E preference a tool for incorporating patient preferences into health decision aids
This presentation is the property of its rightful owner.
Sponsored Links
1 / 52

e -Preference: A Tool for Incorporating Patient Preferences into Health Decision Aids PowerPoint PPT Presentation


  • 45 Views
  • Uploaded on
  • Presentation posted in: General

e -Preference: A Tool for Incorporating Patient Preferences into Health Decision Aids. Amar K. Das, MD, PhD Assistant Professor Departments of Medicine (Medical Informatics) and Psychiatry and Behavioral Sciences Stanford University. Outline. Health decision aids Clinical example

Download Presentation

e -Preference: A Tool for Incorporating Patient Preferences into Health Decision Aids

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


E preference a tool for incorporating patient preferences into health decision aids

e-Preference: A Tool for Incorporating Patient Preferences into Health Decision Aids

Amar K. Das, MD, PhD

Assistant Professor

Departments of Medicine (Medical Informatics) and

Psychiatry and Behavioral Sciences

Stanford University


Outline

Outline

  • Health decision aids

  • Clinical example

  • e-Preference approach

  • Prototype system and evaluation


Health decisions in aging

Health Decisions in Aging

  • Older individuals often face complex health decisions involving significant risk of morbidity and/or mortality

  • Patient participation is desirable in such decisions

  • Clinicians’ ability to facilitate shared decision making varies


Health decision aids

Health Decision Aids

  • Focus typically on

    • Improvements in patient knowledge

    • Explanation of treatment alternatives

    • Communication of risk


Hda presentation

HDA Presentation

  • Non-interactive formats

    • Brochure (paper booklet or Web based)

    • Audiotape

    • Video

  • Interactive formats

    • Decision board

    • Computer

    • Multimedia


Outline1

Outline

  • Health decision aids

  • Clinical example

  • e-Preference approach

  • Prototype system and evaluation


Atrial fibrillation

Atrial Fibrillation

  • Atrial fibrillation leads to a significant risk of stroke, ranging from 1% to 15% per year, based on patient factors

  • Anticoagulation therapy (warfarin) can reduce the risk of stroke by approximately two thirds, but incurs a risk of major bleeding complications of 1% to 3% per year


Measuring preferences

Measuring Preferences

  • Eight studies that modeled treatment preferences of patients with atrial fibrillation

  • Studies used three methods

    • Probability tradeoff technique

    • Decision aid

    • Decision analysis

(Man-Son-Hing et al., 2005)


Audiobooklet

Audiobooklet

(Man-Son-Hing et al., 2000)


Audiobooklet1

Audiobooklet

(Man-Son-Hing et al., 2000)


Audiobooklet2

Audiobooklet

(Man-Son-Hing et al., 2000)


Decision analysis

Decision Analysis

(Protheroe et al., 2000)


Decision analysis1

Decision Analysis

(Protheroe et al., 2000)

17 on treatment

28 on treatment


Decision support tool

Decision-Support Tool

(Thomson et al., 2002)


Decision support tool1

Decision-Support Tool

(Thomson et al., 2002)


Hda limitations

HDA Limitations

  • Typically designed for one type of health decision

  • May not provide patient-specific information on alternatives and risks

  • May be only accessible in particular settings

  • Does not have readily modifiable design


Design desiderata for hdas

Design Desiderata for HDAs

  • We need a design that can

    • Be tailored to specific health problems

    • Incorporate patient-specific data

    • Be accessible via the Internet

    • Be easily modified


Outline2

Outline

  • Health decision aids

  • Clinical example

  • e-Preference approach

  • Prototype system and evaluation


Motivation for e preference

Motivation for e-Preference

  • Create an environment for clinical experts and software developers to design and implement HDAs

  • Based on our research group’s long standing interest in developing customizable and reusable software architectures for decision support


Eon architecture

EON Architecture

End-User

Application

Problem-Solving

Method

Query

Engine

Patient

Database

Protocol KB

Protégé


Design of e preference

Design of e-Preference

  • A set of software methods for

    • Knowledge representation

    • Decision-analytic computation

    • Data access from existing database

    • Web-based multimedia presentation


E preference architecture

e-Preference Architecture

HDA

Query

Engine

FLAIR

Netica

Patient

Database

KBDM

Protégé


Knowledge based decision model

Knowledge-Based Decision Model

  • Encode concepts related to

    • Influence diagrams

    • Health decisions and outcomes

    • Risk factors

    • Patient preferences

    • Relationships between these factors


Netica

Netica


Flair

FLAIR


Aristotle s categories

Aristotle’s Categories

Supreme genus:SUBSTANCE

Differentiae:material immaterial

Subordinate genera:BODYSPIRIT

Differentiae:animate inanimate

Subordinate genera:LIVINGMINERAL

Differentiae:sensitive insensitive

Proximate genera:ANIMALPLANT

Differentiae:rational irrational

Species:HUMANBEAST

Individuals:Socrates Plato Aristotle …


E preference a tool for incorporating patient preferences into health decision aids

The NCI Thesaurus


Structuring knowledge

Structuring Knowledge


Web ontology language

Web Ontology Language

  • A Semantic Web standard to use ontologies to represent knowledge on the Internet

  • OWL can be used to build ontologies of high-level descriptions, based on three concepts:

    • Classes (e.g., Influence Diagram, Nodes, Patient)

    • Properties (e.g., has_node, has_disease)

    • Individuals (e.g., “atrial fibrilaton”)


Owl example

OWL Example

Patient

Influence

Diagrams

has_chance_node

AF

E. MyChart

Nodes

has_model

has_diagnosis

Diagnoses

Decision

Chance

Outcome

AF

DM


Semantic web rule language

Semantic Web Rule Language

  • A language for expressing logical rules in terms of OWL concepts

  • Rules in SWRL can be used to deduce new knowledge about an existing OWL ontology

Patient(?pt) ^ has_dx(?pt, ?dx) ^ has_model(dx, ?hda) 

activate_HDA(?pt, ?hda)


Making restrictions

Making Restrictions


Generating a decision model

Generating a Decision Model


Remaining challenges

Remaining Challenges

  • Modeling and editing probabilities in Protégé OWL

  • Generating interface based on modified influence diagram


Kbdm approach

KBDM Approach

  • Advantages

    • Ability to modify knowledgebase and create tailored decision model for HDA

  • Disadvantages

    • Efforts needed for acquiring and maintaining knowledge


Outline3

Outline

  • Health decision aids

  • Clinical example

  • e-Preference approach

  • Prototype system and evaluation


Conclusions

Conclusions

  • HDAs can help to incorporate patient preferences into shared decision making

  • The knowledge used in developing HDAs using decision analyses can be encoded

  • Such knowledge can be used to generate and tailor HDAs


Acknowledgments

Acknowledgments

Stanford Medical Informatics

Bilal AhmedDaniel Rubin

Yael Garten Ravi Shankar

Jeremy Robin Samson Tu

Center for Primary Care and Outcomes Research

Mary GoldsteinTamara Sims

Doug Owens

NIA and CADMA for funding support


  • Login