Larger sample sizes are needed when developing a clinical prediction model using machine learning in oncology: methodological systematic review.

Background: Having a sufficient sample size is crucial when developing a clinical prediction model. We reviewed details of sample size in studies developing prediction models for binary outcomes using machine learning (ML) methods within oncology and compared the sample size used to develop the models with the minimum required sample size needed when developing a regression-based model (N).

Methods: We searched the Medline (via OVID) database for studies developing a prediction model using ML methods published in December 2022.

Development and internal validation of prognostic models for event-free survival in newly diagnosed Ewing sarcoma patients based on routinely collected clinical characteristics from the European randomised controlled trial, EE2012.

Introduction: Ewing sarcoma is a rare paediatric cancer. Currently, there is no way of accurately predicting these patients' survival at diagnosis. Disease type (ie, localised disease, lung/pleuropulmonary metastases and other metastases) is used to guide treatment decisions, with metastatic patients generally having worse outcomes than localised disease patients.

Improving Sternal Closure Outcomes in Cardiac Surgery: Polyethylene Suture Tapes vs. Steel Wires.

Steel wires are often inadequate for sternal closure for patients at high risk of sternal complications. This study compares a novel sternal closure system to conventional steel wires to assess its potential to reduce sternal complication rates and improve clinical outcomes. A retrospective study was conducted on 300 consecutive patients undergoing cardiac surgery via median sternotomy.