Updated report on features of the Regenstrief New Gopher System

1. Regenstrief Institute’s New
Medical Gopher:
A Next-Generation Open-Source
Physician Order Entry System
Jon D. Duke, MD, MS
Burke Mamlin, MD
Doug Martin MD
MedInfo 2013

4. Gopher
• Gopher grew from a single clinic to over
1000 workstations, inpatient, outpatient, ED
• 25+ years of iterations has resulted in robust
functionality and efficiency
• Served as the research platform for many of
the seminal studies in healthcare computing

5. 1984 2010

6. • In 2009 Regenstrief Institute began rebuilding
its core clinical information system platform
• In 2010, we began work on a new web-based
version of the venerable Gopher
• This system was designed using the
knowledge gained from the past 25 years of
Gopher as well as from the evolving literature
on CPOE system design
Developing the new Gopher

7. Started with a Blank Slate

8. Improve User Satisfaction
Support Patient Safety
Improve Quality of Care
Promote Provider Efficiency
Guiding Principles

9. Set Gravity in the Right Direction
Leverage Metaphors
Constrain Then Innovate
Design Strategies

10. Leverage
Metaphors

11. Leveraging Metaphors

12. Leveraging Metaphors

13. Leveraging Metaphors

15. E-Commerce

16. Workflow Wizards

17. Smart Autocompletion

18. Constrain
Then Innovate

19. 140 characters
hashtags
retweets
url shorteners
brevity
Instagram
Vine
Yammer
Waze

20. Screen Real Estate
• At outset of development process, set aside
an untouchable area of screen real estate
• That area– the InfoPanel– was not utilized for
>1 year into development but has become a
critical asset

22. Set Gravity in the
Right Direction

23. Right Thing
Wrong Thing
UserUser

24. Formulary Recognition

25. Allergy Entry

26. Fitt’s Law

28. What’s inside the new Gopher?

29. Major Functions
• Order entry
• Documentation / note writing
• Medication / problem / allergy management
• Results viewing
• Research
• Clinical decision support

30. Advancements in New Gopher
• Context-Driven Dynamic Alerts
• Adaptive Learning
• Real-time Natural Language Processing
• Multimedia Alerts
• Advanced Rule Authoring

31. Advancement #1: Dynamic Alerts
• Gopher has embedded mechanics to
dynamically change alert display based on
context
– Patient
– Physician
– Institutional

32. Alerting Zones

33. Relevance Adjustment Module
• Every alert has a baseline relevance level
which determines its display location
• For example, for DDI alerts, about 40% are
interruptive and 60% non-interruptive
• The RAM can adjust this default level

34. DDI
Alert Service
DDI
Alert Service
TRIAMTERENE Interacts with LISINOPRIL
Risk of Hyperkalemia
Severity: Moderate
Relevance: 5 (Average)
TRIAMTERENE Interacts with LISINOPRIL
Risk of Hyperkalemia
K 5.3*, Cr 1.3, GFR 55
Relevance: 7 (High)
Lisinopril Order
Related
Concepts
Related
Concepts
Hyperkalemia Has Relevant Labs:
K, Cr, GFR
Data
Repository
Data
RepositoryK, Cr, GFR
Relevance Adjustment ModuleRelevance Adjustment Module
Original Alert Final Alert
Patient has lab values:
K 5.3*, Cr 1.3, GFR 55

36. DDI
Alert Service
DDI
Alert Service
TRIAMTERENE Interacts with LISINOPRIL
Risk of Hyperkalemia
Severity: Moderate
Relevance: 5 (Average)
TRIAMTERENE Interacts with LISINOPRIL
Risk of Hyperkalemia
K 3.3, Cr 0.8, GFR 114
Relevance: 3 (Low)
Lisinopril Order
Related
Concepts
Related
Concepts
Hyperkalemia Has Relevant Labs:
K, Cr, GFR
Data
Repository
Data
RepositoryK, Cr, GFR
Relevance Adjustment ModuleRelevance Adjustment Module
Original Alert Final Alert
Patient has lab values:
K 3.3, Cr 0.8, GFR 55

38. Relevance Adjustment Module
• RAM can also make changes based on
provider characteristics
• For example, can make particular alerts non-
interruptive for certain specialties
• Conversely, for medical students all alerts can
be made interruptive

