systematic review. Journal of the American Medical Association, 293 (10): 1223-38.
8Abu-Hanna, A., Eslami, S., & de Keizer, N.F. (2007). Evaluation of outpatient computerized physician medication

     order entry systems: A systematic review. Journal American Medical Informatics Association, 14 (4): 400–
     406.
Challenges
   A 2011 review found that “few studies have found
    any benefits on patient outcomes, though many of
    these have been too small in sample size or too short
    in time to reveal clinically important effects”9
   A CDSS can recommend the best treatment, but if that
    treatment is ineffective, the CDSS will appear to have
    accomplished nothing
   Both CDSSs themselves and the methods used to
    evaluate them need further development
9Jaspers,M.W., Peute, L.W., Smeulers, M., & Vermeulen, H. (2011) Effects of clinical decision-support systems on
      practitioner performance and patient outcomes: A synthesis of high-quality systematic review findings.
      Journal American Medical Informatics Association, 18(3):327-34.
Challenges
   The interaction between the system and the user is
    crucial and requires changes in provider behavior
    and improvements in system design

       “Four studies showed that most of the alerts (from 55% to
        91.2%) were ignored by the physicians. Two studies showed
        that ‘clinically irrelevance’ was the main reported reason for
        overriding alerts”8 (2007 JAMIA study)


8Abu-Hanna, A., Eslami, S., & de Keizer, N.F. (2007). Evaluation of outpatient computerized physician medication
     order entry systems: A systematic review. Journal American Medical Informatics Association, 14 (4): 400–
     406.
   CDSS of the Future

           • Standardized    1- Populate Conditionals/Variables
 Wider     • Comprehensive
adoption   • Connected
of EMRs                      • EMR (Database connection)
                             • Epidemiological data (Database connection)
                             • Patient Exam (Entered as found via voice or
Real-time • Database           device connection, such ECG )
             design
Epi. & Pt. • Device
  Data       Design



                             2 - Form a differential diagnosis


                               3 - Develop a treatment plan
   CDSS of the Future
                           1- Populate Conditionals/Variables


Medical • Confidence
Decision  determination         2 - Form a differential diagnosis
Research                        • Present diagnostic possibilities and associated
                                  confidences
  User – • System design        • Recommend additional diagnostic information that
 focused • User training          would improve confidence
software



                                 3 - Develop a treatment plan
  CDSS of the Future
                    1 - Populate Conditionals/Variables



                             2 - Form a differential diagnosis




           • Outcomes
Evidence- research                 3 - Develop a treatment plan
 based • Protocol
protocols modification             • Modify standard protocol to reflect variable data (check
          research                   for drug interactions etc)
                                   • Present treatment suggestions for
           • System design           modification/confirmation (such as using a generic drug)
  User –   • User training         • Check changes and automatically enter orders
 focused
software
Questions?


   A copy of this presentation is available at:
www.mattsimko.com/myportfolio.html

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:3
posted:11/30/2012
language:Latin
pages:24