Medical Thinking · Health 201

Medicine runs on information. Is the right piece reaching the right reader?

Patient records, literature, and now AI-generated summaries have grown past what any one person can read in full. Medical Thinking is about the flow of information in medicine — what is the most pertinent information for a given reader, at a given moment. That question starts with summarization, done rigorously enough to trust.

Contributions

Papers & frameworks

Work toward making the summarization and flow of medical information evaluable, not just fluent.

01

Toward a Consensus Standard for Evaluating AI-Generated Health Summaries

A two-layer framework — universal criteria plus specialty-specific salience — for grading AI-generated clinical summaries against consensus-ratified criteria rather than reference summaries.

Why this matters

Fluent isn't the same as complete

Right info, right reader

What a cardiologist needs before clinic differs from what primary care needs at an annual exam. Tailoring has to scale past per-user idiosyncrasy.

Silent omission is the risk

A summary that drops a critical lab trend still reads as complete. Evaluating only what's said, never what's missing, misses the most dangerous failure mode.

Criteria, not references

No single "gold" summary generalizes. What scales is a validated, consensus-ratified rubric — and a validated process for applying it.