BMI 210: Modeling Biomedical Systems

• Represent information about the world for a computer to use to solve problems, I.e. diagnosing medical conditions.
• Incorporates logic to enable reasoning by the computer

• 1. Logic Programming (First Order Logic aka FOL)
• 2. Semantic Networks
• 3. Frames (a type of semantic network)
• 4. Rule-based systems

• Knowledge is stored as program code
• Usable only in a specialized problem-solving context
• Highly efficient (in the correct context)
• Used to execute functions that do things
• Examples:
•   Plan a route from Stanford → SFO
•   Find all family members of Tiffany

• Knowledge stored as propositions that must be interpreted
• Accessible for a variety of purposes
• Relatively inefficient for problem-solving
• Used to declare a certain logical statement is true or not
• Or use to declare that two objects have a certain relationship
• Examples:SFO is 30 miles from Stanford → distance(Stanford, SFO) = 30
• Tiffany and Ben are siblings → siblings(Tiffany, Ben)

you can say what you want to say

you will get all the right answers

you will get all the answers

you will get an answer

Fundamental tradeoff between being able to say what you would like to say about the world being modeled (expressivity) and knowing that inference is decidable and computationally efficient (tractability)

• Not very expressive
• Offer computationally tractable relational operations
• Look up all males under 30 with disease X

• Very expressive
• Logical inference may be computationally intractable
• Start with set of axioms and formulas that are true
• Use modus ponens to make conclusions about other formula
• Many formulas and variables can be expressive, but may be intractable to solve for all of the variables
• Might be no solution, in which case the query is “undecidable”

• 1) Frames
• 2) Description logic
• 3) first order logic

True

False

if ... then ...

rule-based systems

• Goal-driven reasoning
• Start with our final goal (e.g. Fritz is green)
• Find rules with our goal as the consequent (then clause), use the antecedent (if clause) as our new goal
• Repeat until we can prove the antecedent with our given truths

• MYCIN
• Goal: find significant disease-causing organismsUses rules to available data
• Once it finds such organisms, it attempts to select a therapy to treat the disease(s)
• Designed as a consultant for physicians - given the ability to explain both its reasoning and its knowledge

• Data-driven reasoning
• Repeated application of modus ponens
• Modus ponens
• If conditional statement if p then q is accepted, and p holds, then the consequence q may be inferred
• Search rules until we find one where the antecedent is true

• Rules offer much more flexibility in problem solving, but they do not encode inspectable models as frames do
• Rules are hard for developers to maintain
• No means to introspect the knowledge within the systems (rules)
• Rule engine cannot scan through rules to adjust them, add rules, or delete rules

• Arden Syntax
• Health e-Decisions
• MYCIN

• Markup language used for representing and sharing medical knowledge
• Rule-based system

• Rules are often “data-driven” (aka forward-chaining)
• Thus, when a physician enters new info about a patient, the system searches for rules that are relevant.

• Alert: messages for dangerous situations
• Medication interaction or dangerous lab result
• Interpretation: a non-emergency messaged designed to supply supportive information such as an interpretation of liver function tests
• Screen: message sent to clinical researchers when a patient meeting criteria for clinical trial or quality assurance concern are admitted to hospital
• Management: messages used for administrative purposes such as managing bed assignments, same day admissions and discharges from hospital

• 1. Clinical decision support artifact sharing
• 2. Clinical decision support guidance service

• Answered the question: “How can I share a really good clinician decision support rule with someone else in an electronic format, so they can use the rule in their electronic health record?”
• Focused on sharing three types of artifacts
• Event-condition-action rules
• Order sets
• Document templates

Answered the question: “How can I send important data to an up-to-date website or service that will give me advice about immunizations or other complex decisions?”

• One big criticism of rule-based systems is that they fail to capture the complexities of a patient’s situation, which might include many (potentially conflicting) symptoms and other information that needs to be consolidated into a differential diagnosis. Some more advanced systems that used rules but accounted for more complexity include:
• MYCIN: Accounted for lots of info about a patient via “Evidence Combination” and gave a differential of infectious diseases

Representation of classes, attributes, and values

concepts

nodes and relations

object-oriented models

set theory

• Offer cognitive tractability
• Class hierarchy organizes a flat knowledge base by introducing structure
• Simple, easy to understand
• Inheritance is captured in a natural, modular fashion
• Frames support efficient inference by following links

• Negation cannot be represented uniformly
• Disjunction cannot be represented naturally - Jim has either mumps or rubella
• Quantification is not a part of the language - All of Jim’s diseases are infectious
• No standard way to represent exceptions
• Assumes a closed-world assumption - Everything that is true is known to be true, therefore everything that is not stated is false

• Internist-1, and it's predecessor, Quick Medical Reference (QMR)
• FMA (Formal Model of Anatomy)

• For each internal medicine disease, the creators recorded the evoking strength, frequency, and importance of many symptoms/physical exam findings.
• This was in the form of Frames.

disease

symptoms/findings for an actual patient

user enters patient's findings

differential diagnosis

• Disease complications: Can explain diseases that may result from complications of the primary disease
• Helps to “rule in” diagnosis: Suggests additional findings that would support diagnosis, Assists in ordering additional tests

• Rules act on information stored within frames
• Left-hand side of rules refer to frames that may become instantiated at run time
• Right-hand sides of rules conclude values that alter instantiations of frames or that instantiate new frames

We can now use the rule to update our frame for Bob to have the role (data property) that he is green

most

first order logic

for all, there exists

and, or, exclusive or, implies

• Describe variables and relationships between variables
• Diagnosis(X, anemia)
• Male(Y)
• Patient(Z)

• quantifiers
• logical connectives
• negation
• predicates
• variables
• function

description logic

OWL

Web Ontology Language

• Open-world assumption: Just because something hasn’t been said yet, doesn’t mean it is not true
• Automatic classification of new concepts
• Automatic identification of redundant concepts
• Ease of customization when customers require specialized terms

description logic

• conceptual model is populated by:
• individuals
• related by binary relationships (roles and features)
• grouped into classes (concepts)

• 1. subsumption: is category C1 a subset of C2?
• 2. classification: does object O belong to C?
• 3. satisfiability: can category C ever be instantiated?

• What is not known to be true must be false
• Frame-based systems, rule-based systems, FOL

• Unstated things are unknown
• Just because someone hasn’t said it yet, doesn’t mean it isn’t true
• Description logic uses an open-world assumption

This new statement is not entailed from the current knowledgebase, but it is not contradicted by it either. Since we’re using OWL, which is based in DL, and the open­world assumption holds in DL, then we accept the new statement into the knowledgebase as true, but can’t conclude anything more about animals.

decidable fragments

Classification takes a new Concept and automatically determines all subsumption relations between it and all other Concepts in the network

true

concepts

hierarchy

inheritance relationships

specialization

roles

minCardinality, maxCardinality: Must have at least/most X values entered

discrete, clear descriptions of facts/relationships

things like multi-valued relations and probabilistic relations (or anything other than descriptions)

• A patient may have some subset of symptoms but its not clear how many of the symptoms a patient needs before they reach a diagnosis. Some symptoms may be more important than others. 
• A patient’s symptoms give clues about the probability of disease more often than they definitively denote a disease.

SNOMED-CT

• There is an object/thing in the real world (e.g. Down Syndrome)
• We have a mental concept for what that object is
• We have a symbol to represent that object and how we conceive it so that we can communicate the thought of the object to other people and to computers
• For example, it could be an instance of the class Developmental Disease and have certain symptom properties

anything used to represent any subject matter in order to help us to understand this subject matter

• Provide a good start for building a model
• Use to limit the scope of the model
• Which wine characteristics should I consider when choosing a wine?
• Is Bordeaux a red or white wine?

• Minimum Information About a Microarray Experiment
• Describes the minimum information required to ensure that microarray data can be easily interpreted and that results derived from its analysis can be independently verified.
• The ultimate goal of this work is to establish a standard for recording and reporting microarray-based gene expression data, which will in turn facilitate the establishment of databases and public repositories and enable the development of data analysis tools.

• Elements of EHR
• Dr. Larry Weed
• Created new model based on patient problems
• 1971

• S: subjective data
• O: objective data
• A: assessment
• P: plan
• Every problem is numbered
• Description of problem may change over time with new information
• Number for each problem never gets recycled

ICD-10, ICD-10-CM, DRG

CPT-5, ICD-10-PCS

LOINC

NIC, NOC, HHCC, Omaha

Multum, Micromedex, NDFRT

MeSH

Medcin, Purkinjie

UMLS

A systematically organized collection of medical terms providing codes, terms, synonyms and definitions used in clinical documentation and reporting.

description logic

ICD code

• Disease surveillance and public health
• Institutional planning
• Quality assurance
• Economic modeling
• Billing and reimbursement

• Provides a code for every type of medical procedure
• Relationships between codes are implicit
• Example: Code 93571 codes for an intravascular doppler measurement during a coronary angiogram. Then Code 93572 is the code for each additional vessel that you measure after measuring the first one. The definition of Code 93572 does not make any explicit mention of Code 93571...it’s just implied.

