The recent increase of artificial intelligence in clinical research mandates more transparency and reproducibility, just as with traditional evidence-based care.
“Observe carefully, deduce shrewdly, and confirm with evidence.”
A landmark article from Nature Medicine on the application of federated learning in the training process of artificial intelligence models.
Duke University paper lauded for its effort to have a curated, annotated, and publicly available dataset, as well as sharing the algorithm with the journal.
Grasp the basics of graph neural networks, architectures, and their applications in healthcare.
The powerful paper that reviews the recent accomplishments, shortcomings and future challenges of deep learning
The Google Health paper that describes the use of multitask learning with electronic health records to allow for concurrent prediction of multiple endpoints
Fighting fire with fire. How we still under leverage AI for solving some of the issues with AI
How machine learning has its inherent strengths but also its unavoidable weaknesses, especially in perpetuating biases