Sherri Rose

What they work on

1. Develop microsimulation models of the health care system's cause-and-effect network to estimate how an algorithm would affect access, quality and costs before deployment, using billing claims, primary care records and qualitative data.
2. Build simpler causal network models and Markov cohort models, which track patient groups between health states, as comparison benchmarks for the pre-deployment impact framework.
3. Develop and test data intervention methods that use microsimulations to generate counterfactual outcomes, meaning what results would look like under a desired state of primary care.
4. Create penalized regression estimators, prediction methods that use penalties to enforce chosen constraints, and compare them with existing estimators in comprehensive simulation studies.
5. Test the combined framework on chronic kidney disease quality of care using national primary care registry data, and release open-source tools, tutorials and a synthetic dataset.

More about the research

Why it matters

Algorithms already shape care for millions of people. A way to test their effects on access, quality and cost before deployment could help health systems avoid tools that harm patients, and could inform future standards for health AI. Primary care tools tested on chronic kidney disease care could improve care quality for patients with this common condition, and open software could let other clinics adapt the methods.

Known grants

From NIH and NSF research grants. Labs often have other funding we can't see.

Closest labs

The school

Stanford University: 87 labs on PI Pages, $1.6B a year on research, 739 research doctorates a year.

More about Stanford University

Reach out

A start for your email. Fill in the brackets.