Scientific Digest

Featured Post

New guidelines for early implementation of CDSS in the clinical care !

Wonderful work by Vasey et al. that provide a multi-stakeholder, consensus-based reporting guideline for the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI). 

The authors of this Nature Medicine paper report an actionable checklist of minimal reporting items, including a crucial focus on the human role in AI systems adoption in the clinical setting.

Latest Posts

AI for radiographic COVID-19 detection selects shortcuts over signal.

Discover in Nature Machine Intelligence how recent deep learning systems to detect COVID-19 from chest radiographs rely on confounding factors rather than medical pathology, creating an alarming situation in which the systems appear accurate, but fail when tested in new hospitals. Moreover, the authors showed that the evaluation of a model on external data is insufficient to ensure AI systems rely on medically relevant pathology, because the undesired ‘shortcuts’ learned by AI systems may not impair performance in new hospitals!

Digital medicine and the curse of dimensionality

If you want to understand what is the curse of dimensionality in statistical learning theory, this NPJ paper is for you!

The false hope of current approaches to explainable artificial intelligence in health care

A great viewpoint in the Lancet Digital Health about the intrinsic incompatibility between Deep Learning and Explainability

%d bloggers like this: