← Back to all news
arXiv Machine Learning By Ayesha Tanveer, Khandakar Ahmed, Assefa Teshome, Oyetunde Gbadeyan, Ziad Nehme

Quantifying the Impact of Ambulance Ramping: A Multi-Year Analysis of Victorian Emergency Medical Services Cases

Read the original on arXiv Machine Learning →

This study analyzes 2,850,575 ambulance attendances in Victoria, Australia, to quantify ambulance ramping—the delay between hospital arrival and patient handover—across 59 hospitals and 79 local government areas from January 2020 to March 2024. It finds that cumulative ambulance hours lost (AHL) totalled 1,491,127 hours, with ten hospitals accounting for 57.8 % of lost hours. Ramping duration increases with the number of ambulances arriving at the same hospital in the preceding hour and shows a moderate correlation with hourly demand two to four hours later.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 11

Communication-efficient distributed hazard difference estimation for heterogeneous multi-site survival data

arXiv:2601. 14609v2 Announce Type: replace-cross Abstract: Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environments block patient-level data sharing and the persistent server connections required by iterative federated methods.

By Ziwen Wang, Siqi Li, Marcus Eng Hock Ong, Nan Liu
safety
More like this →
arXiv Machine Learning
5d ago

Missingness-Aware Conformal Prediction Under Cross-Hospital Distribution Shift

The paper introduces a missingness‑aware conformal calibration method for mortality prediction that accounts for cross‑hospital distribution shifts. By selecting a measurement on an independent sample, grouping patients by whether that measurement is recorded, and applying Mondrian calibration within each group, the method avoids reusing calibration outcomes. Experiments on eICU and MIMIC‑IV data show that, compared to pooled calibration, it reduces the worst‑group coverage gap by a median of 1.9 percentage points across six settings, though the benefit varies with predictor and hospital.

By Liang You, Dongwen Ou, Hengyu Shi, Siyuan Dai
More like this →