“Expert” Knowledge Module

8/14/2019 Expert Knowledge Module

1/67


2/67


3/67

One Definition of Expert System

A computing system capable of representing andreasoning about some knowledge rich domain,

which usually requires a human expert, with aview toward solving problems and/or giving

advice.

the level of performance makes it expert

Some also require it to be capable of explaining its

reasoning. Does not have a psychological model of how the

expert thinks, but a model of the experts model of

the domain.


4/67

Categories of Expert Systems

Category Problem AddressedPrediction Inferring likely consequences of given situations

Diagnosis Inferring system malfunctions from

observations, a type of interpretationDesign Configuring objects under constraints, such as

med orders

Planning Developing plans to achieve goals (care plans)

Monitoring Comparing observations to plans, flaggingexceptions

Debugging Prescribing remedies for malfunctions

(treatment)Repair Administer a prescribed remedy

Instruction Diagnosing, debugging, and correcting studentperformance

Control Interpreting, predicting, repairing, andmonitoring system behavior


5/67

Knowledge in a Knowledge Base

Knowledge specific to the domain + facts specific to the problembeing solved

A medical KB is defined in HANDBOOK of MEDICAL INFORMATICS as:

a systematically organized collection of medical knowledge that is accessible

electronically and interpretable by the computer. They note a medical KB usually:

includes a lexicon (vocabulary of allowed terms) and

specifies relationships between terms in the lexicon.

For example, in a diagnostic KB, terms might include: patient findings (e.g., fever or pleural friction rub),

disease names (e.g., nephrolithiasis or lupus cerebritis) and

diagnostic procedure names (e.g., abdominal auscultation or chest computedtomography).

Knowledge Representation is the key issue Aim is usually to present the knowledge in as "declarative" a fashion as possible


6/67

Traditional Feature Comparisons:

E/KBS versus ANNE/KBS Symbolic

Logical Mechanical

Serial

Rule Based

Needs Rules

Much Programming Requires Reprogramming

Needs an Expert

Neural Networks

Numeric

Associative Biological

Parallel

Example Based

Finds Rules

Little Programming Adaptive System

Needs a Database

But much of this too simple, KBS are not really logical and can use examples etc.


7/67


8/67

Medical Expert and KB systems

are designed to give expert-level, problem-specific advice inthe areas of :

medical data interpretation, patient monitoring,

disease diagnosis,

treatment selection, prognosis, and

patient management.

Research in medical expert and knowledge-based systemsand the development of such systems has been mostsignificant to the broad realm of quality assurance and cost

containment in medicine.


9/67

One Distinction Between an Expert System

and a Knowledge-Based System

To be classified as an expert system the systemmust be able to explain the reasoning process.

This is often accomplished by displaying the rules

that were applied to reach a conclusion.


10/67

Some Basic Concepts

Knowledge representation deals with the formal modeling ofexpert knowledge in a computer program. Important questions in this respect concern the given degree of

structuralization of the medical domain under consideration, the necessity to

include vagueness of medical terms and uncertainty of medical conclusionsinto the chosen formal representation, as well as the extent and completionof the respective knowledge domain.

Reasoning mechanisms are inference methods which draw

medical conclusions from given patient data by means of thestored medical knowledge. Most important is the selection of the appropriate formal approach with

respect to the given medical domain.

One differentiates methods to infer logical conclusions (e.g., propositionaland predicate logic, three-valued logic, fuzzy logic, non-monotonic logic)and to combine medical evidence (e.g., Bayes theorem, certainty factors,Dempster-Shafer theory of evidence).


11/67

Assertional Knowledge

It might be a detailed description of a complex domain

like a disease, a linguistic structure, etc.

This type of knowledge is used to describe a givenclinical situation usually in an object structure.

This is done by associating the different elements or

objects characterizing the context inside the same

framework with the consideration of the relationships

between these objects.

Example: an exhaustive description of a specific disease

organized following: the set of its symptoms, its possible

treatments, medicines, etc.


