Prospective validation of an AI algorithm to identify adult-onset type 1 diabetes misclassification: protocol for a non-interventional multicentre study
Irene Brusini, Suyin Lee, Alvi Lai, Amanda Sees, Matthew Hackenberg, Greg Liptak, Ajay D Rao, Catherine Anastasopoulou, Nadejda Leavitt · 2026
Read Prospective validation of an AI algorithm to identify adult-onset type 1 diabetes misclassification: protocol for a non-interventional multicentre study by Irene Brusini, Suyin Lee, Alvi Lai, Amanda Sees, Matthew Hackenberg, Greg Liptak, Ajay D Rao, Catherine Anastasopoulou, Nadejda Leavitt (2026) 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/PMC13264913.txt.
Description
Irene Brusini and co-authors wrote a 2026 protocol for a study testing an AI tool that flags adults whose type 1 diabetes was wrongly labeled type 2. The mix-up delays right treatment and raises the risk of a dangerous crisis called ketoacidosis. The tool was built on national records data and sharpened on regional exchange data, but live proof was missing.
The study will run at two health systems in southeastern Pennsylvania. At the start, the tool will score every adult listed as type 2, using two years of past data. Patients above a set score will go to doctors for chart review and guideline-based follow-up, including antibody tests where fitting. The main measure is how many flagged patients truly have type 1 diabetes. Interviews will probe how doctors adopt and trust the tool.
Catalog record
| CREATOR | Irene Brusini, Suyin Lee, Alvi Lai, Amanda Sees, Matthew Hackenberg, Greg Liptak, Ajay D Rao, Catherine Anastasopoulou, Nadejda Leavitt |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 44051 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |