Misleading metrics in classification tasks: a closer look at negative predictive value in the context of post-ERCP pancreatitis prediction.

Gastrointest Endosc

Gastroenterology and Liver Diseases Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran.

Published: March 2025

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.gie.2024.10.044DOI Listing

Publication Analysis

Top Keywords

misleading metrics
4
metrics classification
4
classification tasks
4
tasks closer
4
closer negative
4
negative predictive
4
predictive context
4
context post-ercp
4
post-ercp pancreatitis
4
pancreatitis prediction
4

Similar Publications

Oral Health Misinformation on Youtube - A Content Analysis.

J Pharm Bioallied Sci

December 2024

Department of Public Health Dentistry, CRRI, Sathyabama Dental College and Hospital, Chennai, Tamil Nadu, India.

Introduction: With the rise of social media and widespread smartphone use, information is now readily accessible worldwide. However, the credibility of this information often remains unchecked. Few studies have evaluated oral health content on online platforms.

View Article and Find Full Text PDF

Quality and reliability evaluation of YouTube® exercises content for temporomandibular disorders.

BMC Oral Health

February 2025

Department of Physiotherapy and Rehabilitation, Faculty of Health Sciences, Tokat Gaziosmanpaşa University, Tokat, 60250, Turkey.

Objectives: YouTube is a popular source for health-related content, including exercises for temporomandibular disorders (TMD). This study aimed to evaluate the content and quality of YouTube videos on TMD exercises.

Methods: A systematic search on YouTube using keywords related to TMD exercises and rehabilitation identified relevant videos.

View Article and Find Full Text PDF

The proliferation of algorithm-assisted decision making has prompted calls for careful assessment of algorithm fairness. One popular fairness metric, equal opportunity, demands parity in true positive rates (TPRs) across different population subgroups. However, we highlight a critical but overlooked weakness in this measure: at a given decision threshold, TPRs vary when the underlying risk distribution varies across subgroups, even if the model equally captures the underlying risks.

View Article and Find Full Text PDF

Clinical endpoints, such as overall survival, directly measure relevant outcomes. Surrogate endpoints, in contrast, are intermediate, stand-in measures of various tumour-related metrics and include tumour growth, tumour shrinkage, blood results, etc. Surrogates may be a time point measurement, that is, tumour shrinkage at some point (eg, response rate) or biomarker-assessed disease status, measured at given time points (eg, circulating tumour DNA, ctDNA).

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!