12/67

Alternative KB Approaches

Rule-based approach

Events trigger firing of rules (condition/action pattern)

e.g. Arden Syntax and Medical Logic Modules (MLM)

Case & Model-based approach

Create a model (template) of clinical guidelines e.g. PRODIGY, EON, PROforma, GLIF


13/67

But AI is a broad field - a tree representation


14/67

Knowledge-base may really include many things

Knowledge-base

HeuristicsHypothesis Rules

Facts

Processes

Events

DefinitionsRelationships

Attributes

Objects


15/67

user

KBS Editor

Inference Engine

Explanation System

GeneralKnowledge-Base

Case SpecificKnowledge-Base

User Interface

may employ:

question &

answer

menu-driven

natural

language, or

GUI styles

KBS architecture and components

Knowledge Acquisition

Module


16/67

Knowledge representation formalisms

& Inference

KR Inference* Logic Resolution principle

* Production rules backward (top-down, goal directed)

forward (bottom-up, data-driven)

* Semantic nets &

Frames Inheritance & advanced reasoning


17/67

A Representation: First-Order Logic

Constants: Mr_Smith, Dr._Jones, anemia

Variables: X, Y

Functions: Address(X), Age(Y)

Predicates: Diagnosis(X, anemia); Male(Y); Patient(Z)

Negation: Male(X); Name(X, Smith)

Connectors:

Conjunction (AND): Patient(X) Male(X) Disjunction (OR): Doctor(X) Nurse(X)

Logical implication: Female(X) Male(X)

Quantifiers: Universal quantifier: X (Patient(X) Doctor(X))

Existential quantifier: Y (Patient(Y) Name(Y, Jones))

From Yuval Shahar, Frame-Based Representations and Description Logics

Temporal Reasoning and Planning in Medicine


18/67


19/67

Relationship Of this K to a DB

Representing patient X has Diabetes in a table:

Diabetes (x)

A table called Diabetes with column (s) identifyingpatient x and a column of the value of Diabetes (x)

Has_Diagnosis (x, Diabetes) A table called Diagnosis with column (s) identifying

patient x, and diagnosis y and a column of the value of

Has_Diagnosis (x, y) Has (x, Diagnosis, Diabetes)

A table called observation with column (s) identifying

patient x, observation type y and observation value z

and a column of the value of Has x z


20/67

Experts typically form sets of rules to apply to a givenproblem

Set of rules reflects the skill of the expert on a topic; usedifferent rule sets to reflect problem-solving competenceof expert

Need a strategy to know when to apply them ie use metarules

Rule sets often represented in a tree-like structure withmost general, strategic rules at the top of the tree; mostspecific rules at leaf nodes

Adopts a top-down approach to problem-solving, whererule sets only used when appropriate; reflects human approach divide and conquer

eases modular development each module may use different representation and reasoning

techniques (say for body system)

Production Rule sets


21/67

21

Rules & Decision Tree Example

Q1: Test is

Q3: the

Cost is

Q2: the

Panel cost

is

Q3: the

cost is

Q3: the

cost is

Q3: the panel

cost is

c1: 30%

chance

Rule 1

c2: 70%chance

Rule 2

c3: 10%

chance

Rule 7

c2: 70%

chance

Rule 8

c1: 30%

chance

Rule5

c2: 70%

chance

Rule6

c1: 30%

chance

Rule3

c2: 70%

chance

Rule 4

included

2K 3K 4K

=x24hrs) to determine bacterial species

Classified as a "production- rule" system, depth-first, backwardchaining.

Given patient data (incomplete & inaccurate) MYCIN gives interimindication of organisms that are most likely cause of infection &drugs to control disease

Uses certainty factors to handle incomplete and uncertain information, includedthe "how" and "why" capabilities that are now considered essential, definingcharacteristics of Expert Systems.

Drug interactions & already prescribed drugs taken into account

Able to provide explanation of diagnosis (limited) Thoroughly documented in Buchanan and Shortliffe Rule Based Expert

Systems, Addison- Wesley, Reading, Mass., 1984.


