Optimising antibiotic switching via forecasting of patient physiology
Magnus Ross, Nel Swanepoel, Akish Luintel, Emma McGuire, Ingemar J Cox, Steve Harris, Vasileios Lampos · 2026
Read Optimising antibiotic switching via forecasting of patient physiology by Magnus Ross, Nel Swanepoel, Akish Luintel, Emma McGuire, Ingemar J Cox, Steve Harris, Vasileios Lampos (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-13635169.txt.
Description
Magnus Ross and six colleagues forecast patients' vital signs to time the switch from drip to pill antibiotics, in a study from two thousand twenty-six. To switch early shortens stays in hospital. It also cuts catheter infections in the ward. Yet one in five patients in England stays on intravenous antibiotics despite qualifying to switch.
Their system models vital sign trajectories probabilistically, with neural processes at its core. Switch readiness is judged by comparing forecasts against clinical guidelines. It is not judged by copying the habits of past doctors. Patients are ranked by review priority for the ward team. Validation used American intensive care data for the tests. It also used the records of a British hospital group. The system brought up several times more relevant candidates than baseline approaches. Guideline-based forecasting also adapts as guidelines change. It does so with no retraining of the model at all.
Catalog record
| CREATOR | Magnus Ross, Nel Swanepoel, Akish Luintel, Emma McGuire, Ingemar J Cox, Steve Harris, Vasileios Lampos |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 71 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |