The Health AI Brief cover art

All Episodes

The Health AI Brief — 159 episodes

#
Title
1

Managing ‘Needle in a Haystack’ Context - Why AI Struggles with the Middle of Your Notes

2

Can the WHO’s AI Fix Medical Misinformation?

3

AI Just Beat Harvard Doctors?

4

Google DeepMind AI Co-Clinician Tries to Examine Patients

5

XML Tags for Data - How Tech Giants Structure Medical Charts for AI

6

The Negative Prompt Strategy for LLMs

7

Politeness vs Performance – Why Saying Please may Killing Your AI’s Accuracy

8

What Blindness is Warning Us About AI

9

Pre-, mid-, post-training - The Complete LLM Training Guide

10

Model Context Protocol (MCP) - the 'universal adaptor' for artificial intelligence

11

Small Language Models (SLMs) - The Lean Machine

12

How Bixonimania Fooled the World's Leading AI Models

13

Test-Time Inference - The High Cost of Thinking

14

Multimodal AI - Seeing the X-Ray

15

People Use AI Instead of Doctors (Here’s Why)

16

Temperature & Top-P- The Creativity Dial for Controlling the Chaos

17

Meta Muse Spark - New Standard for Healthcare AI?

18

Vector Databases - The AI's Filing Cabinet

19

System Prompts - The Secret Instructions How System Prompts Define AI Personality

20

AI Scribes in 2026: What Every Leader Needs to Know

21

AI Scribes Worth It? - New JAMA Study Analysis

22

Heidi Remote - Dedicated Hardware for Ambient Clinical AI Scribe

23

RAG - Ending Hallucinations and Confabulation with Retrieval Augmented Generation

24

Doctronic AI is Legally Prescribing Drugs (And Doctors Agree 99% of the Time)

25

How to Spot AI Writing

26

Chain-of-Thought (CoT) - Making The AI 'Think' Out Loud

27

Why This AI Failed to Catch 17 Fatal "Never Events" - Validating NG tube Position AI

28

Benchmarks - How We Grade AI

29

Foundation Models & Patient Privacy: Is There a Risk?

30

Zero-Shot vs Few-Shot - The Secret of Few-Shot Prompting

31

Is Perplexity Health the Future of Medical AI? The Surprises Behind the Launch

32

Fitbit AI Health Coach - Medical Records & Google Gemini Integration

33

Data Privacy & HIPAA - Is Patient Data Leaking

34

How ChatGPT and AlphaFold Helped Shrink a Terminal Tumour by 75%

35

Microsoft Copilot Health AI and The Systemic Failures Driving Us Towards Similar Medical AI

36

The Age of the Medical Generalist: Foundation Models in Healthcare

37

Google AI vs Human Doctor - AMIE AI Clinical Trial - Real-World Primary Care Results

38

Amazon Health AI Explained - Workflow & Medical Records

39

What Medicine Can Learn From Consumer AI Trends

40

SleepFM: The AI Foundation Model for Disease Prediction

41

Context Windows - The ‘Short-Term Memory’

42

Am I an AI? And the bot that tried to destroy a human’s career

43

Quantization - Shrinking the LLM 'Brain'

44

Scaling Neuro-Rehab: How Nyra Health’s €20M Series A Might Redefine AI Therapy

45

064 Parameters - Does LLM Size Actually Matter

46

Amazon Connect Health Agentic AI Aiming to Eliminate Administrative Burden

47

Why Medical AI Fails: Lessons About Model Collapse From Purely AI Synthetic Data

48

World Models vs LLMs for Healthcare - Master the Next Frontier According to Yann LeCun

49

063 Reinforcement Learning from Human Feedback (RLHF) - Human-in-the-Loop

50

Elon Musk's Grok Medical "Second Opinion" Suggestion

51

ChatGPT Health Deemed Unsafe: Nature Medicine Urgent Alert

52

062 Fine-Tuning - Specialist vs Generalist - Sending AI to Medical School

53

Health AI in 2026: The Definitive Guide to Big Tech Strategies

54

Heidi Acquires Automedica and Rolls Out New Products

55

061 Pre-Training - What LLMs Learn Before They Become 'Medical'

56

Deep Dive into Ant Afu Health AI App - Affiliate of Jack Ma’s Alibaba

57

060 Positional Encoding - How AI Knows the Order of Your Symptoms

58

059 BERT vs. GPT - Understanding the Difference Between an Encoder and Decoder

59

Agentic AI Era in Healthcare: Lessons from OpenClaw

60

058 Regular Expressions (Regex) - The ‘Old School’ Trick That (Sometimes) Still Beats Modern AI

61

AI scribe transcripts - Digital Exhaust or Digital Gold

62

Are LLMs Reliable for Medical Advice? Nature Medicine Study

63

Nature medicine principles to guide AI readiness

64

International AI Safety Report 2026

65

Large Language Models for Complex Cardiology? Google AMIE/Stanford Study Review

66

057 Named Entity Recognition (NER) - How AI Spots Drugs and Dosages Instantly

67

Lotus Health AI - AI Aimed at Primary Care

68

AI Stethoscope TRICORDER Trial Results - Why Good AI Doesn't Guarantee Clinical Impact

69

056 TF-IDF - How to Find a Needle in a Digital Haystack

70

AI For Mammography Screening - Results of Lancet RCT

71

055 N-grams - Why Blood Pressure is One Word, Not Two

72

OpenEvidence: The $12B AI Changing Clinical Decisions

73

AlphaGenome Explained - Decoding the Non-Coding Genome

74

054 Stop Words - The ‘Invisible’ Words That Are Troubling Your AI Models

75

Sued for using AI scribe

76

053 Stemming & Lemmatization - How AI Groups Healing and Healed Automatically

77

Google MedGemma 1.5 and MedASR - 3D Scans & Medical Speech

78

052 Tokenization - How AI Slices Symptoms into Tokens

79

Amazon's New 'Agentic' Health AI

80

Gates and OpenAI Deploying AI in Rwanda

81

How to Use Ambient AI Scribes - The Ultimate Clinical Guide to Stop Editing AI Notes

