Topic
Validating healthcare AI
How to tell a trustworthy clinical AI tool from a fragile one, grounded in building and validating decision support.
This page collects every article by Dr. Damon Tojjar in this topic. For all topics see browse by topic, and for the source-anchored record see damontojjar.com/record.
Articles in this topic (36)
- Bringing AI decision support to diabetes care
Decision support earns its place in the clinic only when it is validated where care actually happens. EASY Diabetes, the type 2 diabetes decision-support system I...
- What clinicians actually need from AI tools
The most common mistake in clinical AI is building for the model instead of the user. A tool can be accurate and still useless if it does not fit the few minutes a...
- How a decision-support system is evaluated: the EASY-1 trial
Claims about clinical AI should be settled by evidence, not enthusiasm. EASY Diabetes was evaluated in EASY-1 (NCT03258268), a registered randomized controlled...
- Calibration vs Accuracy in Plain Terms, and Why Calibration Is the One That Keeps You Safe
A model can be accurate and still mislead you about how sure it is. Accuracy measures how often the model's call is correct. Calibration measures whether its stated...
- Data Quality for Clinical AI: Why the Model Is Only as Good as Its Data
A clinical AI is only as good as the data it learned from, and most of the data we feed these systems was never collected to teach a machine anything. It was...
- How to Evaluate a Symptom Checker
A good symptom checker is honest about what it is for, careful with uncertainty, and quick to point you toward real care when the situation might be serious. The...
- A Buyer's Checklist for Deciding Whether Healthcare AI Deserves Your Trust
Before you let an AI tool touch patient care, you can decide whether it deserves your trust by answering six questions: what it is meant to do, what evidence stands...
- Explainability in Medical AI: A Real Explanation vs a Reassuring Story
Explainable medical AI means a clinician can see the reasons behind a recommendation well enough to check them against the patient and decide whether to trust them,...
- External Validation: Why a Model Must Prove Itself Outside Its Training Data
A clinical model has only really been tested when it performs on data it never saw during development, ideally on patients from a different place or a later time...
- How to Check That a Clinical Algorithm Serves Every Patient Group
To check that a clinical algorithm serves every patient group it will be used on, do three things in order: confirm the data it learned from looks like the patients...
- How Regulators Think About Generative-AI Mental-Health Chatbots
When a generative-AI chatbot is built to diagnose or treat a psychiatric condition, regulators do not treat it as a wellness app. They treat it as a medical device,...
- What Makes a Clinical Prediction Model Robust Instead of Fragile
A robust clinical prediction model does three things a fragile one cannot. It ranks patients by risk in the right order, it gets the actual numbers close to...
- Good Machine Learning Practice: 10 Principles for Trustworthy Medical AI
What Good Machine Learning Practice actually isGood Machine Learning Practice (GMLP) is a set of ten guiding principles, published jointly in October 2021 by the...
- How AI Is Changing Drug Discovery, and Where the Hype Outruns the Evidence
Artificial intelligence is doing real work in the earliest stages of drug discovery. It helps rank which biological targets are worth pursuing, it generates and...
- Human in the Loop: Designing Clinical AI That Supports Judgment
The clinician stays in charge because accountability cannot be delegated to software, and good clinical AI is designed around that fact rather than against it....
- Model Cards and Nutrition Labels for Health AI, Explained
A health AI model card, sometimes called a nutrition label, is a short standardized document that summarizes what an artificial intelligence model does, the patient...
- Why a Clinical Model Degrades After Launch, and How to Watch for It
A clinical model that performed well at launch can quietly get worse because the world it learned from keeps moving. The patients change, the way data is recorded...
- Predetermined Change Control Plans: Letting Medical AI Improve Without Losing Its Approval
A predetermined change control plan, or PCCP, is a document a device maker submits and gets authorized alongside the device itself, describing in advance the...
- Prospective vs Retrospective Validation in Clinical AI
Retrospective validation tests a clinical model on data that already exists, while prospective validation tests it going forward on patients as they actually...
- How to Read a Calibration Plot, and Why a Confident Model Can Still Be Wrong
A calibration plot answers one question: when a model says thirty percent, does the event actually happen about thirty percent of the time? Predicted probability...
- How to Read an ROC Curve Without Being Misled by the AUC
An ROC curve plots a model's true positive rate against its false positive rate across every possible decision threshold, and the area under it (the AUC) is the...
- Watching an AI Device in the Wild: Real-World Performance Monitoring
A real-world performance monitoring plan is the ongoing process that tracks an approved AI medical device once it is used on actual patients, so that a quiet loss...
- Reporting Standards for Medical AI: What Makes a Claim Checkable
A medical AI claim is only as credible as it is checkable, and checkability comes from structured, complete reporting: what the tool is for, what it learned from,...
- The Cost of a False Positive: Why Medical Errors Are Not Symmetric
A false positive is a test that says disease is present when it is not, and a false negative is a test that says disease is absent when it is there. These two...
- Validation vs Marketing: How to Read a Health-Tech Claim Honestly
A validated claim tells you what was tested, who it was tested on, what it was compared against, and what measurably changed. A marketing claim tells you how the...
- Transportability: Will a Prediction Model Work in a Population It Never Saw?
Transportability is the question of whether a prediction model that performed well where it was built will still perform where it is used, on people it never saw in...
- Understanding Overfitting in Clinical Models
Overfitting is when a model learns the quirks and noise of the data it was trained on instead of the real pattern, so it performs brilliantly on that data and...
- Prediction vs Explanation: Two Different Questions a Model Can Answer
A model that predicts well tells you what is likely to happen next. A model that explains tells you why it happens, in terms you could act on to change the outcome....
- Validating Healthcare AI: Test It Like a Medicine, Not a Benchmark
If you want to know whether a clinical AI tool actually helps patients, there is one honest answer: test it the way we test a drug. Put it in front of real patients...
- The Decision Threshold: The Quiet Choice That Turns a Model Score Into an Action
A clinical model rarely hands you an action. It hands you a number, a probability between zero and one, and someone must decide how high it climbs before anything...
- What Decision Curve Analysis Adds That Accuracy and AUC Cannot
The short answerAccuracy and the area under the ROC curve (AUC) tell you how well a model separates people who will have an outcome from people who will not. They...
- What Foundation Models Mean for Medicine, Explained by a Physician-Scientist
A foundation model is a very large AI system trained on broad data so it can be adapted to many tasks, and in medicine that generality is both its promise and its...
- What Makes an AI Tool Explainable to a Patient
An AI tool is explainable to a patient when that person can answer four plain questions without a technical background: what does this tool do, what does it not do,...
- When a Clinical Algorithm Should Say I Don't Know
What does it mean for a clinical algorithm to say I don't know?A trustworthy clinical algorithm is one that knows the edge of its own competence and is allowed to...
- When More Data Is Not Better: Why a Bigger Sample Can Be Confidently Wrong
A bigger dataset is not automatically better evidence, because size fixes one kind of error and is helpless against another. More data shrinks random noise, so the...
- The WHO's Governance Frame for Generative AI in Health: Who Is Responsible for Each Safeguard
The World Health Organization's January 2024 guidance on large multi-modal models does something most AI-ethics documents avoid: it names who is accountable for...