Optimising antibiotic switching via forecasting of patient physiology
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912955172388864 |
|---|---|
| author | Ross, Magnus Swanepoel, Nel Luintel, Akish McGuire, Emma Cox, Ingemar J. Harris, Steve Lampos, Vasileios |
| author_facet | Ross, Magnus Swanepoel, Nel Luintel, Akish McGuire, Emma Cox, Ingemar J. Harris, Steve Lampos, Vasileios |
| contents | Timely transition from intravenous (IV) to oral antibiotic therapy shortens hospital stays, reduces catheter-related infections, and lowers healthcare costs, yet one in five patients in England remain on IV antibiotics despite meeting switching criteria. Clinical decision support systems can improve switching rates, but approaches that learn from historical decisions reproduce the delays and inconsistencies of routine practice. We propose using neural processes to model vital sign trajectories probabilistically, predicting switch-readiness by comparing forecasts against clinical guidelines rather than learning from past actions, and ranking patients to prioritise clinical review. The design yields interpretable outputs, adapts to updated guidelines without retraining, and preserves clinical judgement. Validated on MIMIC-IV (US intensive care, 6,333 encounters) and UCLH (a large urban academic UK hospital group, 10,584 encounters), the system selects 2.2-3.2$\times$ more relevant patients than random. Our results demonstrate that forecasting patient physiology offers a principled foundation for decision support in antibiotic stewardship. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08242 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Optimising antibiotic switching via forecasting of patient physiology Ross, Magnus Swanepoel, Nel Luintel, Akish McGuire, Emma Cox, Ingemar J. Harris, Steve Lampos, Vasileios Machine Learning Applications Timely transition from intravenous (IV) to oral antibiotic therapy shortens hospital stays, reduces catheter-related infections, and lowers healthcare costs, yet one in five patients in England remain on IV antibiotics despite meeting switching criteria. Clinical decision support systems can improve switching rates, but approaches that learn from historical decisions reproduce the delays and inconsistencies of routine practice. We propose using neural processes to model vital sign trajectories probabilistically, predicting switch-readiness by comparing forecasts against clinical guidelines rather than learning from past actions, and ranking patients to prioritise clinical review. The design yields interpretable outputs, adapts to updated guidelines without retraining, and preserves clinical judgement. Validated on MIMIC-IV (US intensive care, 6,333 encounters) and UCLH (a large urban academic UK hospital group, 10,584 encounters), the system selects 2.2-3.2$\times$ more relevant patients than random. Our results demonstrate that forecasting patient physiology offers a principled foundation for decision support in antibiotic stewardship. |
| title | Optimising antibiotic switching via forecasting of patient physiology |
| topic | Machine Learning Applications |
| url | https://arxiv.org/abs/2603.08242 |