• Standardized terminology for lab tests
• Codes enumerate highly structured attributes of laboratory observations (e.g., substance measured, analytical method used)
• No hierarchical organization

provides a way to unify all of the other ontologies (diseases, procedures, lab tests, etc)

imprecise

Concept Unique Identifier (CUI)

Health Level-7 or HL7 refers to a set of international standards for transfer of clinical and administrative data between software applications used within a give hospital...lets a health system share data across its domains

• The models and messages were too complex - Average HL7 V3 message had 5–10 times the number of XML nodes as messages in other industries
• The RIM tried to model everything, with maximum extensibility and generality
• The standard lacked a useful mechanism to add extensions
• Documentation was poor

Version 3 RIM

• "80/20"
• make life simpler for implementers, rather than for modelers

• modular
• "Resources"
• Small contained model
• Concepts related to a particular thing
• e.g. medication prescription, adverse reaction
• Discrete, but may reference one another, forming a graph

"profiles"

within

it can be shared with another health system

• How to package up composite information for transfer *across* institutions?
• Mobilization of patient data electronically across regions, communities, or health-care organizations
• Enables exchange of information across disparate information systems
• Goals are
• To enable more coordinated, timely, efficient care
• To aid public health reporting and clinical research

a clinical document

RIM

within and between

XML-based language,

RIM and from controlled terminologies

HL7 International and ASTM.

allowing physicians to send electronic medical information to other providers without loss of meaning and enabling improvement of patient care.

Continuity of Care Document

HL7 Version 3 Clinical Document Architecture (CDA)

• formal specification of a shared conceptualization
• Conceptualization: the way we think about a domain
• Specification: formal way of writing it down

• lexicon
• simple taxonomy
• thesaurus
• relational model
• fully axiomatized theory

vocabulary, possibly with natural-language definitions

terms with class-subclass relations

taxonomy plus related terms

unconstrained use of arbitrary relations

upper-level ontology

• Share common understanding of the entities in a given domain - Among people, software agents, between people and software
• Enable reuse of data and information - Introduce standards to allow interoperability and automatic reasoning - Create communities of researchers

• patients - chronically ill, acutely ill
• care providers - doctors, nurses
• notes - histories, updates

• care providers write notes
• doctors have patients
• notes pertain to patients

Ontology that consists of very general terms (such as “object”, “property”, “relation”) that are common across all domains

• Support broad semantic interoperability among a large number of domain-specific ontologies
• Provides a common starting point for the formulation of definitions
• Domain ontology terms are ranked under terms of upper ontology - I.e. upper ontology classes are superclasses or supersets of all classes in domain ontologies

• Upper-level classes provide a useful organizing structure
• Upper-level classes minimize the chance of category errors
• Standard upper-level ontologies aid alignment and reuse across ontologies

• Small, upper level ontology
• Designed for supporting information retrieval, analysis and integration in scientific and other domains
• Does not contain physical, chemical, biological or other terms that fall within domain ontologies

definitions should be objective and complete

• Ontology should sanction those inferences consistent with the definitions
• No concepts exist that are unsatisfiable (interpreted as a empty set)

Should anticipate future uses

No assumptions about knowledge representation

Say no more than is necessary

• Determine the scope that your ontology needs to cover - Consider how it will be used and how it might need to be used in the future when deciding how detailed you want it to be. 
• Enumerate the terms that need to be covered by the ontology
• Define your classes (concepts)
• Define the roles (aka data properties and object properties) of each class
• Define constraints for these properties
• Create instances

• Gene Ontology (GO)
• Foundational Model of Anatomy (FMA)
• MYCIN
• INTERNIST-1/QMR

• 1. molecular function - elemental activity or task, DNA binding
• 2. cellular component - location or complex, cell nucleus
• 3. biological process - goal or objective within cell, secretion

• Suggesting biological process associated with expressed genes
• Enables analysis of how genes cluster together based on functional properties
• Using gene annotations to custom-design microarrays based on biological processes of interest

• Knowledgebase of anatomy information
• Well-developed

Explicitly

frame hierarchy - Concepts, attributes, relations

upper-level ontology - Anatomical spatial entity, anatomical structure, body substance

• rule-based system
• certainty factors and backward chaining

a translation of a rule that has the parameter in its premise

• frame-based system
• its own brand of ad-hoc system (ranking algorithm, heuristic rules)

hypothetico-deductive reasoning as performed by human experts (considered the importance and frequency of each symptom in relation to each disease to rank diseases in a differential diagnosis)

• a Bayesian Belief Network
• They mapped the frequency rankings (1 to 5) in the ad-hoc system to conditional probabilities so that they could get P(symptom | disease)

