AI x ML in Medicine
INTRODUCTORY COURSE
2023
Welcome to our third introductory course in medical AI. Originally delivered live in 2023. It introduces the basics of AI, coding in Python, and applications of AI in medical specialties.
A1. Introduction to Artificial Intelligence in Medicine
Learning Objectives (Students should be able to):
Define Artificial Intelligence and Machine Learning
Describe the potential role of artificial intelligence in medicine
Explain at a basic level why data type/quality is important for use in machine learning tools
A2. Introduction to Programming and Python
Learning Objectives (Students should be able to):
Successfully create and run a python program in Google Colab
Understand and use the basic syntactic elements of Python
Develop awareness of good coding habits such as readability and descriptive commentary
A3. Reviewing Major Python Libraries Relevant to AI
Learning Objectives (Students should be able to):
List the major Python libraries used in AI
Give examples of what each library can be used for
Know where to find documentation for using specific libraries
B1. Medical Data and Preprocessing
Learning Objectives (Students should be able to):
Understand the importance of data quality used in machine learning
List the basic medical data types
Describe common data processing techniques used in AI
B2. Introduction to AI Models and Application
Learning Objectives (Students should be able to):
List the commonly used AI models and provide examples of their application
Know where to find documentation on using specific AI models
Develop an awareness of the advantages and drawbacks of each AI model
B3. Privacy in Medical Applications of Artificial Intelligence
Learning Objectives (Students should be able to):
Appreciate the complexity of the ethicolegal considerations when using AI in medicine
Explain the role of privacy in data collection and usage
Describe how data bias can affect outcomes and fairness in AI implementations
C1. AI Applications in Public Health
Learning Objectives (Students should be able to):
Understand the scope of public health
Provide examples of how AI has been applied in public health
Provide examples of how AI might transform the future of public health
C2. Machine Learning and Infectious Diseases
Learning Objectives (Students should be able to):
Understand the scope of infectious disease
Provide examples of how AI has been applied in infectious disease
Provide examples of how AI might transform the future of infectious disease
C3. Application of Artificial Intelligence in Neurology and Neurosurgery
Learning Objectives (Students should be able to):
Understand the scope of Neurology and Neurosurgery
Provide examples of how AI has been applied in these disciplines
Provide examples of how AI might transform the future of these disciplines
C4. Introduction to Artificial Intelligence in Radiology, Pathology, and Cardiology
Learning Objectives (Students should be able to):
Understand the scope of Radiology, Pathology, and Cardiology
Provide examples of how AI has been applied in these disciplines
Provide examples of how AI might transform the future of these disciplines
D1. Artificial Intelligence in Omics and Oncology
Learning Objectives (Students should be able to):
Understand the scope of Medical Genetics, Omics and Oncology
Provide examples of how AI has been applied in these disciplines
Provide examples of how AI might transform the future of these disciplines
D2. Artificial Intelligence in Primary Care & How to read a AI in Medicine Paper
Learning Objectives (Students should be able to):
Provide examples of how AI has been applied in these disciplines
Provide examples of how AI might transform the future of these disciplines
Have an approach to reading a medical AI paper
D3. Case-based learning, Conclusion & Wrap-up
Learning Objectives (Students should be able to):
Describe how AI has been applied to the given study
Provide examples of how AI might transform the future of this discipline
Develop the ability to evaluate a medical AI paper