Introduction and Overview

photofitterInternet και Εφαρμογές Web

4 Δεκ 2013 (πριν από 4 χρόνια και 5 μήνες)

94 εμφανίσεις

Computational Intelligence in
Biomedical and Health Care Informatics

HCA 590 (Topics in Health Sciences)

Rohit Kate

Introduction and Overview

Course Information

Course Website:

D2L course site will be also used for:

Posting some readings

Submitting homeworks and assignments

Course Information

Textbook: No single book covers all the topics we
want to cover

Main text:
From Patient Data to Medical Knowledge: The
Principles and Practice of Health Informatics
by Paul Taylor,
BMJ Books, 2006.

Covers many topics that we want to cover (especially its Part 2)
and is focused on their medical applications

We will not cover the entire book

Other readings will be made available through D2L site

Course Information


4 assignments (60%)

Doing some specific task using tools or software that
we will cover in class



Submit answers to questions if given at the end of the
class (last slide) before the next class (through D2L)

Final project (30%)

Come up with your own project based on the topics
covered in the class

Introduction and Overview:

Chapter 1, Artificial Intelligence: A Modern
Approach by Stuart Russell and Peter Norvig

Paper: Ramesh et al.
Artificial Intelligence in

Ann. R. Coll. Surg. Engl. 2004

Slides Overview

Computational Intelligence

Computational Intelligence in Medicine

Course Information

What is Computational Intelligence?

Intelligence, generally speaking, is the ability to do the
right or the best thing in a given situation to achieve a

Humans and some animals exhibit intelligent behavior


is the capability of a
computer to exhibit intelligent behavior

A chess playing machine

A robot or a car that finds its way around

A computer that answers natural language questions about a

A computer that diagnoses a patient from the symptoms


What is NOT Computational

Word processing softwares

Graphics design using computers

Entering or searching for an entry in a

Computer networks, Internet protocols

Computer security

These tasks require data processing but do not
require the computer to be intelligent.

Computational Intelligence as a

A traditional discipline of Computer Science

More commonly known in Computer Science as “Artificial
Intelligence” or “AI”


Intelligence may seem to suggest that the
intelligence is not real or is just a simulation of human

The term creates misunderstanding outside of Computer

“Computational Intelligence” is perhaps a better term and
seems to be preferred in Biomedical disciplines

We will use both the terms in the course interchangeably

Definitions of Computational

Various definitions are around ranging from
philosophical to engineering perspectives

Machines with minds…

Study of design of intelligent agents

A study of duplicating human faculties like
creativity, self
improvement and language use.

A good working definition: Study of how to make
computers do tasks at which currently humans are
better (Rich and Knight, 1991)

What Makes Humans

Knowledge (knowing facts about the world)

Reasoning (ability to derive conclusions)

Learning (improving through experience)

Language and Perception

All these are reflected in the major sub
of Computational Intelligence or AI

Different Sub
Areas of AI

Knowledge Representation and Reasoning

How to encode knowledge so that computer can
reason about it

order logic,
, rules, knowledge

Handling uncertain knowledge, probabilistic reasoning

Example application in medicine: Encode
knowledge about diseases, symptoms to
automatically predict diagnosis

Different Sub
Areas of AI

Machine Learning

Improve performance by learning from examples

Humans do it all the time (learn to walk etc., develop
special skills)

based methods: e.g. decision

Statistical methods: e.g. neural networks, support
vector machines, maximum entropy models

Example application in medicine: Learn to
diagnose a disease from previous examples of
patient data

Different Sub
Areas of AI

Computer Vision

“Eyes of computer/robot”

Recognize objects (e.g. face, human) from an image
(e.g. face detection by cameras)

Reconstruct a 3D model from 2D images, e.g. track an

Example application in medicine: Distinguish
between a cancerous from a non
radiology image

Different Sub
Areas of AI

Natural Language Processing

Understand and process natural languages like
English, Chinese etc.

Natural language is the preferred medium of
communication for humans

Follow natural language commands

Answer natural language questions

Find required information from several documents

Translate from one natural language to another

Example application in medicine: Answer clinical
questions using a repository of research articles

Different Sub
Areas of AI


Physical agents that act in the physical world

Example application in medicine: Surgical robots


Coming up with a best sequence of inter
dependent tasks to perform (e.g. wear socks
before shoes)

Example application in medicine: Planning and
scheduling in a hospital environment

Foundations of AI

AI is extremely inter
disciplinary; its foundations
come from several older disciplines


Where does intelligence come from?


How to infer logically? How to reason under uncertainty?


