A highly accurate risk factor-based XGBoost multiethnic model for identifying patients with skin cancer

All work done in All Of Us (AoU) Researcher Workbench:cancer.extract_data.ipynb obtains the data from the AoU OMOP databasecancer.clean_data.ipynb refines the data (re-annotates ancestry, calculate age, reannotates survey data)cancer.analysis_epidemiology.ipynb performs the analyses and predictionscancer.skin_cancer_predictor.manuscript_prepare_data.ipynb prepares the data for figures and tablescancer.skin_cancer_predictor.manuscript.ipynb generates figures and tables for the manuscriptcancer.analysis_epidemiology.all_current_date.ipynb performs the predictions using current date for all individuals<br>

所有工作均在All Of Us（AoU）研究人员工作台中完成：`cancer.extract_data.ipynb` 从AoU的OMOP数据库中获取数据；`cancer.clean_data.ipynb` 对数据进行精细化处理，包括重新注释祖先信息、计算年龄以及重新标注调查数据；`cancer.analysis_epidemiology.ipynb` 执行数据分析与预测任务；`cancer.skin_cancer_predictor.manuscript_prepare_data.ipynb` 为论文图表与表格准备所需数据；`cancer.skin_cancer_predictor.manuscript.ipynb` 生成论文所需的图表与表格；`cancer.analysis_epidemiology.all_current_date.ipynb` 针对所有个体使用当前日期开展预测分析。