An essay to start with
Patient Safety and the Slack in the Institutional Line
Reporting a safety concern is only the beginning. What happens when a request moves through an organization while the risk remains?
Read the essay →
I follow healthcare problems from the front line to the data.
I write to make sense of what I see in healthcare and what I learn by building things. These essays follow small details into larger questions about safety, technology, and responsibility.
Selected writing
Writing on care and the systems behind it.
On safety, technology, and the decisions that shape care.
Essay · September 13, 2026
Making engineering part of healthcare’s work
An institution can buy a platform and still lack the capacity to build. Engineering needs a place in the everyday work of care.
Read the essay →Essay · September 14, 2026
From Emerge to clinical AI: designing information around clinical work
Bringing the record together is useful. Helping a care team recognize what changed, what is missing, and what needs action is the harder design problem.
Read the essay →Perspective · August 11, 2026
Agentic AI Red Teaming for Patient Access
Weak authorization and poor recovery already put patient-access systems at risk. Agentic AI can expose and repeat those failures at greater speed and scale.
Read the perspective →Follow a question
Three ways into the work.
Explore the trails → 01 02 03
What helps a patient reach care?
Start with the message, then follow the outreach pathway and the route to the clinic.
What does the evidence actually establish?
From counting appointments to evaluating a change and tracing a claim to its source.
How did I learn to build?
Computing, science, and the lessons that became personal on the clinical floor.
About Cole
Where the questions come from.
Clinical work, research, and building systems have shaped the way I think about care and the systems around it. I write to connect those experiences to the decisions and work that follow.
A little about me →Research & Publications
A closer look at the work.
A Penn Medicine case study of a customer-service workshop evaluated with Automated Quality Monitoring, matched comparison agents, and a quasi-difference-in-differences design.
Read the case study →A shared map of practices, specialties, and routes helped Jefferson outreach staff explain nearby care during live calls. It contained no patient information.
Read the case study →How one failed health-system profile became a research architecture for source acquisition, identity, governed interpretation, and publication.
Read the case study →Independent lab
Open Informatics
For current projects, source repositories and their maturity boundaries, see Open Informatics. The research infrastructure case records the work and its evidence limits.
A problem to try · Synthetic data
One report says eight.
Another says five.
What is each one counting? Look at the records, make a judgment, and see how the difference can be explained.
Open the records →8Status log
5Scheduling export