How should we make (intelligent) decisions that maximize payoff ?


How do brains process information?


How do humans and animals think and act?


How does language relate to thought? How do we process

How to Make Computers

Should we model human intelligence

A good idea but difficult to model

Human brain is different from computer processor

Humans are good at remembering and recognizing patterns;
computers are good at crunching numbers

A compromising approach: Model human
intelligence as much as possible but also utilize
computer’s ability to crunch numbers

Airplanes have wings like birds but they don’t flap them,
instead they use engine technology

History of AI

Relatively brief history, only 50
60 years old

Interesting with many ups and downs

A look at its history helps to understand how
the current focus and methodologies in AI
have emerged

History of AI


McCulloch and Pitts (1943) proposed a model of
artificial neurons could compute any computable

Marvin Minsky (1951) built the first neural
network computer using vacuum tubes

Alan Turing (1950) introduced machine learning,
genetic algorithms and reinforcement learning

History of AI

Birth of AI

Dartmouth conference (1956)

Organized and attended by some of those who are
now regarded as founders of AI: John McCarthy,
Marvin Minsky, Allen Newell, Herb Simon

Coined the term “Artificial Intelligence”

Presentation of a reasoning program, "Logic
Theorist" which could automatically prove many
mathematical theorems

History of AI

Early Years (1950s and 60s)

Several interesting and impressive AI work that
people earlier did not believe that computers
could ever do

General Problem Solver: Could solve limited
classes of puzzles thinking like humans

Geometry Theorem Prover: Could prove theorem
that were tricky for students

Checkers player: Disproved the idea that
computers can only do what they are told to do,
soon the program learned to play better than its

History of AI

Early years (1950s and 60s)

SAINT: Solved freshman calculus problems

ANALOGY: Solved IQ test analogy problems

SIR: Answered simple questions in English

STUDENT: Solved algebra story problems

SHRDLU: Obeyed simple English commands in the
blocks world

History of AI

Limitations of Early Systems

Could only work on "toy" problems which were
not at the scale of real
world problems, for two
main reasons

Difficult to formalize and encode real
world knowledge

For example, they tried to build a machine translation system
from Russian to English using dictionaries and syntactic
transformations, but due to lack of world knowledge: "the
spirit is willing but the flesh is weak"
> Russian
> "the vodka
is good but the meat is rotten“

The systems used simple search to find a solution out
of all the potential solutions, this would not work with
more complex problems which have a

large space of potential solutions

History of AI

based Systems (1970s)

Realization that domain
specific knowledge could
help finding the solution led to several expert
systems for specific domains

Encoded rules that human experts would used
and so these systems could perform like human
domain experts

DENDRAL: First knowledge
intensive system to
infer molecular structure from mass spectometer

History of AI

based Systems (1970s)

MYCIN: A medical expert system, could diagnose
blood infections from symptoms

Encoded 450 rules

Could perform as well as some experts and better than
junior doctors

But was never used in actual practice because of non
technical reasons

History of AI

AI Industry (1980s)

Several expert systems built and deployed, every
major U.S. company had its own AI group to use
or to investigate expert system

R1: Helped configure orders for new computers,
saved $40 million a year

Japanese started a project to build intelligent
computers running Prolog (logic programming

In U.S. the company MCC was formed with the
same goal

History of AI

AI Industry (1980s)

However, limitations of expert systems became

Brittleness (won't work with slightly different input),
too domain

Difficult to acquire all the knowledge even for a specific
domain (
acquisition bottleneck

A brief period of "AI Winter"

Recent History of AI

Recent years

Focus on learning from examples to address the
acquisition bottleneck

To counter brittleness: shift of focus from rule
based and
logical methods to probabilistic and statistical methods
(e.g. Bayesian networks, Hidden Markov Models)

AI has become a science:

Show real
world applications and not success on toy problems

Base claims on hard experimental evidence and not on

Analyze results for statistical significance, make data and tools
available to replicate experiments

Recent History of AI

Recent years

Instead of remaining isolated like early years, AI
has embraced other disciplines like statistics,
optimization, formal methods etc., whichever
areas are needed for success

Useful applications at the large scale of the

search engines, recommender systems, Web site
construction systems

data mining (find useful patterns in huge amounts of

State of the Art in AI

Deep Blue beats Kasparov (1997)

State of the Art in AI

Spirit, Opportunity (2003) and Curiosity (2012)
explore Mars

State of the Art in AI

DARPA grand challenge: Autonomous vehicle
navigates across desert and then urban environment

State of the Art in AI

IBM supercomputer “Watson” beats the best
human champions on Jeopardy!

