All Stories

Advancing analysis of FDA Adverse Events using LLMs

Patient safety continues to be an issue in 2023, with nearly 1 in 4 patients experiencing an adverse event upon admission. Up to 40% of adverse events were related to...

Switchover disruptions: The true cost of an AI scribe

“Switchover disruptions” were highlighted in Harvard Business Review’s recent article on the challenges of AI adoption in healthcare. Economists define it as the cost of integrating new technologies that can...

Create word embeddings from PubMed patient summaries

Building upon the previous tutorial on one-hot encoding, this tutorial will explore the concept of word embeddings and implement this with real-world data.

Should AI replace the hospital fax machine?

VC firm Andressen Horowitz recently published an article on how the latest AI technologies will have a big impact on healthcare. Is it finally time to say good-bye to the...

Encoding PubMed abstracts for NLP tasks

Last month, I gave a talk at a local meetup on LLMs, LangChain & SQL. Since then, I’ve wanted to explore the technical foundations of LLMs, particularly neural networks.

When a correct diagnosis matters

When does a correct diagnosis matter? Does it matter if a human or computer makes the decision? I reflect on a recent article by the Mayo Clinic on a diagnosis...