Development and Internal Validation of Post-Retrieval OHSS Risk Stratification Models

500 infertility patient records from a single-center retrospective study conducted between 2020 and 2023. The dataset was used to develop and internally validate machine learning models for predicting ovarian hyperstimulation syndrome risk after oocyte retrieval. The author is Xiangqian Meng, and the data was last updated on 2026-05-25.

Use Cases

• Training risk prediction models based on clinical and laboratory data from infertility patients.
• Validating model interpretability techniques using SHAP analysis on identified key predictors.
• Benchmarking the performance of Random Forest, LASSO, and other ML algorithms for a binary classification task.
• Analyzing the influence of specific predictors like number of oocytes retrieved and patient age on OHSS risk.

Strengths

• Includes data from 500 patients, with 40 diagnosed cases of OHSS.
• Model performance metrics are reported, including an AUC of 0.81 for the best-performing RandomForest model.
• Key predictive features are identified through LASSO and SHAP analysis.

Limitations

• Row count and column-level documentation are absent, requiring manual inspection after download.
• Data is from a single-center, retrospective study, which may limit generalizability.
• The dataset is small at 305.7 KB, indicating limited scope.

Provenance

Source

Jinxin Xinan Women & Children Hospital

Collection Method

Retrospective collection of clinical and laboratory data from infertile patients undergoing controlled ovarian hyperstimulation.

Time Range

2020 to 2023

Freshness

Last updated 2026-05-25 04:33:10.

Geography

Single-center study; location likely corresponds to the hospital.