Transcript Heart Disease Program

Clinical Decision Making
Group Information
Director:
Peter Szolovits ([email protected])
Mission:
To provide better health care
through applied artificial intelligence.
Description:
The Clinical Decision Making Group at
the MIT Laboratory for Computer
Science is a research group dedicated to
exploring and furthering the application
of technology and artificial intelligence
to clinical situations.
Because of the vital and crucial nature of
medical practice, and the need for
accurate and timely information to support
clinical decisions, the group is also
focused on the gathering, availability,
security and use of medical information
throughout the human "life cycle" and
beyond.
Training Programs
 Courses
 Photo
Gallery
 Internal (MIT only)
Contact:
People
Phone: (617) 253-5860
Fax: (617) 258-8682
Email: [email protected]
Web: http://www.medg.lcs.mit.edu/
Projects
Guardian Angel
Personal lifelong active medical assistants
EMRS
The Electronic Medical Record System
project aims to provide unified common
medical record access via the world-wide web.
Heart Disease Assisting the diagnosis and
therapy of cardiovascular disease. Physicians
can try the diagnosis program.
Projects
MAITA
The Monitoring, Analysis, and Interpretation
Tool Arsenal provides means for automated
gathering, understanding, and reacting to
important information in a broad range of
application areas, including clinical, military,
industrial, commercial, and scientific
monitoring and surveillance.
Geninfer
Assisting clinical genetics counselors
Case-Based
Reasoning
Learning diagnostic expertise from
experience
Heart Disease Program
Purpose:
To assist physicians in the diagnosis of
patients with cardiac symptoms, focusing
on hemodynamic dysfunction.
Description:
The Heart Disease Program is a computer
system to act as an intellectual sounding
board, assisting the physician in the task
of differential diagnosis and anticipating
the effects of therapy in the domain of
cardiovascular disorders.
To address these problems we have developed two
significant methodologies for medical reasoning.
For diagnosis we have responded to the challenges
of this very rich domain with a diagnostic
mechanism that combines probabilistic reasoning
in a Bayesian network with the constraints
composed by the severities of the states and
the temporal relations of causality.
This allows the Heart Disease Program (HDP) to
generate differential diagnoses that are consistent
with respect to the known conditions of causality
in the medical domain.
The hypotheses that make up the differential are
causal networks representing the likely
mechanisms causing and complicating the
hemodynamic dysfunctions at a clinical level of
detail. Most of this web focuses on the diagnostic
program.
For predicting the effects of therapy we have
developed a mechanism that uses equations for the
hemodynamic relationships and a signal flow
technique to calculate the likely quantitative
steady-state change for all parameters given
changes in therapies (or other parameter changes).
This mechanism effectively captures the
hemodynamic effects of the therapies on which it
has been tested for a variety of pathophysiologic
conditions.
Questions, comments about this site?
Email: [email protected]
KR Conferences
Hosting the web site for the Principles of
Knowledge Representation and
Reasoning Conferences.
Questions, comments about this site?
Email: [email protected]
Guardian Angel.
Current health information systems are built
for the convenience of health care providers
and consequently yield fragmented patient
records in which medically relevant lifelong
information is sometimes incomplete, incorrect,
or inaccessible.
We are constructing information systems centered
on the individual patient instead of the provider, in
which a set of guardian angel (GA) software
agents integrates all health-related concerns,
including medically-relevant legal and financial
information, about an individual (its subject).
This personal system will help track,
manage, and interpret the subject's health
history, and offer advice to both patient and
provider.
Guardian Angel
Minimally, the system will maintain
comprehensive, cumulative, correct,
and coherent medical records,
accessible in a timely manner as the
subject moves through life, work
assignments, and health care providers.
Each GA is an active process that
performs several important functions: it
collects patient data; it checks,
interprets, and explains to the subject
medically-relevant facts and plans; it
adapts its advice based on the subject's
prior experiences and stated
preferences
it performs sanity checks on both
medical efficacy and cost-effectiveness
of diagnostic conclusions and
therapeutic plans; it monitors progress;
it interfaces to software agents of
providers, insurers, etc.; and it helps
educate, encourage, and inform the
patient.
All this serves to improve the quality of
medical decision-making, increase
patient compliance, and minimize
iatrogenic disease and medical errors.
Heart Disease Program
Project Information Group:
Clinical Decision Making Group
Project Leader:
Bill Long ([email protected])
Purpose:
To assist physicians in the diagnosis
of patients with cardiac symptoms, focusing
on hemodynamic dysfunction.
Description:
The Heart Disease Program is a computer
system to act as an intellectual sounding
board, assisting the physician in the task
of differential diagnosis and anticipating
the effects of therapy in the domain of
cardiovascular disorders. To address these
problems we have developed two significant
methodologies for medical reasoning.
For diagnosis we have responded to the
challenges of this very rich domain with a
diagnostic mechanism that combines
probabilistic reasoning in a Bayesian network
with the constraints imposed by the severities
of the states and the temporal relations of
causality.
This allows the Heart Disease Program
(HDP) to generate differential diagnoses
that are consistent with respect to the
known conditions of causality in the
medical domain.
The hypotheses that make up the
differential are causal networks
representing the likely mechanisms
causing and complicating the
hemodynamic dysfunctions at a clinical
level of detail. Most of this web focuses
on the diagnostic program.
For predicting the effects of therapy we have
developed a mechanism that uses equations
for the hemodynamic relationships and a
signal flow technique to calculate the likely
quantitative steady-state change for all
parameters given changes in therapies (or
other parameter changes).
This mechanism efectively captures the
hemodynamic effects of the therapies on
which it has been tested for a variety of
pathophysiologic conditions.
Questions, comments about this site?
Email: [email protected]
Case Based Reasoning in Cardiovascular Disease
Over the last eight years, we have been working on
the problem of case-based reasoning (CBR) for
medical diagnosis. Through a succession of
research projects, we developed a system that used
physiologic causes to match findings in cases,
evaluated the system on 240 cases, and developed a
system that divides cases and memory based on the
diagnostic units in the case.
Each of these steps has been a significant
advance toward diagnostic systems that can
effectively learn from experience. Still, it is
clear that CBR has not reached its potential
to effectively handle the case material and
work in concert with a model-based program.
Documents
Phyllis A. Koton, ``Using Experience in Learning
and Problem Solving,'' MIT PHD Thesis, May
1988.
David S. Aghassi, Evaluating Case-Based Reasoning
for Heart Failure Diagnosis, MIT/-LCS/TR-478,
(MS Thesis), June 1990.
Yeona Jang, HYDI: A Hybrid System with Feedback
for Diagnosing Multiple Disorders, MIT Ph. D.
Thesis, September 1993.