COVID-19 Hospital Treatment Plan: Patient Length of Stay Prediction Data

Length of stay data for hospital patients, categorized into 11 classes from 0-10 days to over 100 days. The dataset includes features related to patient demographics, hospital characteristics, and admission details to support resource allocation planning during the COVID-19 pandemic. It is hosted on OpenML under a CC0-1.0 license.

Use Cases

• Predict patient length of stay based on admission type and illness severity to optimize bed allocation.
• Identify high-risk patients for extended stays using features like age, department, and bed grade to tailor treatment plans.
• Analyze hospital resource strain by correlating available extra rooms with patient admission patterns and stay duration.
• Model the impact of hospital region and city on patient length of stay for regional healthcare planning.

Strengths

• Target variable (Length of Stay) is divided into 11 distinct classes for granular prediction.
• Includes multiple categorical features describing hospital type, department, ward, and admission details.
• Dataset description explicitly links the data to COVID-19 pandemic resource management challenges.

Limitations

• Row count, file size, and sample data are unknown, limiting suitability assessment.
• Last update date and author/organization details are unknown; freshness is unverified.
• Column-level documentation is absent for some fields; field semantics must be inferred after download.

Provenance

Source

OpenML