MIMIC_Extract_LOS_3: ICU Patient Length-of-Stay Prediction from Prescriptions

MIMIC-III data from Kaggle, focusing on the PRESCRIPTIONS table for predicting hospital length of stay. The dataset was created by Alistair Johnson, Tom Pollard, and Roger Mark. The description details a comprehensive list of drug administration route abbreviations used in clinical practice.

Use Cases

• Predicting patient length of stay in the ICU based on prescription administration routes.
• Assessing patient condition severity for early clinical intervention based on treatment patterns.
• Analyzing correlations between specific drug delivery methods (e.g., IV, oral) and hospital stay duration.

Strengths

• Based on the widely-used MIMIC-III clinical database.
• Description provides a detailed clinical key for over 60 drug administration route abbreviations.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Kaggle, originating from the MIMIC-III database.

Collection Method

Extracted from the MIMIC-III PRESCRIPTIONS table.

Time Range

null

Freshness

Last updated date is unknown.

Geography

null