Medizinische Experten und wissensbasierte Systeme

1
Medical Expert Systems Klaus-Peter
Adlassnig Department of Medical Computer
Sciences Section on Medical Expert and
Knowledge-Based Systems University of Vienna
Medical School
2
(No Transcript)
3
Objectives

• support of medical decision making for the
  single patient
• provide a correct diagnosis
• selection of an optimal therapy
• correct assessment of prognosis
• optimal patients management in medical
  institution

4
Structure

• algorithm
• data
• conventional program

• problem solving
• method
• knowledge base
• data
• knowledge-based system

5
Knowledge-Based Methodology

• measurements and observational level
• measured and observed data
• data-to-symbol conversion
• measurement and observational level ? knowledge
  level(data processing) (knowledge
  processing)
• knowledge level
• modelling of mental processes linguistically
  communicated
• modelling based on symbols linguistic concepts
  abstract concepts
• objective and subjective knowledge (definitional,
  causal, statistical, and heuristic knowledge)

6
patients medical data
physicians medical knowledge
induction
symptoms signs test results biosignals images 3D-v
isualizations diagnoses therapies standardiz
ation telecommunication chip cards
anatomy physiology pathophysiology pathology nosol
ogy therapeutic knowledge (e.g.,
pharmacology) subjective experience intuitio
n
? ? ?
many patients
general knowledge
deduction
single patient
general knowledge


HIS, MIS, LIS, PDMS, RIS, PACS
expert and knowledge-based systems
telemedicine
7
(No Transcript)
8
differential diagnosis
9
(No Transcript)
10
(No Transcript)
11
(No Transcript)
12
Clay Tablets from New Babylonian(about 650 B.C.)

• instructions to medical examination, diagnosis,
  and prognosis
• When you are about to examine a sick man ...
• IF, after a days illness, he begins to suffer
  from headache, ...
• IF a mother conceives again, her scalp and
  forehead becoming yellowish in colour, ...
• IF ... head ... , he will die suddenly.

13
(No Transcript)
14
Computer-Assisted Medical Diagnosis and Therapy

• Reasoning Foundations of Medical Diagnosis
  (1959)in Science by Ledley and Lusted
• symbolic logic
• symptom complexes logic combinations diagnoses
  implicated or excluded
• probability
• frequency of symptoms with diseases, frequency of
  symptoms and frequency of diseases in a
  population most probable diagnosis
• value theory
• decision trees optimal treatment

15
Medical problem solving is the process of making
adequate decisions with inadequate information.

Anonymous
16
MYCIN

• diagnostic and therapeutic proposals for patients
  suffering from infectious diseases
• IF
• 1) the stain of the organism is grampos, and
• 2) the morphology of the organism is coccus, and
• 3) the growth confirmation of the organism is
  clumps,
• THEN
• there is suggestive evidence (0.7) that the
  identity of the organism is staphylococcus.
• Example of a
  heuristic MYCIN rule.

17
(No Transcript)
18
Project Phases

• 1. knowledge representation
• formalization and representation of medical
  knowledge in a knowledge base
• 2. knowledge acquisition
• knowledge transfer from the expert to the
  computer
• (possibly contribution to standardization and
  concensus finding in medicine filling in of
  white areas in medicine)
• 3. inference method
• combining the single data of one patient with
  stored general medical knowledge
• 4. evaluation of correctness and applicability
• 5. man/machine interface and network integration

19
Medical Expert Systems

• name domain place of development
• intelligent monitoring systems
• ONCOCIN clinical oncology Stanford
  University
• intelligent control systems
• FuzzyKBWean intensive care medicine
  University of Vienna Medical School
• knowledge-based laboratory interpretive systems
• PUFF pulmonary function tests Pacific
  Medical Center, San Francisco
• SPE serum protein electrophoresis tests Rutgers
  University, New Jersey
• HEPAXPERT-I, -II, -III, -III/WWW hepatitis
  serology tests University of Vienna Medical
  School
• TOXOPERT-I, -II, ToxoNet toxoplasmosis serology
  tests University of Vienna Medical School
• clinical consultation systems
• QMR general internal medicine First Data Bank
• ILIAD general internal medicine University of
  Utah
• DXplain general internal medicine Harvard Medical
  School, Boston
• CADIAG-I, -II, -III, -IV rheumatology,
  gastro- University of Vienna Medical School
• enterology, hepatology
• RHEUMexpert rheumatology University of Vienna
  Medical School
  
• 
  
  and industry
• knowledge-based information systems

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
(No Transcript)
29
(No Transcript)
30
IF. . . an order for DIGOXIN is placed
THEN. . . The system immediately takes the
following predefined actions
The system works behind the scenes as an active
agents evaluating clinical scenarios.
Pharmacist enters medication order
Notify the ordering pharmacist of the drug
interaction and contact the requesting physician
immediately
AND The patient is already receiving FUROSEMIDE
System checks patients medication
AND
Notify the clinical pharmacist for follow-up
and documentation
AND The patients POTASSIUM LEVEL is low
rule fires
System checks patients lab results
AND
Notify the requesting physician of the situation
and suggest a potassium supplement
CONDITIONS MET
31
(No Transcript)
32
(No Transcript)
33
hemisphere
domainstructure
frontal lobe
parietal lobe
postcentral gyrus
frontal superior gyrus
precentral gyrus
domainblood supply
anterior cerebral artery
domain function
internal carotid artery
hand movement
middle cerebral artery
image volume
motorocity
34
(No Transcript)
35
Discussion

• development of medical expert and knowledge-based
  systems demands tight interdisciplinary
  cooperation (physicians, knowledge engineers, and
  programmers)
• knowledge representation schemata and inference
  mechanisms are often being developed especially
  for medical purpose
• knowledge acquisition process may contribute to
  medical methodology and theory formation
• result will then be a theoretical sound,
  practically integrated software system to improve
  individual patient care

36
Future Developments I

• integration of medical information systems,
  knowledge-based systems, and PAC systems
• global view of patient data including 2D- and
  3D-visualization
• integrated software modules for monitoring and
  alerts
• development of medical workstations with
  consultation mode
• various forms of diagnostic and therapeutic
  decision support
• WWW-based medical knowledge base server
• hospitals, practitioners, and patients
• mobile access

37
(No Transcript)
38
Health Care Procedures
Technical Informatics
Medical Technology
PHYSICIAN
PATIENT
Medical Knowledge
Medical Data
Diagnostic, Therapeutic, and Patient
Care Procedures
Documentation of Procedures
HEALTH CARE COSTS
Multimedia Patient Record
Medical Knowledge Bases
Computer-Based Health Care Billing
39
Future Developments II

• far-reaching goal
• integration of knowledge-based patient health
  care systems with cross-connection to billing and
  cost systems of health care carriers
• patients medical needs
• become transparent and substantiated

40
(No Transcript)
41
(No Transcript)