Table 1_Machine learning model for predicting hypotension following continuous renal repla

A dataset of 1,103 adult patients with end-stage kidney disease who underwent continuous renal replacement therapy (CRRT). It was used to develop and compare multiple machine learning models for predicting intradialytic hypotension (IDH) within 6 hours of CRRT initiation. The dataset was created by Shuang Qiu and last updated in May 2026.

Use Cases

• Training predictive models for intradialytic hypotension based on demographic, medication, laboratory, and treatment-related variables.
• Benchmarking machine learning algorithms like SVM, XGBoost, and Random Forest on clinical outcome prediction tasks.
• Applying SHAP analysis to interpret feature importance, such as systolic blood pressure, in a clinical prediction model.

Strengths

• Dataset contains 1,103 patient records, providing a substantive sample size for model development.
• Model performance was rigorously evaluated, with the SVM model achieving an AUC of 0.805.
• Includes multiple definitions of the target outcome (IDH) for model robustness testing.

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 small in file size (533.3 KB), suggesting limited scope or feature set.

Provenance

Source

figshare

Collection Method

Data was collected from adult patients with end-stage kidney disease undergoing CRRT.

Freshness

Last updated 2026-05-15 05:44:59