2026 · Analytical chemistry · paywalled
Prolonging Sample Stability with Machine Learning Expands the Catalog of Tests Available for Mail-In Capillary Blood Collected At-Home
O'Meara et al.
The finding, in our words
A machine learning model called Remote Control was trained on 2685 blood samples to predict change due to instability, enabling accurate calibration of results to approximate the time zero value at collection. With calibration, unprocessed whole blood could be transported for up to 9 days under ambient conditions and temperatures between 3.4 and 47.4 degrees Celsius, achieving agreement with CLIA TEa between 98.1 and 100 per cent and expanding the catalog of tests available for at-home collection.
A paraphrase to the Library’s standard, never the abstract. The source is one link away and is always the authority.