Metrological and Algorithmic Traceability of Machine Learning in Laboratory Medicine
Qing Li, Mario Plebani · 2026
Read Metrological and Algorithmic Traceability of Machine Learning in Laboratory Medicine by Qing Li, Mario Plebani (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/PMC13402924.txt.
Description
Qing Li and Mario Plebani argue that machine learning in laboratory medicine needs two kinds of traceability kept distinct. One is the metrological kind that anchors a measurement to reference standards. The other is an algorithmic kind that lets auditors rebuild how a model turned data into output. Labs now use learning models to interpret tests, predict outcomes, and run operations, and each use carries different proof burdens.
A model can eat perfectly traceable lab values yet transform them in ways that leak information, hide uncertainty, or drift after deployment as methods and populations shift. The authors propose a functional framework aligning calibration thinking with model documentation, plus traceability dossiers and tiered rules backed by international teamwork. Their aim is reproducibility and comparability strong enough for clinical trust, without pretending a training set is a reference material.
Catalog record
| CREATOR | Qing Li, Mario Plebani |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 29 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |