{"paper_id":"9e989bc6-d225-40f1-8734-4c120d6155b6","body_text":"R Code for Development and Temporal Validation of a Machine Learning–Based Diagnostic Model for Endometriosis Using Routine Clinical Indicators\nAuthors/Creators\n- 1. Department of Gynecology, The First Affiliated Hospital of Bengbu Medical University, Bengbu, Anhui, China\n- 2. Graduate School, Bengbu Medical University, Bengbu, Anhui, China\n- 3. School of Clinical Medicine, Bengbu Medical University, Bengbu, Anhui, China\nDescription\nThis repository contains the R code used for the formal model-development and validation analyses in the study entitled “Development and Temporal Validation of a Machine Learning–Based Diagnostic Model for Endometriosis Using Routine Clinical Indicators.” The analytical workflow includes repeated nested cross-validation, feature-selection stability assessment, comparison of six candidate algorithms, XGBoost model development, internal and temporal validation, discrimination and calibration assessment, decision-curve analysis, SHAP-based model interpretation, and benchmark comparisons.\nThe repository also provides session information documenting the R environment and package versions used for the formal analysis. Individual-level clinical data are not publicly distributed because of privacy and ethical restrictions. The fitted final XGBoost model object may be available from the corresponding author upon reasonable request, subject to applicable institutional and data-governance requirements.\nFiles\nEM_code_repository_for_Zenodo.zip\nFiles\n(14.0 kB)\n| Name | Size | Download all |\n|---|---|---|\n|\nmd5:01c9881a8529b0e420251f48030901b7\n|\n14.0 kB | Preview Download |\nAdditional details\nSoftware\n- Programming language\n- R","source_license":"CC0","license_restricted":false}