52
The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

  • View
    219

  • Download
    0

Embed Size (px)

Citation preview

Page 1: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

The Promise of Pathology Informatics

James J. Cimino, M.D.

Department of Medical Informatics

Columbia University

Page 2: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Questions You WouldLike Answered

• How can we link patient record information to pathology specimens to support clinical research?

• If we can do this, what will be possible?

Page 3: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

The Question I ThinkYou Need to Answer

• How can pathology information be represented to support data reuse?

Page 4: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

What is “Data Reuse”?

In contrast to the primary use of health data (“show it to the doctor”)…

…any secondary use of the data for tasks ranging from direct patient care, to financial purposes, to research

Page 5: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

My Goal for this Talk

• Expand upon the notion of data reuse

• Discuss representational issues needed for reuse

• Propose a challenge

Page 6: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

First Admission: August, 1983

In August, 1983, a 50 year old male presented to the St. Vincent’s Hospital (NY) emergency room with a scalp laceration due to a falling paint can. The wound was cleaned and sutured, and the patient was give a follow up appointment for surgery clinic. Two weeks later, the patient was seen at the scheduled clinic visit and was found to have delayed healing of one portion of the wound. After several weekly visits, the poorly-healing area was excised and the wound was closed. The patient had a good result and was discharged from further follow up.

Page 7: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Second Admission - March, 1984

The patient was brought to the emergency room for recent increasing lethargy. Laboratory evaluation was remarkable only for a calcium of 17 mg/dl. The patient was treated aggressively with hydration and diuretics, but expired shortly after admission. A diagnostic report was received.

Page 8: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Prologue as Epilogue

The pathology report from the wound revision the previous September included the following phrase:

“Metastatic adenocarcinoma of uncertain origin is noted at the tissue margins”

Page 9: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

What Happened?

• The primary use of the data was to produce a report

• An information system could have managed that report

• High-quality data representation could have supported the reuse of the data by a decision support system

Page 10: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Pathology Information Today

• Narrative reports

• Structured reports

• Coded data (ICD9-CM vs. SNOMED vs. Local Codes)

Page 11: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Potential for Reuse of Pathology Information

• Direct use by care providers

• Billing

• Quality assurance/Case management

• Clinical research (including Outcomes)

• Automated decision support

• Integration with other information systems

Page 12: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

ResearchDatabase

Example:Retrospective Clinical ResearchPathology System

Financial System

Laboratory System

Pharmacy System

Data Monitor

Repository

Page 13: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

ResearchDatabase

Example:Prospective Clinical Research

Pathology System

Financial System

Laboratory System

Pharmacy System

Data Monitor

Repository

DecisionSupport KB

Page 14: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Example:Prospective Clinical Research

• Data monitor checks eligibility criteria

• Alert sent to subject recruiter

• Example: Biphosphonate Study

Page 15: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Example:Automated Decision Support

• Data monitor checks for triggering conditions

• Medical Logic Modules decide if warning conditions are present

• Message sent to appropriate channel

• Example: Tuberculosis culture result

Page 16: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Caveats: TB Example

• Monitors for delayed culture results

• Sends message if result not equal to the code “No growth”

• One day, dozens of alerts about positive results but no organism was reported

• What happened?

Page 17: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

How the Lab Fooled the Alert

• Alert looked for results “No Growth”

• Lab started reporting “No Growth to Date”

• “No Growth to Date” “No Growth”

• Solution: Use the controlled terminology to map all No-Growth-like lab terms into a single class, and have the alert logic refer to the class.

Page 18: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

No Growth after ...

How we Outsmarted the Lab

No Growth

No Growth after 48 Hours

No Growth after 72 Hours

“No Growth” Results

No Growth after 24 Hours

No Growth to Date

Page 19: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Example:Linking to On-line Resources

• Clinician reviewing reports will have information needs

• On-line information sources can satisfy that need

• Data from report can be used to automate the query

Page 20: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 21: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 22: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 23: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 24: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 25: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 26: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 27: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 28: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 29: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 30: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Linking Text Reports to On-line Information Sources

• Natural Language Processing

• Data representation to support reuse

• Codification of information needs

Page 31: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 32: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 33: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 34: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 35: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 36: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 37: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 38: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 39: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 40: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 41: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 42: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 43: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 44: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 45: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University
Page 46: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

How does CPMC Support Data Reuse?

• Natural Language Processing

• High-quality controlled terminology ( “codes”)

Page 47: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

High-Quality Terminology

• Concept oriented - with concept permanence

• Multiple synonyms

• Multiple hierarchies

• Semantic network of interconcept relations

• Integration of low-level (clinical) terminology with high-level (aggregation) terminology

Page 48: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

LaboratoryTest

Medical Entities Dictionary

HasIngredient

Measures

Chemical

AminoglycosideAntibiotic

Gentamicin

Serum Gentamicin

Test

Drug

Injectable GentamicinTrade-Name: Garamycin"Has-Ingredient: GentamicinMeasures

Random Gentamicin Level

Main-MeSH:

Supplementary-MeSH: "Gentamicin/bl"

Measures: Gentamicin

Page 49: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Pathology Informatics“Grand Challenges”

• Representing the concepts in reports

• Represent the relationships among concepts in reports

• Representing the concepts for aggregation and retrieval

• Integration of the concepts

Page 50: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

What Will Be Possible

• Data retrieval

• Data mining

• Improvements in report quality

• Improved reuse of data…

…including patient care

Page 51: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

My Challenge to You

Ask not what informatics can do for you.

Ask what you can do for informatics.

Page 52: The Promise of Pathology Informatics James J. Cimino, M.D. Department of Medical Informatics Columbia University

Questions?