23/67

Top-level goal rule

IF there is an organism which

requires therapy, and

consideration has been given

to the possibility of additional

organisms requiring therapy

THEN compile a list of possibletherapies, and determine the

best therapy in this list.


24/67

THERAPY rule

IF the identity of the organism

is Pseudomonas

THEN I recommend therapy fromamong the following drugs:

1 - COLISTIN (.98)2 - POLYMYXIN (.96)

3 - GENTAMICIN(.96)

4 - CARBENICILLIN (.65)

5 - SULFISOXAZOLE (.64)


25/67

THERAPY rule

The number with each drug is the akin to the

probability that a Pseudomonas will be sensitive tothe named drug.

To select the actual therapy, the drugs on the list are

screened for contra-indications and to minimize the

number of drugs administered, while maximizing

sensitivity.

T i l RB E i


26/67

Typical RB Exercise:

Write Rules by Diagnosis

Write rules for patients with the following

diagnoses (one at a time):

diabetes mellitus

heart failure

myocardial infarction benign prostatic hyperplasia

K Engineer compares notes and leads discussion on integration.


27/67

Evaluation of MYCIN

In 1974, an initial study of MYCIN was conducted

where five experts approved 72% of MYCIN's

recommendations on 15 actual cases.

The system was improved and in 1979 MYCIN was

again compared to experts.


28/67

MYCINs Performance Compared to

Human ExpertsMYCIN 52 Actual

Therapy

46

Faculty-1 50 Faculty-4 44

Faculty-2 48 Resident 36Inf. Dis

fellow

48 Faculty-5 34

Faculty-3 46 Student 24

Ratings by 8 experts on 10 cases

Perfect score = 80


29/67

MYCIN is not currently in use:

Knowledge base is incomplete, does not cover a fullspectrum of infectious diseases.

computing power was not available in most hospitalwards.

MYCIN's development lead to the development of

"EMYCIN" - for "Empty MYCIN". To demonstrate this capability, they developed "EMYCIN",

the first shell.

The developers of MYCIN believed that the programmingapproaches they used in MYCIN could be applied to otherdomains.


30/67

1 The need justifies cost.

2 The (human) expertise* is not available in allsituations where it is needed.

3 The problem may be solved using symbolicreasoning techniques.

4 The domain is well structured and does not requirecommon sense reasoning.

5 The problem may not be (better) solved using other(traditional) computing methods.

6 Cooperative and articulate experts exist.

7 The problem is of proper size and scope. This isrelative to resources and evolving technology.

What makes an ES feasiblefeasible ?

Life Cycle for Developing Expert


31/67

Life Cycle for Developing Expert

Systems

Problem Definition


Knowledge Representation

Prototype system

Operational system

Knowledge base maintenance


32/67


33/67


" the transfer and transformation of potential

problem-solving expertise from some knowledge

source to a program.

- Buchanan 1983.

machine learning - building capabilities into the

system that allow it to learn from what it is doing. the problem of induction - how many instances must be

observed before it can be added to the knowledge base

as "true"


34/67

knowledge elicitation - extract the

knowledge from the human expert, throughsome means

direct - interaction with the human expert

interviews, protocol analysis, direct

observation, etc.

indirect - utilize statistical techniques to analyzeof data and draw conclusions about the

structure of the data.

Knowledge Acquisition (cont.)


35/67


A method to represent the knowledge you are

eliciting and/or learning. Several major methods rules, bayes nets, frames

Strengths and weaknesses for each. None is completely dominant.

Trent is to build heterogeneous systems, that s whatexperts are.


36/67


A method to represent the knowledge about thedomain

Three major symbolic methods: rules

semantic objects

logic Although a shell contains a way to representknowledge, shell selection should be influenced

by the matching the representation to theknowledge in the domain.

Knowledge must be coordinated, so that the

knowledge base is consistent.


37/67

Prototype system

Typically use an "incremental" development

approach to an expert system.

Build an initial prototype and adjust and expand Allow the expert to interact with the prototype to

get feedback

Reevaluate if the project should be continued,

if major redesign (knowledge representation)

is necessary, or to go ahead.

