相关实验视频

Updated: Jan 10, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

使用预期的实用性来评估人工智能启用规则外置设备的乳房扫描查的使用

Kwok Lung Fan¹, Yee Lam Elim Thompson¹, Weijie Chen¹

¹US Food and Drug Administration, Silver Spring, MD, USA.

Medical decision making : an international journal of the Society for Medical Decision Making

|November 24, 2025

概括

评估人工智能 (AI) 排除癌症查设备需要超出灵敏度和特异性的指标. 预期效用 (EU) 分析表明,这些人工智能工具在回顾性研究中并不能显著改善查性能.

科学领域:

医疗成像医学成像
医疗保健中的人工智能
放射学放射学是一门学科.

背景情况:

人工智能 (AI) 排除设备旨在通过过出正常患者图像来减少放射科医生的工作量.
传统的性能指标,如灵敏度和特异性,对于对AI排除器件的回顾性评估是模两可的.
追溯研究往往显示出因排除应用程序的性质而导致敏感性偏差的结果.

研究的目的:

为了比较仅为放射科医生和放射科医生与AI排除设备的工作流程之间的查性能.
评估正/负预测值 (PPV/NPV) 和预期效用 (EU) 的实用性,作为绩效指标.
评估人工智能排除设备对乳房扫描查结果的影响.

主要方法:

修订了PPV/NPV和EU指标,用于性能比较.
将PPV/NPV和EU应用于评估AI排除装置的美国追溯数据集.
应用了欧盟对欧洲数据集的应用,使用各种AI值的召回率和癌症检测率.

主要成果:

在美国的研究中,PPV/NPV和EU都没有显示出人工智能排除装置的显著性能改善.
欧盟分析表明,当AI排除了欧洲研究中的更多患者时,整体查性能较低.
欧盟指标显示,人工智能排除患者的增加,包括虚假阴性,降低了查效率.

结论:

敏感性和特异性对于评估回顾性AI规则排除设备是模两可的.
PPV/NPV和欧盟指标可以解决模两可的问题,当地面真相无法获得时,欧盟特别有用.
预期的实用性分析表明,当前的AI规则排除设备可能不会在回顾性设置中提高乳房镜检查性能.

关键词:

预期的效用预期的效用检查的mammography检查的mammography检查的mammography检查的mammography检查的mammography检查的mammography检查的评价评价评价评价没有 rule-out 的规则.半自主的人工智能/MLML

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

相关概念视频

Decision Making: P-value Method

Decision Making: P-value Method

The process of hypothesis testing based on the P-value method includes calculating the P- value using the sample data and interpreting it.
First, a specific claim about the population parameter is proposed. The claim is based on the research question and is stated in a simple form. Further, an opposing statement to the claim is also stated. These statements can act as null and alternative hypotheses: a null hypothesis would be a neutral statement while the alternative hypothesis can...