Episodit
-
We’re back! This is the start of our regular discussions about healthcare AI topics and recent literature. On today’s episode - the 10 commandments of decision support, the checkered history of EMRs, clinicians as “moral crumple zone” for AI models and much more.
01:18 Technical update (Llama 3.1, Phi releases)
06:25 Main discussion
41:20 Article round-up
Episodes | Twitter | [email protected]
-
In this episode, we discuss more of the technical aspects of LLM implementation in healthcare, including the following topics:
EmbeddingsRetrieval augmented generation (RAG)Fine tuningLow-Rank Adaptation (LoRA)Small modelsQuantisationEncoder and decoder modelsMultimodal transformersOh my!
Episodes | Twitter | [email protected]
-
Puuttuva jakso?
-
In this episode, we discuss some concerns about LLM implementation in the healthcare setting, including the following topics:
More detail about hallucinations, issues with accuracy Difficulties of model evaluationConcerns regarding bias and equityGovernance and monitoring of LLMs in a healthcare settingsEpisodes | Twitter | [email protected]
-
Finally! We’re talking about large language models (LLMs) including ChatGPT. We discuss the following topics:
Brief explanation of transformer models and how they work including the attention mechanism and context windowDiscuss a brief development of LLMs to this pointHow LLMs are trainedSome limitations - privacy, accuracy, provenanceEpisodes | Twitter | [email protected]
-
In this episodes we give an overview of neural networks and how they’re used in healthcare. We'll be covering the following topics:
Definition of neural networks and a high level explanation of their structureOverview of the development of neural networks and use in healthcareHow neural networks are currently used in medicineLimitations and considerations for their useEpisodes | Twitter | [email protected]
-
Welcome to Medical Attention. This episode is an introduction to artificial intelligence and machine learning for people in healthcare with no technical background.
Episodes | Twitter | [email protected]
