An illustrated Joseph L. Smith walking through an Art Deco digital forest

Joseph L. Smith

I design real-world evidence studies, test AI in healthcare workflows, and lead research teams.

I design and lead real-world evidence studies. The work starts with the decision, then moves to the question, data, methods, and team needed to answer it.

Areas of workReal-world evidence
Healthcare AI
Research leadership

What I do

Study design, practical AI, and research leadership.

Recent writing

Essays on study design, real-world evidence, healthcare AI, and leadership.

All writing
Healthcare RWE

Treatment Failure Is an Endpoint, Not a Code

In real-world evidence, treatment failure and non-response are endpoint contracts. The analyst has to define the adequate trial, the failure components, the source of each signal, and the intercurrent events before the data can mean anything.

Read the note
Healthcare RWE

Target Trial Emulation, Explained for Operators

Most observational studies fail in the design, not the analysis. Target trial emulation is the protocol habit that prevents it: specify the randomized trial you would run if you could, then emulate every element - eligibility, time zero, strategies, and contrast - explicitly in real-world data.

Read the note

Other projects

RWEdnesdays covers real-world evidence methods. JoeSmith.ai covers practical AI tools and experiments.

View both projects

Contact

Send a note about RWE study design, healthcare AI, research collaboration, teaching, or leadership.

Send a message