Remove 12 evaluation-of-classification-model
article thumbnail

Redefining clinical trials: Adopting AI for speed, volume and diversity

IBM Big Data Hub

In 2022, less than 10% of trial participants for FDA approval were Black, fewer than 12% were Asian, under 13% were Hispanic, and women constituted less than 50% (Exhibit 3), not reflective of the current US population. It’s crucial to evaluate the feasibility of trials and refine protocols using evidence-based strategies.

article thumbnail

Explaining black-box models using attribute importance, PDPs, and LIME

Domino Data Lab

In this article we cover explainability for black-box models and show how to use different methods from the Skater framework to provide insights into the inner workings of a simple credit scoring neural network model. The interest in interpretation of machine learning has been rapidly accelerating in the last decade.

Modeling 139