Publications by authors named "B Van Calster"
Objectives: Identifying cardiac surgical patients at risk of requiring red blood cell (RBC) transfusion is crucial for optimizing their outcome. We critically appraised prognostic models preoperatively predicting perioperative exposure to RBC transfusion in adult cardiac surgery and summarized model performance.
Methods: Design: Systematic review and meta-analysis.
Article Synopsis
- - The ROCkeTS study aimed to find the best diagnostic test for ovarian cancer in symptomatic postmenopausal women by comparing multiple risk-prediction models in a real-world setting.
- - Researchers recruited women aged 16-90 with non-specific symptoms and abnormal test results from 23 UK hospitals, excluding those with certain conditions like normal CA125 levels or other cancers.
- - The study involved various diagnostic models and tests, including CA125 levels and ultrasound assessments, to evaluate their effectiveness in predicting ovarian cancer risk among the participants.
Background: Random forests have become popular for clinical risk prediction modeling. In a case study on predicting ovarian malignancy, we observed training AUCs close to 1. Although this suggests overfitting, performance was competitive on test data.
View Article and Find Full Text PDFObjectives: Multicategory prediction models (MPMs) can be used in health care when the primary outcome of interest has more than two categories. The application of MPMs is scarce, possibly due to added methodological complexities compared to binary outcome models. We provide a guide of how to develop, validate, and update clinical prediction models based on multinomial logistic regression.
View Article and Find Full Text PDF