同行:通过基于患者的早期退出与拒绝进行可靠和有效的推断
Zaifu Zhan1, Shuang Zhou2, Rui Zhang2
1Department of Electrical and Computer Engineering, University of Minnesota, 200 Union St SE, Minneapolis, 55455, MN, USA.
Journal of biomedical informatics
|January 22, 2026
概括
一个新的框架PEER通过将拒绝机制与早期退出相结合来增强生物医学AI. 这确保了可靠的预测和在各种医疗数据和模型中有效的推断.
科学领域:
- 人工智能的人工智能
- 生物医学信息学 生物医学信息学
- 机器学习 机器学习
背景情况:
- 生物医学AI模型需要在推断效率和预测可靠性之间保持平衡.
- 基于患者的早期退出 (PABEE) 加快推断,但与不确定的预测作斗争.
研究的目的:
- 引入PEER (基于耐心的早期退出与拒绝),一个统一的框架,将PABEE与拒绝机制相结合.
- 在没有再培训的情况下,在生物医学应用中实现高效可靠的AI推断.
主要方法:
- PEER 将一个拒绝机制集成到 PABEE 中,使用耐心计数器来跟踪预测的一致性.
- 模型要么做出预测,要么拒绝不确定的输入,避免不可靠的最终层预测.
- 在11个生物医学数据集 (文本和图像) 上使用变压器骨干进行评估,测量精度,宏F1和加速度比.
主要成果:
- 在保持早期退出效率增长的同时,PEER始终提高了可靠性.
- 通过拒绝2.79%的不确定样本,在MIMIC-III上获得了90.73%的准确性,超过了基线.
- 在具有可比性能的高效设置中显示了80%的加速度比率.
- 成功地避免了不确定的情况,改善了跨不同数据集和模式的预测可靠性.
- 在各种架构,尺度和模式 (语言和视觉) 中展示了概括.
结论:
- PEER提供了一个简单的,架构无关的框架,用于快速和可靠的AI推断.
- 它在语言和视觉模型中的通用性显示了临床决策支持系统的巨大潜力.
相关概念视频
01:29Reliability and Validity
13.8K
Reliability and validity are two important considerations that must be made with any type of data collection. Reliability refers to the ability to consistently produce a given result. In the context of psychological research, this would mean that any instruments or tools used to collect data do so in consistent, reproducible ways.
13.8K
01:23Influence of Parents and Peers on Identity
483
Adolescence is a pivotal period of identity formation, during which individuals begin to answer questions central to their sense of self, such as "Who am I?" and "Who do I hope to become?" Both parents and peers play critical roles in guiding adolescents through this complex developmental phase.
Parental Influence on Identity Development
Parents serve as primary guides and managers in an adolescent's life, offering support instrumental in decision-making and personal growth....
Parental Influence on Identity Development
Parents serve as primary guides and managers in an adolescent's life, offering support instrumental in decision-making and personal growth....
483
01:15Theory of Attribution I: Correspondent Inference Theory
490
Correspondent inference theory, proposed by Jones and Davis in 1965, seeks to explain how individuals infer stable personality traits from observed behaviors. It suggests that people attribute actions to underlying dispositions rather than external circumstances, particularly when the behavior appears intentional and socially significant.Voluntary Behavior and Dispositional AttributionAccording to this theory, individuals are more likely to attribute behavior to personal traits when it appears...
490
01:02Quantifying and Rejecting Outliers: The Grubbs Test
3.7K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
3.7K
01:17Hypothesis: Accept or Fail to Reject?
29.4K
The outcome of any hypothesis testing leads to rejecting or not rejecting the null hypothesis. This decision is taken based on the analysis of the data, an appropriate test statistic, an appropriate confidence level, the critical values, and P-values. However, when the evidence suggests that the null hypothesis cannot be rejected, is it right to say, 'Accept' the null hypothesis?
There are two ways to indicate that the null hypothesis is not rejected. 'Accept' the null...
There are two ways to indicate that the null hypothesis is not rejected. 'Accept' the null...
29.4K
01:25Distribution Reliability and Automation
498
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
498