Concern 119 · Working draft · editorial review in progress
Cross-domain transfer failure
Cross-domain transfer failure occurs when a model that works in one institution or setting performs worse in another.
Understanding the concern
The sites may differ in equipment, recording practices, populations, or decisions about who is tested. A model can learn those local patterns along with the intended task.
Research in chest imaging has shown why external testing matters. That does not mean transfer always fails or that every medical model has the same problem. A new setting needs its own assessment instead of inheriting the original site's performance claim.
An example
A hospital tool may rely on image features tied to one site's equipment that do not carry over elsewhere.
Illustrative unless identified as a documented case.
Words in plain English
- Model
- The learned part of an AI system. It uses patterns found during training to produce an answer or prediction.
Evidence and its limits
The study evaluates pneumonia-model performance across hospital datasets and identifies generalization limitations.
Zech and colleagues · PLOS Medicine 2018 · Research study
Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs ↗ (opens in a new tab)Cross-hospital evaluation shows site-associated signals and variable generalization in the systems studied.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Was the system tested independently in this setting with the people it will serve?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Humility
Humility means recognizing the limits of our knowledge and being willing to learn from others. Expertise can be valuable without answering every question.
State where evidence is weak, invite criticism, and listen to people with different experience. Leave room to revise a decision when new information appears.
Ask together: What might we be missing, and who could help us see it?
Prudence
Prudence means using careful judgment before and during action. It balances worthwhile opportunities with the need to avoid harm that could have been anticipated.
Start with a limited trial, set stopping points, and prefer choices that can be undone when uncertainty is high. Review what happens rather than assuming the original plan remains sound.
Ask together: What is a careful next step, and when should we stop or change course?
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.