Build Operational System & Knowledge base


38/67

Build Operational System & Knowledge base

maintenance

Once The actual system is built

New rules can be continually added and old ones

refined/ removed.

This is a tricky process, but there does not

seem to be much literature on it. One characteristic of an Expert system should

be maintainability, so the ability to

add/change/delete rules is essential.

M di l K l d ( dj i i i )


39/67

Medical Knowledge (Adjusting to Situations)

Biochemical lab rulesGo from simple, modular to confusing complications

From Toward Situated Knowledge AcquisitionTim Menzies,

Int. J of Human Computer Studies, 1998


40/67

Disadvantages of Production Knowledge

Difficult to maintain for Very Large-KB- One reason is addition of new, contradictory knowledge. Consider

Rule 1. IF it is raining

THEN not (weather is sunny)Rule 2. IF location is Florida

THEN not (weather is cloudy)

Rule 3. IF it is late afternoon

THEN weather is sunny or weather is cloudy

FACTS: it is late afternoon location is Florida

Conclude?????

Maintenance is to ADD Rule 4. IF it is late afternoon AND location isFlorida

THEN it is raining

Some observe that RB development never ends.KE is a continuousprocess..


41/67

KBS as real-world problem solvers

- Problem-solving power does not lie with smart reasoning

techniques nor clever search algorithms butdomain dependent real-world knowledge

- Real-world problems do not have a well-defined

solutions in literature- Expertise not laid down in algorithms but are domain

dependent rules-of-thumb orheuristics (cause-and-effect)

- KBS allow this knowledge to be represented incomputer & solution explained

These are not logical

A Semantic Network beyond the ERA


42/67

A Semantic Network beyond the ERA

model for real world problems

A directed graph of vertices (V)and edges (E)

where Vi are concepts and Ei,j are relations

Jim

PersonIS-A

Disease

5 Days

Mumps

Has

Duration

DiagnosisPatient

27 years

Age

MamalAKA

Focus is on

categories of objects

relations between those obj

Semantic Networks:


43/67

Semantic Networks:

Arity of Relations

Unary relations

Person(Jim): IS-A link

Binary relations

Age(Jim, 27 years): Age link

N-ary relations Disease(Jim, Mumps, 5 days): By creating a reified

disease-relation object with several cases (patient,diagnosis, duration)


44/67

Frames

(Minksy, 1975)

A type of Semantic network

Both can be used to represent logic systems

Used to graphically represent taxonomies of

objects and their properties Concepts have roles, or properties, (also

known in OOLs as slots), such as age

Frames encapsulate more meaningful

chunks of knowledge (e.g., birthday party)


45/67

Representing Knowledge in Frames

1. Frame Architecture

- A record-like data structure for representing stereotypical

knowledge about some concept or object (or a class of objects)

- A frame name represents a stereotypical situation/object/process

- Attributes or properties of the object also called slot

- Values for attributes called fillers,facetsprovide additional

control over fillers.

Frame Name:

Class:

Properties: Property 1 Value 1

Object 1

Object 2

Property 2 Value 2

...


46/67

(1) Class Frame

- Represents general characteristics of common objects- Define properties that are common to all objects within class

- Static & dynamic property

Static: describes an object feature whose value does not changeDynamic: feature whose value is likely to change during operation

Frame Name:

Class:

