AI in Health
AI tools are entering clinical practice — from diagnostic imaging to triage chatbots. The evidence is developing fast, but so are the risks. This hub collects our evidence-first guides on clinical AI.
This hub is for patients and clinicians who want to understand AI in healthcare through the lens of evidence quality — not hype. Each guide examines a specific aspect of clinical AI, from how tools are validated to the cognitive and social risks they introduce.
What This Covers
- Evidence standards — how to judge whether a clinical AI tool actually works
- Cognitive risks — automation bias and the danger of uncritical trust in algorithms
- Fairness — algorithmic bias and who gets left behind when training data isn't representative
- Real-world impact — why lab performance metrics don't always translate to better patient outcomes
We've moved beyond Dr Google. This is the Dr AI Era — and the grey zone is where the most important questions live.
Featured Guides
AI in Medicine: Evidence Standards
How to evaluate claims about AI diagnostic tools using established evidence frameworks.
Automation Bias in Clinical Practice
When clinicians over-rely on algorithmic suggestions — and how to guard against it.
Algorithmic Bias in Healthcare
How biased training data can produce AI systems that widen health disparities.
AI in Radiology: Hype vs Evidence
What the evidence actually shows about AI-assisted imaging in real clinical settings.
All AI in Health Guides
6 guides
What This Page Is Not
- A product review or endorsement of any AI tool
- Clinical advice — always consult your healthcare provider
- An exhaustive technical overview of machine learning