39. TM Nintendo
Advancement #2:
Gopher is a Learning System

40. Advancement #2:
Gopher is a Learning System
• Gopher can track user actions and activity
such as
– Number of logins
– Frequently selected orders
– Responses to previous alerts
• Can customize system behavior based on
individual user history

41. Alerts That Learn
• Picture of learning message, then another of
the small alert
Diazepam
Diazepam 5 MG

42. Alerts That Learn
Diazepam
Diazepam 5 MG

43. Advancement #3:
Natural Language Processing
• Gopher can analyze notes in real-time
• Can determine section (e.g., FHx, PMH) to give
context to the concepts retrieved
• Multiple services may be run simultaneously
(e.g.,CDS, quality metrics, study recruitment)
• Results may be displayed as alert or used for
background data capture
Section header detection thanks to SecTag from Vanderbilt University:
http://knowledgemap.mc.vanderbilt.edu/research/content/sectag-tagging-clinical-note-section-headers

44. Order Detection

45. Study Reminders

46. Natural Language Processing
• Can be used as a CDS trigger
• Can be used to enhance structured
documentation for ‘meaningful use’
• Can be used for clinical research
• Integrated with our Advanced Rule Authoring
environments

47. Advancement #4:
Multimedia Alerts

49. Adherence Information

50. Research Study Eligibility

51. Advancement #5:
Advanced Rule Authoring
• The Rule Authoring and Validation
Environment (RAVE) is a rule authoring tool
within Gopher
• The RAVE is designed to empower
stakeholders to create complex, rule-based
actions using a simple graphical interface

52. Rule Authoring
• Rules are necessary to drive decision support
logic as well as other system actions
• Rule authoring is generally a complex task
requiring code-like syntax

54. Good artists copy.
Great artists steal.
- Pablo Picasso

55. ifttt.com

56. Great Artists Steal

60. RAVE = IFTTT for EMRs
• Built a variety of channels for EMR activities
• Channels may server as
– Triggers (If)
– Actions (Then)
– Both
• Additionally, we added a ‘For’ component to
specify when the rule should be run

61. Rule Authoring and Validation Environment
• Picture HERE

62. Rule Authoring and Validation Environment
• Picture HERE

63. Rule Authoring and Validation Environment
• Picture HERE

64. RAVE Channels
If Channels
• Orders
• Diagnoses
• Allergies
• Note NLP
• Chart Actions
• Observations
• ADT
• HL7
Then Channels
• Alerts
• Email / SMS
• Logging
• Observations
For Channels
• Patient
• User

65. FOR: Patient Channel
• Picture HERE

66. IF: Diagnosis Channel
• Picture HERE

67. THEN: Alert Channel
• Picture HERE

68. RAVE Output
• Picture HERE

69. RAVE Output
• Picture HERE

70. RAVE DROOLS Syntax
• Picture HERE

71. Rule Authoring and Validation Environment

72. RAVE = Customizability
• Can mix and match channels to create a
remarkable array of functionality without
need for programmer intervention
• Can write rules just for yourself or (with
permission) your clinic, specialty, or all users
• Rule syntax is generated automatically in a
standard rules syntax (Drools)

73. Gopher Demo

74. Gopher and Open Source
• Regenstrief is philosophically and
contractually committed to release of the new
Gopher platform as open source software
• We are looking for partners to take part in
both software development and community
building around this effort
• Please let us know if this is something you
would be willing to commit time and energy
to pursuing

75. Acknowledgements
• Chris Beesley
• Chris Bonham
• Mike Brehm
• Jason Cadwallader
• Joshua Castagno
• Vidhya Chari
• Parishkar Chauhan
• Ling Cheng
• Sireesha Chilukuri
• Cyril Colvard
• Jonathan Cummins
• Alex Franken
• Cindi Hart
• Charity Hilton
• Joshua Jones
• Warren Killian
• Jeremy Leventhal
• Allen Logan
• Ernesto Maldonado
• Burke Mamlin
• Andrew Martin
• Doug Martin
• Jim Meeks-Johnson
• Pat Milligan
• Justin Morea
• Chris Power
• Linas Simonaitis
• Kenneth Spry
• Jeff Stroup
• Blaine Takesue
• David Taylor
• Jeff Warvel
• Jennifer Weatherspoon
• Chen Wen

76. Questions?
jduke@regenstrief.org