[TBD] James Siddle | Explaining AI Diabetes models using PiML #39
Description
Main talk (25 minutes + 5 minutes for Q&A)
Speaker: James Siddle [email protected] @
Title: Explaining AI Diabetes models using PiML
Abstract: This talk is about how to develop, train, explain, and interpret AI models for use in the medical field using the PiML toolkit, focused on the widely used Pima Indians Diabetes dataset.
The talk will provide an easy to understand high level introduction to the topics of model explainability and interpretability, and help the audience understand how significant these are to medical professionals who may be considering use of ML in the clinic.
It will then provide a step-by-step walk through of using the PiML toolkit to train predictive models for diabetes, and then use toolkit features to explain and interpret their performance.
The talk will wrap up with a look ahead to the future adoption of AI in the healthcare, pointing out challenges that may limit adoption along with opportunities for potential exploitation of AI and ML.
Some knowledge of AI, ML and Python topics will be beneficial to the audience, but the talk will cover a wide range of topics related to the use of AI in the medical field, so is expected to be of general interest.
Recording consent: Yes
Publishing slides consent: Yes
Availability: None
Special requirements: No
Submitted 03/01/2024 08:57:14 via PyData London - Submit a Talk
- Contacted
- Confirmed
- RSVP yes
- Reminder email
- Arrived
- Slides published