Bringing machine learning to clinical use safely, ethically and cost-effectively

Go back to programme

Bringing machine learning to clinical use safely, ethically and cost-effectively

As part of the AI and Health Discovery series, learn how digital health is benefitting from advanced applications of machine learning (ML) and how to avoid the “Artificial Intelligence chasm.”

Despite good predictive performance, models trained on electronic health record (EHR) data using ML do not necessarily translate into clinical gains in the form of better care or lower cost, leading to a gap referred to as an “AI chasm.” There is increasing concern that current models are not useful, reliable, or fair. The usefulness of making a prediction and taking actions depends on factors beyond model accuracy, such as lead time offered by the prediction, the existence of a mitigating action, the cost and ease of intervening, the logistics of the intervention, and incentives of making the intervention.

This AI for Good webinar illustrates how to shift the focus from metrics that rely solely on performance characteristics of the model to metrics that incorporate characteristics of the workflow in which the model’s output is used as well as the consequences of model guided decision making.

Share this session
In partnership with
Scroll Up