---
title: "Hierarchical Spatio-Temporal Transformer for Coherent Emergency Department Forecasting"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.27106v1"
permalink: "https://feed.astralor.com/items/itm_4d79891245020ee706f77267"
published: "2026-07-29T16:33:18.000Z"
score: 81
channel: "ai"
tags: ["HierSTT","Transformer","ED forecasting"]
---

# Hierarchical Spatio-Temporal Transformer for Coherent Emergency Department Forecasting

## AI commentary

> This paper addresses a long-overlooked issue in healthcare demand forecasting—cross-level coherence. HierSTT demonstrates its effectiveness on real-world data with an elegant hierarchical Transformer design and coherence loss. It is a valuable framework for medical AI researchers and hospital operations managers.

## At a glance

This paper proposes HierSTT, a hierarchical Transformer-based framework for jointly predicting emergency department demand at hospital, regional, and national levels. The model uses a Temporal Fusion Transformer for national dynamics and spatio-temporal Transformer encoder-decoder modules for regional and hospital demand conditioned on higher-level forecasts. On a nationwide Portuguese dataset covering 81 hospitals across 5 regional health administrations, HierSTT reduces average WAPE by 32% relative to the best non-hierarchical baseline while producing near-coherent predictions across levels.

## Key points

- Proposes HierSTT, an end-to-end hierarchical Transformer framework for jointly predicting ED demand at hospital, regional, and national levels.
- Introduces a coherence-aware loss function to penalize cross-level inconsistencies.
- On a Portuguese dataset of 81 hospitals, reduces average WAPE by 32% over existing methods while maintaining prediction coherence.

## Full text

Emergency Departments (EDs) are critical access points in healthcare systems, yet they face persistent pressure from unpredictable patient demand, seasonal surges, and non-urgent visits. Effective ED planning requires forecasts at multiple decision-making levels: hospitals need local demand estimates for staffing and bed management, regions require forecasts to coordinate healthcare units, and national authorities need system-wide projections for capacity planning. However, most existing approaches forecast ED demand independently at a single level, ignoring the hierarchy linking hospitals, regions, and national systems. This can produce incoherent predictions, where hospital-level forecasts do not aggregate consistently to regional or national demand. We propose HierSTT, a hierarchical Transformer-based framework for coherent multi-level ED forecasting. HierSTT jointly predicts hospital, regional, and national level demand in a single end-to-end model. A Temporal Fusion Transformer captures national dynamics, while spatio-temporal Transformer encoder-decoder modules model regional and hospital demand conditioned on higher-level forecasts. A coherence-aware loss penalizes cross-level inconsistencies during training. We further introduce a nationwide Portuguese ED dataset covering 81 hospitals across 5 regional health administrations, with heterogeneous covariates at each level. Experiments show that HierSTT reduces average WAPE by 32\% relative to the best non-hierarchical deep learning baseline and outperforms all classical hierarchical reconciliation methods, while producing near-coherent predictions across levels. Additional resources associated with this work are available at https://github.com/FilipaLino/HierSTT.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_4d79891245020ee706f77267