Properties: Color Unknown

Bird

Animal

Eats Worms

No._Wings 2Flies True

Hungry Unknown

Activity Unknown

Types of Frames


47/67

Subclass Frame- Represents subsets of higher level classes or categories

- Creates complex frame structures

- Class relationships

Bird

Robins Canaries Sparrows

Bird1 Bird2 Tweety Bird3 Bird4

Class

Subclass

Instance


48/67

Anything

AbstractObjects Events

Sets NumbersRepresentational

Objects

Intervals

Places

Physical

Objects

Processes

Categories

Sentences Measurements

Moments

Times Weights

Things Stuff

Animals Agents

Humans

A Quick Ontological View

M di l E titi Di ti (MED) St t


49/67

Medical Entities Dictionary (MED) Structure

MedicalEntity

Substance LaboratorySpecimen Event

LaboratoryTest

LaboratoryProcedure

CHEM-7PlasmaGlucose

Plasma

Specimen

Anatomic

Substance

Bioactive

Substance

Glucose

Plasma

Chemical

Carbo-

hydrate

Substa

nce

Sample

d

Part of

HasS

pecimen

SubstanceMeasur

ed

Diagnostic

Procedure

Multiple hierarchy

SynonymsTranslations

Semantic links

Attributes

60,000 concepts


50/67

1. Generalizations ---- Kind of relationship

Bird

Robins Canaries Sparrows

Kind of links

2. Aggregation ---- Part of relationship

Bird

Wings Feather Eyes

Part of links

3. Association ---- Semantic relationship

Bird owns

Nest Food

Semantic links


51/67

(3) Instance Frame

- Represents specific instance of a class frame- Inherits properties & values from the class

- Able to change values of properties & add new

propertiesFrame Name:

Class:

Properties: Colour Yellow

Tweety

Bird

Eats Worms

No._Wings 1

Flies FalseHungry Unknown

Activity Unknown

Lives Cage


52/67

3. Frame Inheritance

Color Unknown

BirdClass Animal

Eats Worms

No._Wings 2Flies True

Hungry Unknown

Activity Unknown

Color Black-white

Penguin

Class Bird

Eats Fish

No._Wings 2

Flies False

Hungry Unknown

Activity Unknown

Lives South_pole

Color Unknown

Canary

Class Bird

Eats WormsNo._Wings 2

Flies True

Hungry Unknown

Activity Unknown

- Instance frame inheritsinformation from its subclass

frame and also its class.

- Inheritance of behavior, facet

-Ease coding & modificationOf information

A Frame Representation-types and


53/67

A Frame Representation types and

instances and defaults.

Mammals

Humans

Jim

AKA

IS-A

Legs: 2

Age:27

Legs: 4

John

Age:16

IS-A

Lions

AKA

Bats

AKA

Legs: 2

Bibi

IS-A


54/67

Implications of Inheritance

Determination of properties of instances

involves a search of the semantic-network

graph

Default reasoning is enabled

high-level nodes can have values that areinherited by many lower-level nodes unless these

values are overridden

Exceptions imply a nonmonotonic logic

Multiple inheritance is possible, but might be

ambiguous when conflicts occur


55/67

- Exception handling- Frame has property value unique to itself must be explicitly encoded

-Multiple inheritance

- It is natural to discuss objects as they relate to different worlds

- An instance can inherit information from different parent- Frame structure takes form of a network

MenAge Unknown

Weight Unknown

EmployeePhone Unknown

Salary Unknown

Jack

Age 30

Weight 78kg

Phone 123456

Salary 12345

4. Facets


56/67

- Provide additional control over property values & operation of

the system- Constraint on property values

limit a numeric property value to a range

restrict data type to Boolean, string or numeric

- Instruction to a property how to obtain value or make reaction tochanged value

- Types of facets

- Type: defines the type of value that can be associated with the property- Default: defines a default value

- Documentation: provides a documentation of the property

- Constraint: defines the allowable values

- Minimum cardinality: establishes the minimum number of values aproperty can have

- Maximum cardinality:

- If-needed: specifies action to be taken if the propertys value is needed

- If-changed: ... changed


57/67

6. Rule interaction

- Hybrid system: combine frames and rules for KR- Pattern matching, variables are used for locating matching

conditions among all frames, ?X, ?Age

Humans

Jack

Legs 1

Age 35

Sex Male

Residence Belfast

Sports Swim

Likes Unknown

Lucy

Legs 2

Age 30

Sex Female

Residence Belfast

Sports Hiking

Likes Unknown

Bob

Legs 2

Age 33

Sex Male

Residence Dublin

Sports Hiking

Likes Unknown

Frame ?X

instance-of HUMANSWITH Residence = Belfast

WITH Age = ?Age

Frame: JACK

instance-of HUMANSResidence = Belfast

Age = 35

Frame: Lucy

instance-of HUMANSResidence = Belfast

Age = 30

Populating a frame :Example


58/67

Populating a frame :Example

Frame: patient

Attribute1: Patient Name.Associated action: ifthe name is unknown

then create a new folder if not, take the

already existing folder.Attribute2: current date.

