The Future of All Things LIS

1
The Future of All Things LIS
Ulysses J. Balis, MD Past-President of the
Association for Pathology Informatics Associate
Professor and Director, Clinical
Informatics Co-Director, Division of Pathology
Informatics Department of Pathology University of
Michigan Health System Ann Arbor,
Michigan ulysses_at_umich.edu
Michael McNeely, MD President of the Association
for Pathology Informatics Medical Director -
Provincial Laboratory Information Solution
(PLIS) 4481 Shore Way, Victoria V8N3V1 (250)
477-7758 mmcneely_at_islandnet.com
APIII 1030 am 1200 noon October 22,
2008 Session B2
2
The Future of All Things LIS AP, CP, and their
Logical Merger with the Advent of High-throughput
Molecular Data

• Introduction
• Part I Clinical Pathology
• Part II Anatomic Pathology
• Part III The Evolved Next-Generation System A
  Merged Future
• Discussion

3
Clinical Pathology
President of the Association for Pathology
Informatics Medical Director - Provincial
Laboratory Information Solution 4481 Shore Way,
Victoria V8N3V1 [phone] mmcneely_at_islandnet.
com
Michael McNeely, MD

• Association for Pathology Informatics
• The iEHR Project (British Columbia)
• PLIS
• Telepathology
• iEHR

4
The Laboratory Information Cycle

• Transactional support
• Analysis
• Knowledge Support a.k.a. Clinical Decision
  Support (provision of current knowledge)
• Data Mining (creation of new knowledge)

5
PATIENT
PATIENT CHART
PHYSICIAN
KNOWLEDGE ASSIMILATION
TEST SELECTION
REPORT DISTRIBUTION
DATA BASE
COLLECTION
REPORT PREPARATION
ACCESSION
REVIEW INTERPRETATION
QA/QC
TRANSPORT DISTRIBUTION
ANALYSIS / EXAMINATION
6
LIS Historical Perspective

• 2008
• All lab areas
• Mainly transactional
• Interconnected

• 1972
• Chem Hem
• All transactional
• Stand-alone

7
Legend Clinical Pathology Transactional
Activity Anatomic Pathology Transactional
Activity Clinical Pathology Report Knowledge
Content Anatomic Pathology Report Knowledge
Content
Non-quantitative scale
Transactional Activity
Report Knowledge Content
?
60 s 70s 80s 90s 2000s
60 s 70s 80s 90s 2000s
8
Database

• Ubiquitous reach
• Two forms
• Identified for long-term EHR
• De-identified (pseudoanonymized) for research

9
Patient ? Doctor

• The starting point and raison d'être
• Diagnosis, Monitoring, Screening, Follow-up
  previous visits
• Increased patient involvement

10
Test Selection

• Traditional approach ad hoc
• Electronic Ordering Guided and problem oriented.
  CPOE (Computerized Physician Order Entry)
• Transactional Opportunities Insurance/reimburseme
  nt, Improved clarity, Reduced redundancy,
  Improved Compliance
• Clinical Opportunities Chronic Disease
  Management, Clinical Practice Guidelines
• Clinical Decision Support (more on this later)
  Smith McNeely van Wijk et.al.

11
Smith BJ, McNeely MD. The influence of an Expert
System for test ordering and interpretation on
laboratory investigations. Clin Chem. 1999 45
1168-1175.
12
(No Transcript)
13
(No Transcript)
14
(No Transcript)
15
(No Transcript)
16
(No Transcript)
17
(No Transcript)
18
(No Transcript)
19

• A sample is collected
• and sent to the lab

20
(No Transcript)
21
(No Transcript)
22
Results of a trial
23
Study conclusion

• The development of test ordering strategies can
  be enhanced.
• The interpretation of the test results can be
  enhanced.
• A statistical database of diagnosis, clinical
  information, test orders, and results can be
  readily derived. Such information is unique and
  is available for optimizing and developing
  testing strategies and for laboratory management.

24
Study conclusion (cont)

• An appropriate search of the database would
  enable clinician-targeted education and
  utilization feedback to be derived.
• Examination of the database at the time of
  ordering would enable the development of a module
  to identify unnecessary, duplicate testing.
• With appropriate additions to the ordering
  module, a sophisticated "front end" to a
  compliance-checking program could be developed.

25
BloodLink

• Marc Van Wijk Delft Netherlands
• Van Wijk MAM, van der Lei J, Moseseveld M, et.al.
  Compliance of general practitioners with a
  guideline-based decision support system for
  ordering blood tests. Clin Chem. 2002 48 55-60.
• Based on lab tests recommended within the CPGs
  developed by the NSGP
• Standard EMR for all practitioners.

26
(No Transcript)
27
(No Transcript)
28
(No Transcript)
29
(No Transcript)
30
BloodLink Evaluation 50 GPs Two Groups
1-Year
Test reduction of 19.6
31
Collection

• Positive Patient ID
• Bar-Codes
• RF Technology (Wednesday 830)
• Single most vulnerable area
• Need for multi-lab sample distribution

32
Accession

• Linking Positive Patient ID, CPOE, and RF
  Technology

33
Transport Distribution

• GPS Tracking
• Universal distribution

34
Analysis / Examination

• Middleware solutions
• Proteomics
• Genetic/Molecular Testing
• Analytical Algorithms
• Telepathology
• Multiplexed assays
• Multiplexed Cancer Biomarkers

35
QA / QC

• Up until now basic
• Future Informatics solutions
• Automated Key Indicators for LEAN and CQI
• Statistical Comparisons (esp. across
  jurisdictions)
• Monitoring multisteps both pre- and post
  analytical
• Examination for Notifiable/Illogical Reports

36
Review Interpretation

• Middleware
• Pathologists Workstations
• Diagnostic Coding
• Selections of Knowledge Support Material for
  Clinical Decision Making
• Patient oriented interpretations

37
Report Preparation

• Need for standardizing report elements (PLIS
  experience Test Names, Units, Reference Ranges)
• Expert System Interpretation (LABDOC)
• Normalized Reference Ranges
• More complex reports
• Contextualized Report
• Codified Reports
• Logic Reviews

38
Report Distribution

• Can send anywhere
• Is what we send --- what is received?
• Privacy, integrity and ownership issue.

39
Patient Chart

• EMR --- the fate of data when it hits the EMR or
  HIS
• Primary and secondary views
• Pathologists Role

40
Knowledge Assimilation

• The Big Question who will be the report
  assimilator?
• Clinical Decision Support the EMR Vendor, the
  Lab, the HIS
• Contextualized report immortalization
• Molecular Diagnostics the report is forever and
  may be re-interpreted. Problem may be locating
  the patient.

We are the lab results Assimilation is futile
41
Clinical Decision Support Methodology(Must be
automated)

• Coded rules
• Expert Systems
• Production Rules
• Deterministic ClinLab.com
• Readjusting
• Neural Networks
• PubMed A proposal
• Wiki
• Database Merging and Mining

42
CP Summary Points

• Knowledge Support tools can dramatically enhance
  clinical laboratory test ordering and
  interpretation.
• We are at a crossroad where knowledge can and
  should be added to the CP report but who will
  do it?
• Informatics-based QA, Proteomics, Analytical
  Algorithms, Multiplexed Assays, and Genetic
  investigations will add to analytical information
  complexity and will breakdown the old 1-assay
  1-result paradigm.
• The new coded, contextualized, immortalized
  report format, laden with automatically generated
  and context appropriate knowledge content will be
  inseparable from the similarly constructed AP
  report.