Twenty Years of IAIMS: The Columbia University/ New York Presbyterian Hospital Clinical Data Repository

1
Twenty Years of IAIMSThe Columbia
University/New York Presbyterian Hospital
Clinical Data Repository

• James J. Cimino
• Department of Biomedical Informatics
• Columbia University College of Physicians and
  Surgeons
• IAIMS Consortium Annual Meeting
• Boston, MA
• April 10, 2005

2
Overview

• History and evolution (or creation)
• Where we are today
• What we learned

• History and evolution

3
History and Evolution (or Creation)

• 1983-1986 IAIMS Planning Grant
• Rachel Anderson
• Organizational
• 1986-1988 IAIMS Demonstration Grant
• Paul Clayton and Rachel Anderson
• Center for Medical Informatics
• Vision

4
(No Transcript)
5
History and Evolution (or Creation)

• 1983-1986 IAIMS Planning Grant
• Rachel Anderson
• Organizational
• 1986-1988 IAIMS Demonstration Grant
• Paul Clayton
• Center for Medical Informatics
• Vision

• 6M Demo
• 1988-1993 IAIMS Implementation Grant
• Funding from NLM, IBM, CU, Presbyterian Hospital
• Network
• Clinical data architecture

6
Clinical Data Architecture

• Central repository to collect data from myriad
  sources
• Myriad users of data - some not yet imagined

7
New York Presbyterian HospitalClinical
Information Systems Architecture
8
Clinical Data Architecture

• Central repository to collect data from myriad
  sources
• Myriad users of data - some not yet imagined

• Patient-oriented, not visit oriented, database
• Relational, not hierarchical, model
• Entity-attribute-value model

9
Entity-Attribute-Value Clinical Data Repository
10
Clinical Data Architecture

• Central repository to collect data from myriad
  sources
• Myriad users of data - some not yet imagined
• Patient-oriented, not visit oriented, database
• Relational, not hierarchical, model
• Entity-attribute-value model

• Coded data wherever possible
• Unify terminology

11
Medical Entities Dictionary A Central
Terminology Repository
12
Communicating Terminology Changes
13
Solution Hierarchical Integration
K1
K2
14
MED Structure
Medical Entity
CHEM-7
Plasma Glucose
15
Where We Are Today - Repository

• Patients 2.6 million
• Visits gt10 million since 1996 with archives
  going back to 1979
• Visit diagnoses, locations, procedures,
  providers, insurance
• Lab procedures 16 million with 130 million
  results (to 1989)
• Radiology procedures reports 5.7 million
• Pathology 1.4 million
• Cardiology procedures 1.5 million
• Resident signout notes760,000
• Operative Notes 426,000
• Clinical Notes 400,000
• Discharge Summaries 420000

• Medication orders gt60 million
• ObGyn Procedure Reports 241,000
• GI Procedure Reports 101,000
• Neurology Procedure Reports 54,000
• Ideatel BPs 215,000
• Ideatel Glucose 650,000
• Consult Events 18000
• HEENT Events13000
• Hospitalist Notes30000
• PFT 25000
• Provider profiles 11000
• IDX 1.4 million
• East Campus

16
Where We Are Today - MED

• Domains
• HP lab terms
• Misys lab terms
• Cerner lab terms
• Misys Radiology
• Digimedix drugs
• Cerner Drugs
• ICD9-based problem list terms
• Other applications
• Knowledge terms
• Size
• Concept-based (95,641)
• Multiple hierarchy (141,306)
• Synonyms (239,581)
• Translations (141,717)
• Semantic links (225,698)
• Attributes (210,456)

17
Where We Are Today - Outputs

• 7000 Users
• Clinical information systems

18
(No Transcript)
19
(No Transcript)
20
(No Transcript)
21
(No Transcript)
22
(No Transcript)
23
(No Transcript)
24
(No Transcript)
25
(No Transcript)
26
(No Transcript)
27
(No Transcript)
28
LPRO-gt(AE)-gtANTB-gt(DS)-gtPFUN-gt(PO)-gtORGMlt-
(PP)lt-OATT A procedure assesses the effect of
an antibiotic which disrupts a physiologic
function which is a process of an organism which
has an attribute (sensitive/resistant).
29
(No Transcript)
30
(No Transcript)
31
Where We Are Today - Outputs

• 7000 Users
• Clinical information systems

• MedLEE

32
MedLEE
33
Where We Are Today - Outputs

• 7000 Users
• Clinical information systems
• MedLEE

• Decision support systems
• Vigilens TB, Freq Admit, Lab Vals

34
(No Transcript)
35
Where We Are Today - Outputs

• 7000 Users
• Clinical information systems
• MedLEE
• Decision support systems
• Vigilens TB, Freq Admit, Lab Vals

• Infobuttons

36
(No Transcript)
37
(No Transcript)
38
(No Transcript)
39
Where We Are Today - Outputs

• 7000 Users
• Clinical information systems
• MedLEE
• Decision support systems
• Vigilens TB, Freq Admit, Lab Vals
• Infobuttons

• Clinical data warehouse

40
(No Transcript)
41
select patient_id , time primary_time from
visit2004_diagnosis where diagnosis_icd9_code
like '410' and b.primary_time between
'01/01/2000' and '01/01/2005' and b.comp_code
30366
42
Where We Are Today - Outputs

• 7000 Users
• Clinical information systems
• Decision support systems
• Vigilens TB, Freq Admit, Lab Vals
• Infobuttons
• Clinical data warehouse

• Other clinical systems
• Infection Control
• CPOE
• Marconi
• IDEATel
• Data Mining
• Bioinformatics

43
Lessons Learned

• The repository architecture paid off
• Model the data, not the applications
• Write once, read many times
• Pay attention to your terminology
• You will reuse data
• You cant predict how you will reuse it

44
Acknowledgements

• New York Presbyterian Hospital
• Columbia University
• National Library of Medicine
• IBM

• People
• Tom Morris
• Henrik Bendixen
• Rachel Anderson
• Paul Clayton
• Steve Johnson
• George Hripcsak
• Bob Sideli
• Somitra (Sen) Sengupta