Adult Idiopathic Nephrotic Syndrome Relapse Predictions, 2022-2024

562 adult patient records were used to develop and compare machine learning models for predicting relapse in idiopathic nephrotic syndrome. The deep learning model achieved the best performance, with a test AUC of 0.883. The dataset, created by Mingrui Zhao and last updated in April 2026, includes baseline clinical and laboratory variables.

Use Cases

• Building relapse prediction models based on baseline clinical and laboratory data.
• Comparing traditional logistic regression with ensemble and deep learning methods for a medical outcome.
• Analyzing feature importance for relapse risk, using predictors like steroid resistance and proteinuria.
• Studying techniques for handling class imbalance in medical datasets, as SMOTE was applied.

Strengths

• Includes 562 patient records for model development and evaluation.
• Model performance metrics (AUC, accuracy, sensitivity) are reported for three different algorithms.
• Key predictive features, such as steroid resistance and prior relapse history, are identified in the description.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data table is unknown, which may limit suitability assessment.
• The 12.8 KB file size suggests the dataset is very small, potentially containing only summary results or a limited sample.

Provenance

Source

Mingrui Zhao via figshare.

Collection Method

Retrospective cohort study of patients treated between January 2022 and January 2024.

Time Range

2022-2024

Freshness

Last updated 2026-04-13 04:30:44; freshness should be verified.

Geography

null