Optimising antibiotic switching via forecasting of patient physiology

TL;DR

This paper introduces a neural process-based system that forecasts patient vital signs to improve the timing of switching from IV to oral antibiotics, enhancing clinical decision-making and patient outcomes.

Contribution

It presents a novel probabilistic modeling approach that predicts switch readiness without relying on historical decision data, adaptable to updated guidelines.

Findings

Selects 2.2-3.2 times more relevant patients than random

Validated on large ICU datasets from US and UK hospitals

Demonstrates improved decision support for antibiotic stewardship

Abstract

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.