• UML
• Common Logic
• Web languages - XML, OWL

• Entities are not defined at useful levels of abstraction - Necessary to distinguish between mammals and dogs?
• Entity definitions are overloaded - Helpful to have the class red bicycle?
• Hierarchical relationships are not uniformly taxonomic - Amino acid is a descendant of protein

a weak theory

ontological commitment

concepts represented

any specific application

The subject area of a system (e.g. infectious diseases)

Activities within a domain that a system performs (e.g. diagnosis)

The procedures used to carry out the tasks (e.g. classification)

• Characterize the overall task
• Identify a method that solves that task, entailing any number of subtasks
• For each subtask, identify a method that solves that subtask
• Terminate when there is a well-described method for solving each subtask

Heuristic classification is suitable for classification problems in which it is known from experience which observations— or combinations of observations — indicate intermediate or final solutions, and with what degree of certainty.

• In order to accomplish a big, complex task, you need to break it down into sub-tasks that can be solved with the PSMs that you have. 
• 1. Identify the task you want to accomplish
• 2. Create a PSM that can solve it
• 3. Identify the sub-tasks that must be solved to accomplish the PSM
• 4. Create the PSMs necessary to accomplish the sub-task...
• The result is a structure that defines how problem solvers should be invoked

• To help conclude a diagnosis of which you are suspicious
• SpPIn
• Specific test when Positive, rules In

• To help to determine that an unlikely diagnosis is not present
• SnNOut
• Sensitive test when Negative Rules Out

Resulted from a mistrust of Bayesian statistics

(Certainty factors, fuzzy logic)

• Adopts a measure of belief that ranged from -1.0 (complete falsehood) to +1.0 (complete truth)
• Requires each rule to include a certainty factor for its conclusion
• Requires the runtime system to update the CF for a proposition dynamically as each rule fires
• Requires threshold for acceptance or rejection of a proposition

• Does not overcome the conditional independence assumption - Highly related findings (e.g. fever, chills, and sweats) all individually increase posterior probability of disease (eg influenza)
• Assessing “correct” CFs is difficult - There is no direct translation from statistical data to CFs
• Developers assigning CFs have a tendency to conflate probabilistic values with other considerations - I.e. more important conclusions may be assigned higher CFs

• Truth is not binary but a continuous value between 0 and 1
• Reflecting the degree of membership in a fuzzy set
• Goal is to infer degree of truth
• Unlike probability theory, where goal is to determine likelihood of situations
• Process of fuzzification
• Converts numerical values into confident levels for membership in a fuzzy set

• Disease in the differential diagnosis are assumed to be mutually exclusive
• Differential diagnosis is assumed to include the correct diagnosis (complete)
• Observations supporting the diagnosis are assumed to be conditionally independent when seen in the setting of any of the diseases in the differential diagnosis

• conditional dependencies
• conditioned

• Users enter the state of those nodes for which the state is known (e.g., person went to Honey-Baked Ham)
• Algorithm calculates the posterior probability of all possible states of the remaining nodes (e.g., patient has swine flu)
• If no state values are entered, then the initial probability of each value of each node is simply the prior probability

• Markov Logic (the kind of logic used in Bayesian reasoning) is probabilistic. Therefore, you can have two opposing statements that each have some probability of being true
• In a traditional FOL knowledgebase, every statement must be true (with probability one, so to speak), so having two opposing statements would make the knowledgebase incoherent.

• Producing the correct diagnosis? -At the top of the list of candidates? - Somewhere within the list of candidates?
• The “quality” of the differential diagnosis?User acceptance/satisfaction?
• Amount of use of the system?
• Appropriate management suggestions?

• Is there a need for it?
• Does it work?
• How fast does it work?
• Does it work reliably?
• Do people use it?
• Which parts cause which effects?
• How can it be improved?

• Do people like it?
• Does it improve efficiency of performing some task?
• Does it improve accuracy of performing some task?
• Does it influence the collection of data?
• Does it influence users’ decisions
• Does it affect third parties (e.g., patients)
• How long do the observed effects last?

• Formative: How can be build better systems?
• Summative: What can we conclude about a system that has been built?

• What can we measure and compare about a system?
• Quantitative or hard research

• Logical-positivist perspective
• Assumes that questions can be answered in terms of attributes and can be measured
• Assumes that rational people can and should agree a priori what attributes are important to measure
• Assumes that precise numbers are better than imprecise verbal descriptions

Can be relatively easy to do

May not measure the most important results

• peer review
• difficult
• Anonymous computer or human recommendation
• Limitations
• Relatively few cases and evaluators but still arduous to conduct
• Says nothing about usability
• Claims that expert-level performance was meaningless
• System could not fit into real clinical workflow, despite excelling expert-level performance

• What can we infer from observation of a system
• Qualitative or pejoratively, soft research

the observer

context