The Informatics e-Learning Hub: Patient Centered Care

A Patient Perspective of AI

By: Andrea Borondy Kitts MS, MPH

As the use of AI in radiology becomes more common, it’s important to keep the patient’s perspective at the forefront. Transparency in AI is crucial in gaining trust and for patients to feel comfortable, especially when its decisions impact their diagnosis or treatment plan.

This video reviews a patient’s perspective on AI, including their top concerns and how legal agreements can address some of them.

In this video, radiologists will learn:

Some patient concerns about the use of AI in their care, including sharing health data and AI use in their diagnosis and treatment plan.
How to identify different data sharing use cases.
How to develop appropriate data sharing protocols and agreements.
About new trends likely to impact data sharing and acceptance of AI.

Communicating with Patients About AI

By: Nina Vincoff, MD

Communicating with patients about the use of AI in your practice is key to gaining trust and providing quality care. It’s important for patients to know that AI doesn’t replace radiologists but acts as a tool to make them even more efficient and accurate.

This video reviews patient expectations and concerns about the use of AI and strategies for radiologists to effectively communicate how AI is being used to provide quality patient care.

In this video, radiologists will learn:

The components of patient-centered communication.
How to be aware of patient expectations and concerns about AI in radiology.
To be prepared to address patient concerns about AI and communicate the patient-centered benefits of AI.

Ensuring the Safety and Effectiveness of AI in Radiology

By: David Larson, MD, MBA

Before using AI in radiology or any patient care setting, it’s vital to ensure it is both safe and effective. In addition, there are several essential performance elements to consider; diagnostic algorithms should be accurate, reliable, deterministic and more.

This video reviews the complete list of performance elements, how process control systems can be used to monitor AI algorithms and why we should strive for world-class performance in every deployed instance of AI in radiology.

In this video, radiologists will learn:

About process controls systems.
The performance elements of diagnostic algorithms.
Strategies to drive world-class performance in every deployed instance of AI in radiology.

Bias and Fairness in AI Models

By: Monica J. Wood, MD

Unwanted bias may be incorporated unwittingly into AI models at points throughout an algorithm’s lifecycle — including the creation of training datasets, selection of model architecture and refinement of the algorithm post-deployment. And just as radiologists perform quality assurance on all our imaging modalities, we should aim to incorporate bias evaluation in routine assessment of AI algorithms.

Learning Objectives

How biases make their way into AI algorithms.
Examples of bias affecting the training data.
How to engage in meaningful conversations on bias.

Brittleness of AI Models

By: Woojin Kim, MD

“Brittleness” is the term for an AI model which works well where it was trained but fails when taken outside that area and subjected to new data. There are no guarantees that an algorithm developed elsewhere will function well at your institution — even if it has FDA-clearance. The video explores issues relating to brittleness including concept drift, where the goal of the algorithm changes over time, and data drift, which involves changes created by using new data sources to generate medical imaging data.

Learning Objectives:

The limitations of AI and what can be done to mitigate them.
How validation and training issues contribute to brittleness.
What radiologists should look for in evaluating an AI algorithm.