Evidence of unreliable data and poor data provenance in clinical prediction model research and clinical practice
Alexander D Gibson, Nicole M White, Gary S Collins, Adrian G Barnett · 2026
Read Evidence of unreliable data and poor data provenance in clinical prediction model research and clinical practice by Alexander D Gibson, Nicole M White, Gary S Collins, Adrian G Barnett (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/pmc-13352761.txt.
Description
Alexander D Gibson and others studied unreliable data behind medical forecast models, gave their warning in 2026. Forecast tools are often built from large routinely gathered banks, and sound decisions depend on those data being sound and clearly sourced. The team focused on two widely reused Kaggle banks, on stroke and diabetes, whose origins were unclear.
Exploratory checks studied the banks for quality problems and reporting gaps, and the authors traced how often peer-surveyed forecast studies had relied on them. The work shows how weak provenance can quietly spread through issued models. It urges teams and editors to verify a dataset's history before building or trusting a medical forecast tool.
Catalog record
| CREATOR | Alexander D Gibson, Nicole M White, Gary S Collins, Adrian G Barnett |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |