Emergency Department Daily Arrivals with Meteorological and Calendar Features

A 9.5 KB dataset supporting a study on forecasting daily Emergency Department patient arrivals. The data likely contains daily arrival counts alongside meteorological and calendar variables used to develop and compare ARIMA, ANN, LSTM, GLM, and hybrid forecasting models. Hamed Tabesh published the dataset on figshare under a CC-BY-4.0 license, with a last update timestamp of 2026-04-30.

Use Cases

• Benchmarking hybrid forecasting algorithms (ARIMA-ANN) based on the described model comparison.
• Analyzing the impact of meteorological factors on emergency department demand as mentioned in the study.
• Evaluating model performance across short, intermediate, and long forecasting horizons as detailed in the results.
• Training time-series models for patient flow prediction using calendar and weather-related input features.

Strengths

• Includes specific performance metrics (e.g., RMSE, ME, SMAPE) for six different forecasting algorithms, allowing for direct comparison.
• Dataset is openly licensed under CC-BY-4.0, facilitating reuse and sharing.
• The study description explicitly incorporates both linear and nonlinear relationships via hybrid modeling approaches.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is very small (9.5 KB), indicating limited scope, possibly containing only summary statistics or a subset of features.

Provenance

Source

figshare, author Hamed Tabesh.

Collection Method

Likely collected for a research study on ED forecasting, but the specific collection method is not detailed.

Freshness

Last updated 2026-04-30 17:47:37; freshness should be verified.