82

051 Natural Language Processing (NLP) - teaching a computer to read a chart

83

NVIDIA’s SurgWorld - Solving the Surgical Robotics Data Gap with AI Synthesis

84

050 Diffusion Models - Sculpting from Noise

85

049 The Transformer - The Architecture Behind the Revolution

86

Google AI Overviews vs Clinical Safety - Why Reputable Sources Aren't Always Enough for AI

87

Claude for Healthcare - The AI Arms Race Hits the Clinic

88

048 Attention - How AI Focuses on What Matters

89

ChatGPT Health - Consolidating Health Data - Diagnosis or Data-Mine

90

047 Embeddings - The Medical Dictionary for AI

91

AI vs Pancreatic Cancer - Can PANDA Solve the Early Detection Problem

92

The Wealth of Health - Avoiding an Inequality Spiral in the AI Age

93

046 Generative Adversarial Networks - The Forger and the Detective

94

045 LSTMs - Fixing the AI's Short-Term Memory

95

Hugging a PowerPoint - Why ChatGPT makes a Terrible (but Addictive) Therapist

96

The 'Duck Test' for AI And Why Your Chatbot Might Be an Illegal Medical Device

97

044 RNNs - AI With a Memory for Sequences

98

043 CNNs - How AI See Medical Images

99

042 Activation Functions - To Fire or Not To Fire

100

041 Neurons & Weights - The Synapse of AI

101

040 K-Means - The Automated Triage Nurse

102

Beyond the Benchmark - How do we test a 'superhuman' doctor

103

039 SVMs - Drawing the Clearest Line Between Sick and Healthy

104

The Verdict on AI Scribes - Analysing their First Major RCTs

105

038 Random Forests - The Wisdom of the MDT

106

037 Decision Trees - The Algorithms You Already Use

107

036 Regression - The Statistical Bedrock of AI

108

035 The Architecture Shift - From Mechanics to Models

109

The WHO AI Report and Why Governance is Stalling Health AI

110

034 Regularisation - the antidote to overfitting

111

033 The Bias-Variance Tradeoff - The Specialist vs The Generalist

112

032 Underfitting - the overly simplistic intern

113

031 Overfitting - the brittle genius

114

What DeepMind's AI That Mastered Video Games Taught Us for Building Better Health AI

115

030 Actor-Critic Partnership - The Best of Both Worlds

116

029 Policy-Based Methods - Learning How To Act Directly

117

When the Chatbot is More Humane Than the Doctor

118

028 Value-Based Methods and Their Limits - The World of Q-learning

119

Epic's New AI - A Crystal Ball for Medicine, or a Look in the Rear-View Mirror

120

027 Curriculum learning - teaching an agent step-by-step

121

026 Exploration-Exploitation Dilemma

122

AI That Speaks the Language of the Cell and Contributs to Biomedical Discoveries

123

025 Reinforcement learning - rewards and punishments

124

Charting a Course for Safe AI in Medicine to Prevent Us Flying Blind - Report from the JAMA Summit on Artificial Intelligence

125

024 Efficient Learning and Smart Shortcuts for Medical AI - Transfer learning and Active learning

126

023 Self- and Semi-Supervised Learning - Learning from Imperfect Data

127

An AI Doctor Takes on the NEJM: Dr CaBot, the CPC-Bench AI and the Dawn of the Diagnostic Co-Pilot

128

022 Unsupervised learning - finding the patterns we might not have seen

129

021 Supervised learning - like learning with flashcards

130

AI Caught 'Cheating' Its Medical Exams - New Research Paper from Microsoft

131

020 Hyperparameters - the AI's recipe

132

019 Learning rates and Gradient descent - finding the bottom of the valley

133

The UK's New Health AI MHRA Commission - Rewriting the Rulebook or More Red Tape?

134

018 The AI's Scorecard - What is a Loss Function

135

017 How models actually learn

136

Forecasting Health with AI - A Deep Dive into the Delphi-2M AI Transformer Model for Health Records

137

AI in the NHS: A Reality Check on a National Rollout

138

016 DICOM, HL7, FHIR: The Languages of Medical Data Exchange.

139

015 - Training data vs validation data vs test data

140

014 Data annotation and labelling

141

AI stethoscopes research trial - press release vs peer review

142

013 Data cleaning and preprocessing

143

012 Data Quality - Junk in, junk out

144

011 Structured vs. Unstructured Data

145

AI robot surgeon that corrects its own mistakes

146

010 The AI Tipping Point in Medicine - Why Now?

147

Endoscopist deskilling risk after exposure to artificial intelligence in colonoscopy - Does 'helpful' tech actually make us worse?

148

009 AI Agents: Automating Healthcare or a New Clinical Safety Risk?

149

008 Narrow vs General AI, AGI and ASI

150

OpenAI's New Release: Why 'Open-Weights' Isn't 'Open-Source' - And Why They're Both Relevant For Clinicians

151

007 Parameters

152

006 Deep learning

153

Flok Health - an AI Physio for Back Pain - A cure for health service waiting lists? But is it safe?

154

005 Neural networks

155

004 Models

156

DD - OpenAI and Penda Health's AI Consult Real-World Study

157

003 AI vs machine learning

158

002 What is AI?

159

001 Introduction