Prediction Model for Intrapartum Labor Analgesia Efficacy Based on Preoperative Indicators

A retrospective study of 137 parturients who received labor analgesia, aiming to develop a prediction model for analgesia efficacy. The dataset includes preoperative multidimensional indicators such as demographic data, clinical characteristics, and psychological assessments. The model was developed and validated by Biyao Wang, with results last updated in May 2026.

Use Cases

• Training machine learning models to predict labor analgesia efficacy based on preoperative indicators like pregnancy-induced hypertension.
• Comparing the performance of different algorithms (e.g., XGBoost, Random Forest) for a clinical prediction task.
• Identifying key predictive features for labor analgesia outcomes from multidimensional clinical data.
• Conducting decision curve analysis to evaluate the clinical utility of a predictive model.

Strengths

• Model performance is rigorously evaluated with specific metrics, including an AUC of 0.875 in the training set.
• The study employed multiple machine learning algorithms (LR, NB, RF, SVM, XGB) for comparative analysis.
• Feature selection was conducted using LASSO regression to refine the predictor set.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 19.4 KB, indicating limited scope.

Provenance

Source

figshare, author Biyao Wang

Collection Method

Retrospective study enrolling 137 parturients who received labor analgesia.

Freshness

Last updated 2026-05-19 05:28:32; freshness should be verified.