Feb 14


State of the Art in AI

Automated speech/language systems for
airline travel

Spam filters using machine learning

Usable machine translation through Google

Computational Intelligence in

Computational Intelligence involves
systematizing and automating intellectual
tasks and is therefore potentially relevant to
any intellectual activity
including Medicine

Modern medicine is faced with the challenge
of acquiring, analyzing and applying large
amounts of knowledge necessary to solve
complex clinical problems, Computational
Intelligence methods fit this need and will
soon become indispensable

Emergence of AI in Medicine

Over the last few years medicine has become
rich quantitative field
because of
various electronic data capturing methods and
data management systems for both clinical
care and biomedical research, this is
transforming medicine from
art to science

The availability of data in electronic form
(documents, articles, clinical notes, electronic
health records etc.) has increased the
necessity and scope of their automatic
intelligent processing using AI techniques

Emergence of AI in Medicine

Diagnosis, treatment and predicting outcome
depends on complex interactions of many
clinical, biological and pathological variables,
hence there is a growing need for analytic
tools to analyze them

Note: Many AI in Medicine methods are
becoming more and more integrated within
medical applications often resulting into their
loss of visibility, sometimes not even labeled
as AI in Medicine methods; paradoxically, a
sign of success

AI in Medicine: Sub

Knowledge Representation

Design of good ontologies to enable data
exchange, standardization, communication, e.g.
CT, Gene Ontology etc.

Encode rules obtained from domain experts to
automate processing and reasoning

Enable discovering new and useful knowledge and
refine existing knowledge

AI in Medicine: Sub

Natural Language Processing

Unlock the value buried in text and narrative
records so that content can be used

automated processing

Interact with computer in natural language, ask
clinical questions in natural language to search
research articles

Information Retrieval: Find the required
information from a collection of documents,
answer questions

AI in Medicine: Sub

Decision Support Systems

Help in clinical diagnosis

Combine uncertain evidences from multiple sources and
generate a probabilistic diagnosis

Machine Learning

Image analysis in radiology

Predicting diagnosis, treatment or outcomes

Pattern recognition from medical data

Data Mining

Knowledge discovery from medical databases

Automatically find useful patterns from patient records

Adapting AI to Medicine

Medicine is a human endeavor, any AI system needs to
take into account human issues
like usability, user
friendliness, user
supportiveness, organizational
change, workflow etc.

Human expertise in medicine developed over centuries
cannot be discarded or replaced by re
discovering them
by analyzing data; build models that
integrates human
expertise with machine learning methods

The methods that can
use the existing knowledge
refine or augment it
are preferable over the
methods that completely based on data analysis

Adapting AI to Medicine

We need to amputate your finger.


Because our expert system that uses
the most advanced statistical machine
learning technique says so.


Adapting AI to Medicine

The output of an AI system must be
, sometimes preference for rule
based machine learning techniques over more
accurate but opaque statistical machine
learning techniques

Reasoning in medicine is based on arguments,
it is not the accuracy of predictions but their
explanation and communication
that matters

AI in Medicine: Issues

Although there has been a remarkable
progress in AI in Medicine but adoption of
these methods have been slow, mostly
because of political, fiscal and cultural reasons

If an computer makes a wrong diagnosis leading
to bad consequences, who should be held legally

Many learning methods need a lot of data to learn
from, will that compromise medical data

All healthcare workers may not be computer savvy

How much will doctors trust computers?

AI in Medicine: Issues

AI applications are most suited in medicine in
the form of:

Supporting tools instead of a stand
alone systems,
for example, in suggesting possible diagnoses and
their probabilities

Covering human mental shortcomings/lapses

Forgetfulness: reminders of certain tests or medications

Detect possible errors

Searching and mining huge amounts of data which
is not humanly possible and present results to

Course Structure

In this course we will cover the following AI
topics along with medical applications

Probability and Probabilistic Reasoning

Machine Learning

Data Mining

Knowledge Representation



Natural Language Processing (as time will permit)

Course Structure

For each topic we will generally proceed as

Theoretical understanding of the topic

Look at some medical applications from published

Learn and use some available tool or software

AI in Medicine: Some Resources

Artificial Intelligence in Medicine

Journal published by Elsevier, accessible online through library’s website

AIME: A European biannual conference of AI in

An online resource for knowledge management systems in healthcare
includes AI in Medicine (

Artificial Intelligence in Medicine, edited by Peter

An old outdated book but still interesting, entirely available online