Simulating A/B testing versus SMART designs for LLM-driven patient engagement to close preventive care gaps
Sanjay Basu, Dean Schillinger, Sadiq Y Patel, Joseph Rigdon · 2024
Read Simulating A/B testing versus SMART designs for LLM-driven patient engagement to close preventive care gaps by Sanjay Basu, Dean Schillinger, Sadiq Y Patel, Joseph Rigdon (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11574204.txt.
Description
Health programs send reminders to close gaps in screening and shots, but one message does not fit all patients. Sanjay Basu and co-authors used simulations in 2024 to compare two trial designs for tailoring such outreach with language models. One design is the classic A/B test; the other adapts treatment in stages based on each person's response.
Across many scenarios, the staged design gave better value for money and net benefit. It beat the simple test at spotting differing effects only in later stages, when groups were more alike and small differences decided engagement. The study helps programs choose how to test tiered help, mixing automated messages with human support, at a population scale.
Catalog record
| CREATOR | Sanjay Basu, Dean Schillinger, Sadiq Y Patel, Joseph Rigdon |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |