A manifesto on explainability for artificial intelligence in medicine

作者：

Highlights：

• AI in Medicine becomes increasingly ubiquitous, with new concerns and questions:

• How does an AI algorithm work — what is it doing?

• Does an AI system work as well as an expert?

• Does an AI system do what a user would do, were she in the same situation?

• Why cannot the system tell a user how it arrived at a conclusion or made a decision?

• Here, we deal with the need to address gaps in the explainability of AI in Medicine.

摘要

•AI in Medicine becomes increasingly ubiquitous, with new concerns and questions:•How does an AI algorithm work — what is it doing?•Does an AI system work as well as an expert?•Does an AI system do what a user would do, were she in the same situation?•Why cannot the system tell a user how it arrived at a conclusion or made a decision?•Here, we deal with the need to address gaps in the explainability of AI in Medicine.

论文关键词：Artificial intelligence,Explainability,Explainable artificial intelligence,Interpretability,Interpretable artificial intelligence

论文评审过程：Received 2 March 2022, Revised 4 October 2022, Accepted 4 October 2022, Available online 9 October 2022, Version of Record 18 October 2022.

论文官网地址：https://doi.org/10.1016/j.artmed.2022.102423