Associated action: if the patient is known

then calculate the time interval from the lastvisit.

Etc.


59/67

Advantages of Frames

Classes and instances organize a flat

knowledge base (unlike FOL) by introducing

structure on an epistemological level E.g., specialization of subclasses through

restriction of a range of values for a property

Simple; easy to understand

Inheritance is captured in a natural, modular

fashion

Efficient inference (e.g., for validation) by

following links, compared to standard logics


60/67

Problems with Frames

Negation cannot be represented

Jim does not have pneumonia

Disjunction cannot be represented naturally

Jim has Mumps or Rubella

Qualification is not a part of the language

All of Jims diseases are infectious

=> Thus, procedural attachments are often added

The semantics of the links are often not well

defined [Whats in a Link, Woods, 1975]


61/67

- Disadvantages:

Departures from prototypesAccommodation of new situations

Detailing heuristic knowledge

Rule-based Frame-based

Rule 1 Frame - BoilerIF Boiler pressure < 50 Temperature

AND Boiler water level < 3 Water level

THEN Add water to boiler Condition

Rule 2 IF Boiler:Temperature>300

IF Boiler temperature > 300 AND Boiler:Water_level >5

AND Boiler water level > 5 THEN Boiler:Condition = normal

THEN Boiler condition normal


62/67

7. Summarizing Advantages & Disadvantages

(Frames vs. Rules)

Features Rule-based Frame-based

Organization of facts scattered in KB related facts collectedandknowledge (but easy to add) represented within a single frame

Inheritance no inheritance Yes-a frame trade-mark

Inference process general rules & PM general rules & pattern matching

can be slow PM fast

Objects Facets & Message-Passingcommunication


63/67

The Advanced Course: Description

Logics

A subset of FOL designed to focus on

categories and their definitions in terms of

existing relations

More expressive than semantic networks

Major inference tasks:

Subsumption (is category C1 a subset of C2?) Classification (Does Object O belong to C?)

C iti l F t i M DDS F il


64/67

Critical Factors in M-DDS Failures

(after Berner, Luger and Stubblefield) Impossibility of developing an adequate database

Lack of an effective set of decision rules (no end)

Lack of deep (causal) knowledge of the domain (i.e.

systems do not understand physiology)

- Lack of robustness & flexibility. If the knowledge base is

unable to deal with a problem or query not contained

within it, it is unable to resolve or adapt a strategy.

- Unable to provide deep explanations

- Problems in verification

- DSS, in general (unless allied in a hybrid to a CBR, classifier

or neural networks) do not learn from their experience

Arden Syntax and Medical Logic Module


65/67

Arden Syntax and Medical Logic Module

EMYCIN has been used successfully to develop other systems.

But has been overtaken by other approaches such as MedicalLogic Modules. An industry standard maintained by Health Level 7 Org

Organize decision knowledge as a collection of procedural rules(MLMs) that can be triggered by events

Each MLM designed to model knowledge required to make asingle medical decision such as:

Contraindication alerts, management suggestions, data interpretations,treatment protocols, and diagnosis scores

Complex things such as guidelines represented as a collection ofMLMs


66/67

Summary

There are multiple representation formalisms

Frames are a type of semantic networks

A fundamental tradeoff exists in all

formalisms [Levesque and Brachman, 1984],between:

1. Expressive power of a representation language 2. computational tractability of inference with it

References


67/67

References

Yuval Shahar, Frame-Based Representations and Description Logics Temporal Reasoning and Planning in Medicine

http://www.ise.bgu.ac.il/courses/trp/1,

Documents

“Expert” Knowledge Module