Measuring the performance of prediction models to personalize treatment choice: Defining observed and predicted pairwise treatment effects.

Stat Med

Predictive Analytics and Comparative Effectiveness (PACE) Center at the Institute for Clinical Research and Health Policy Studies, Tufts Medical Center, Boston, Massachusetts, USA.

Published: October 2023

Download full-text PDF

Source
http://dx.doi.org/10.1002/sim.9719DOI Listing

Publication Analysis

Top Keywords

measuring performance
4
performance prediction
4
prediction models
4
models personalize
4
personalize treatment
4
treatment choice
4
choice defining
4
defining observed
4
observed predicted
4
predicted pairwise
4

Similar Publications

Intravascular Imaging as a Performance Measure for Percutaneous Coronary Intervention.

Circ Cardiovasc Interv

January 2025

Division of Cardiology, Department of Medicine, University of Washington Medical Center, Seattle (E.J.S., T. Salahuddin, J.A.D.).

Background: Intravascular imaging (IVI) is widely recognized to improve outcomes after percutaneous coronary intervention (PCI). However, IVI is underutilized and is not yet established as a performance measure for quality PCI.

Methods: We examined temporal trends of IVI use for all PCIs performed at Veterans Affairs hospitals in the United States from 2010 to 2022 using retrospective observational cohorts.

View Article and Find Full Text PDF

This meta-analysis focuses on the controversial efficacy and safety of microfragmented adipose tissue (MFAT) as compared with platelet-rich plasma (PRP) in the clinical treatment of knee osteoarthritis (KOA). We have attempted to provide an evidence-based medicine protocol for the conservative treatment of KOA. Researchers collected and compared randomized controlled trials (RCTs) that used microfragmented adipose tissue and platelet-rich plasma to treat knee osteoarthritis.

View Article and Find Full Text PDF

Accurate survival prediction of patients with long-bone metastases is challenging, but important for optimizing treatment. The Skeletal Oncology Research Group (SORG) machine learning algorithm (MLA) has been previously developed and internally validated to predict 90-day and 1-year survival. External validation showed promise in the United States and Taiwan.

View Article and Find Full Text PDF

The aim of this study is to investigate whether not using the calcar screw in proximal humerus fractures affects functional and radiological outcomes. Thirty patients (21 females and 9 males) who presented with proximal humerus fractures and were treated with plate- screw fixation were evaluated. The patients were divided into two groups: group 1 included patients with the use of the calcar screw, and group 2 included patients without the calcar screw.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!