Skip to Content

MIT Sloan: Artificial Intelligence in Health Care 

1. Introduction

The Learning Design Plan (LDP) is the blueprint for the design of a program. It contains a brief description of the program, the key exit-level outcomes that participants will achieve, and the precise manner in which the material will be delivered.

2. High-level overview

2.1 Module titles & exit-level outcomes

* The third and fifth exit-level outcome is assessed in all six modules..

2.2 Module learning outcomes and design

Module 1: AI and machine learning – Applications and foundations

Module descriptor: Become familiar with supervised machine learning and the types of problems it may be applied to.

Learning outcomes

Unit 1
Unit 2

Video Review Links

Module 3: Natural language processing and data analytics in health care

Module descriptor: Using AI to extract value-adding outcomes from medical literature and pathology reports.

Learning Outcomes for Module 3

Unit 1: Natural language processing for medical data extraction
Unit 2: Methods of applying natural language processing

Video Review Links

Module 4: Interpretability in machine learning – benefits and challenges

Module descriptor: Appreciate the importance and benefits of interpretable algorithms.

Module 4: Learning Outcomes

Unit 1: Interpretability in health care analytics

Unit 2: Important criteria unique to AI in health care

Video Review Links

Module 5: Patient risk stratification and augmenting clinical workflows

Module descriptor: Discover how AI can be applied to health care interventions and patient care.

Module 5: Learning Outcomes

Unit 1: Improving risk stratification and clinical workflows with machine learning

Unit 2: Transferability of AI capabilities in health care

Video Review Links

Module 6: Taking an integrated approach to hospital management and optimization

Module descriptor: Investigate a holistic approach to optimizing health care processes.

Module 6: Learning Outcomes
Unit 1: Optimization of operating rooms and block allocations

Unit 2: Using AI to predict patient length of stay and destination

Video Review Links

3. Program review structure

The review structure will follow the path outlined below:

Program Review Structure Table

Unless otherwise stated, the reviewed activities will be in the final unit of each module – Unit 3.

The activity submissions in Module 1 to Module 6 will review the content covered in those modules. Additionally, participants will also need to articulate how the content learned in each module might form part of a decision framework that would assist them in figuring out whether a particular problem could be addressed using AI.

Besides the review activities outlined above, participants will also receive feedback on their understanding as they progress through the program through the following mechanisms:

  • Class-wide discussion forums
  • Small group discussions

These feedback loops will make their engagement with the program’s content more interactive, and ensure that they receive feedback before they submit their written components.

The development and application of an AI decision framework:

As noted above, when participants progress through each module, they will be prompted to think about how the content learned in that module might figure in a decision framework that provides guidance on whether AI could be used to solve a real-life health care problem or use case that they might encounter outside of the program.

image description