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.

The Value of Clinical Prediction Models in General Practice: A Qualitative Study Exploring the Perspectives of People With Lived Experience of Depression and General Practitioners.

Introduction: Prediction models are increasingly being used to guide clinical decision making in primary care. There is a lack of evidence exploring the views of patients and general practitioners (GPs) in primary care around their use and implementation. We aimed to better understand the perspectives of GPs and people with lived experience of depression around the use of prediction models and communication of risk in primary care.

A Glucose-Responsive Glucagon-Micelle for the Prevention of Hypoglycemia.

While glucose-responsive insulin delivery systems are in widespread clinical use to treat insulin insufficiency, the on-demand supplementation of glucagon for acute hypoglycemia treatment remains understudied. A self-regulated glucagon release material is highly desired to mitigate the potential risks of severe insulin-induced hypoglycemia. Here, we describe a glucose-responsive polymeric nanosystem with glucagon covalently grafted to the end-group.

Alternative substrate kinetics of SARS-CoV-2 Nsp15 endonuclease reveals a specificity landscape dominated by RNA structure.

Coronavirus endoribonuclease Nsp15 contributes to the evasion of host innate immunity by suppressing levels of viral dsRNA. Nsp15 cleaves both ssRNA and dsRNA in vitro with a strong preference for unpaired or bulged U residues, and its activity is stimulated by divalent ions. Here, we systematically quantified effects of RNA sequence and structure context that define its specificity.