MATLAB and Simulink Seminars

Explainable AI (XAI) for medical applications

Start Time End Time
18 Oct 2022, 15:00 CEST 18 Oct 2022, 16:00 CEST

Overview

In recent years, artificial intelligence (AI) has shown great promise in medicine and medical device applications. However, interpretability (or in deep learning, “Explainable AI”) requirements make AI applications difficult in the medical devices industry, due to strict regulation guidelines.

Interpretable machine learning provides techniques and algorithms that overcome the black-box nature of AI models. By revealing how various features contribute (or do not contribute) to predictions, you can validate that the model is using the right evidence for its predictions and reveal model biases that were not apparent during training.

In this session, we will demonstrate various interpretability methods available in MATLAB that overcome the black box nature of AI algorithms, useful for building/getting trust in machine learning and deep learning, and validating that models are working.

We’ll also explore the workflow for using artificial intelligence techniques to build digital health applications that comply with global medical regulations.

Highlights

  • Choosing a method for interpretability based on type of data
  • Applying interpretability methods to explain model predictions
  • Explainable AI for Medical Images
  • Certification workflows for medical AI

Who Should Attend

Researchers, data scientists, engineers, looking for ways to interpret machine and deep learning applications for the medical devices industry

About the Presenters

Paola Jaramillo is a Team Lead and Senior Application Engineer at MathWorks in Eindhoven, The Netherlands. She supports customers with MATLAB and Simulink in application areas including signal and image processing, computer vision, and machine learning. Before joining MathWorks, she was awarded a fellowship under an international double degree agreement and obtained a MSc degree in Electronic Engineering from the Politecnico di Torino in Italy. After asix-month internship on DSPs for FPGA at IBM in Switzerland, she spent five years with the SPS Group at the Eindhoven University of Technology where she focused on sensor data analytics for intelligent lighting environments and actively participated in several European Commission projects

Francesca Perino is Principal Application Engineer at MathWorks. She focuses on enabling MathWorks customers to be successful in their adoption and use of MATLAB platform to solve their numerical modelling and AI challenges with cutting-edge technology, tools and methods. She has expertise in data ingestion and processing, software design and application development in MATLAB, big data for enterprise-scale predictive analytics.

Before MathWorks, she spent a few years working as a research engineer and software developer. She holds a M.Sc. in Physics specializing in numerical methods and statistics in atmospheric science from Torino University in Italy.

Product Focus

Explainable AI (XAI) for medical applications

To continue, please disable browser ad blocking for mathworks.com and reload this page.

You are already signed in to your MathWorks Account. Please press the "Submit" button to complete the process.