Loading presentation...

Present Remotely

Send the link below via email or IM


Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.


Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Artificial Intelligence and Medical Diagnosis

No description

Micah Lapinid

on 8 May 2015

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Artificial Intelligence and Medical Diagnosis

What is Artificial Intelligence (AI)?
Area of study in the computer science field
Human created programs/systems that are able to:
- learn and make decisions
- do tasks efficiently with little or no error
The problem:

Approximately 12 million adults are misdiagnosed each year
Missed, incorrect, or delayed diagnosis: 11% to 20% of cases
found to be more common in primary-care settings
Involvement of AI in Medical Diagnosis
Micah Lapinid
Causes of Misdiagnosis
and Medical Errors
flawed ways of thinking
inadequacies with lab tests, medical records or physical check-ups
failure to consult with the appropriate specialist
time constraints in primary care
Medical Liability Claims
From 1986 - 2010: 350,000 paid claims

- errors in diagnosis responsible for deaths, disabilities, and medical liability payments

- diagnostic mistakes involved in 13,614 deaths

- average diagnostic-error payment (after inflation): $386,849

- Of the total $110 million paid out during the 25-year period, 35% was paid in diagnostic-error cases
Brief History
Applied with the invention of programmable computers
US healthcare costs expected to rise 30% by 2050

Indiana University research
- cost per unit of outcome change with AI: $189
- compared to $497 of usual treatment
- Healthcare costs decrease by more than 50%
- 50% diagnostic improvement
Benefits of AI in
Healthcare costs
Report what came easily during the project:
- gathering research
- making the power point

Report what came with difficulty:
- writing the research paper (assignments prior helped a lot)

Tell me what skills you learned that you will take with you beyond the classroom:
- Research techniques
- writing business letters/memos
Artificial Neural
Networks (ANN)
Idea was from Greek mythology
Early studies on the theory of thinking and intelligence helped established the logic of modern AIs
Alan Turing - considered the founder of modern computer science and AI
- Imitation Game theory
- the "Turing test"
IBM's Watson
Early 1970's at Stanford University

The very first AI expert system
- diagnose patients based on reported symptoms and medical results
- able to suggest lab tests
- Recommends treatment once patient is diagnosed

diagnose bacterial infections in the blood
Technique mostly used for diagnosis

Works similarly like the human brain
- simulates biological neurons

Has the ability to learn from training data, self-organize and able to store knowledge in a network
AI computer system specifically designed as a Q & A machine for the game show,
Applied to different fields, most recently healthcare
Built to mirror human learning process, cognition
uses natural language and able to process unstructured documents to help with diagnoses
summarizes medical records to help physicians efficiently treat patients
Full transcript