Shows / Algorithms & Adipose - Clinical AI, Explained
Algorithms & Adipose - Clinical AI, Explained
A practical, evidence-based show for physicians who want to understand AI in Medicine. Hosted by Dr. Farah Deshmukh, a board-certified internal medicine and obesity medicine physician, medical director, and assistant professor who teaches AI in medicine to internal medicine residents. Start at episode one, the season is built in order. Written about at algoadipose.substack.com
Episodes
- Algorithms & Adipose - Clinical AI, Explained
Episode 10: AI Agents in Medicine: When AI Stops Answering and Starts Doing
In this episode we talk about agents - what happens when AI stops answering and starts doing, why errors compound across steps, and why the threshold for…
- Algorithms & Adipose - Clinical AI, Explained
Episode 9: When AI Is Right for the Wrong Reason: Reasoning vs. Accuracy
In this episode we talk about multimodal AI - how a model "sees" an image, why that's the wrong word for what it does, and why it can give you the right answer…
- Algorithms & Adipose - Clinical AI, Explained
Episode 8: Can AI Pass the Medical Boards? What the Scores Really Mean
In this episode we talk about benchmarks and why "it passed the boards" means less than you think. Contamination, obsolescence, and how to read an AI paper's…
- Algorithms & Adipose - Clinical AI, Explained
Episode 7: Making AI ‘Medical’: Fine-Tuning, RAG, and Prompting
In this episode we talk about the three ways to make AI "medical", fine-tuning, retrieval, and prompting, what each one actually does, and how to tell them…
- Algorithms & Adipose - Clinical AI, Explained
Episode 6: Training vs. Using an AI Model: What Clinicians Need to Know
In this episode we talk about training vs. using - how these models are built, why they have a knowledge cutoff, and why they never actually learn from your…
- Algorithms & Adipose - Clinical AI, Explained
Episode 5: Prompt Engineering for Doctors: How You Ask Changes What You Get
This episode: Why a prompt isn't a request but a set of conditions, why "be accurate" accomplishes nothing, and why letting a model say "I don't know" is the…
- Algorithms & Adipose - Clinical AI, Explained
Episode 4: RAG Explained for Clinicians: Grounding AI in Real Sources
This episode: retrieval-augmented generation - giving the model a library instead of a memory. Paper: Zakka C, et al. Almanac — Retrieval-Augmented Language…
- Algorithms & Adipose - Clinical AI, Explained
Episode 3: AI Hallucinations in Medicine: Why It Makes Things Up
This episode: hallucination. The model produces a correct answer and a completely fabricated one by exactly the same process. Paper: Pal A, et al. Med-HALT…
- Algorithms & Adipose - Clinical AI, Explained
Episode 2: What Are Tokens and Context Windows? AI Basics for Clinicians
In this episode we talk about tokens and context - the model's working memory. What's in it, what falls out, why long chats degrade, and why a bigger context…
- Algorithms & Adipose - Clinical AI, Explained
Episode 1: How AI Actually Works: The Prediction Machine
what actually happens in the seconds after you hit enter after typing your prompt. Paper: Goh E, et al. Large Language Model Influence on Diagnostic Reasoning…