在数据集转移下的EEG深度学习的不确定性
Mats Tveter1, Thomas Tveitstøl1, Christoffer Hatlestad-Hall2
1Department of Neurology, Oslo University Hospital, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, Oslo, Norway.
Artificial intelligence in medicine
|February 6, 2026
概括
集体学习方法提高人工智能 (AI) 诊断准确度和对电脑电图 (EEG) 数据的不确定性估计. 这些人工智能模型可靠地预测认知能力下降,即使有数据转移,提高临床信任.
科学领域:
- 医学诊断 医学诊断 医学诊断
- 人工智能的人工智能
- 神经科学是一个神经科学.
背景情况:
- 将人工智能集成到医疗诊断中需要可靠的不确定性估计以及准确的预测.
- 了解预测信心对于临床决策至关重要,特别是在分布之外的场景中.
- 不确定性指标旨在使模型信心与实际表现保持一致,适应可靠性变化.
研究的目的:
- 研究集合学习策略对基于EEG的认知衰退分类中的绩效和不确定性估计的影响.
- 评估人工智能模型在分布内,分布外和数据集转移的EEG数据.
- 在各种数据扰动下评估不确定性估计的可靠性.
主要方法:
- 在大型EEG数据集上评估组合方法和蒙特卡洛脱落.
- 在三个设置中评估模型性能和不确定性:在分布中,在分布之外的概括和逐渐的数据集转移 (噪音,漂移,频率干扰).
- 利用深层组合和独立训练的模型进行强大的分类.
主要成果:
- 组合方法,特别是深层组合,在分发和分发之外的环境中始终优于其他模型.
- 集合提供了更有信息和可靠的不确定性估计在不同类型的EEG数据集转移.
- 模型多样性和独立培训被证明是有利于强大的,不确定性意识的分类.
结论:
- 集体学习策略提高了基于EEG的认知衰退检测AI模型的可靠性和准确性.
- 这些发现支持AI的临床部署,通过在数据变化下确保透明度和稳定性.
- 不确定性意识模型对于医疗保健中安全可靠的人工智能应用至关重要.
相关概念视频
04:08The Uncertainty Principle
32.6K
Werner Heisenberg considered the limits of how accurately one can measure properties of an electron or other microscopic particles. He determined that there is a fundamental limit to how accurately one can measure both a particle’s position and its momentum simultaneously. The more accurate the measurement of the momentum of a particle is known, the less accurate the position at that time is known and vice versa. This is what is now called the Heisenberg uncertainty principle. He...
32.6K
02:46Uncertainty in Measurement: Reading Instruments
53.2K
Counting is the type of measurement that is free from uncertainty, provided the number of objects being counted does not change during the process. Such measurements result in exact numbers. By counting the eggs in a carton, for instance, one can determine exactly how many eggs are there in the carton. Similarly, the numbers of defined quantities are also exact. For example, 1 foot is exactly 12 inches, 1 inch is exactly 2.54 centimeters, and 1 gram is exactly 0.001 kilograms. Quantities...
53.2K
00:59Uncertainty: Overview
1.7K
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
1.7K
03:34Uncertainty in Measurement: Significant Figures
83.3K
All the digits in a measurement, including the uncertain last digit, are called significant figures or significant digits. Note that zero may be a measured value; for example, if a scale that shows weight to the nearest pound reads “140,” then the 1 (hundreds), 4 (tens), and 0 (ones) are all significant (measured) values.
83.3K
00:54Uncertainty: Confidence Intervals
11.7K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
11.7K
00:59Propagation of Uncertainty from Random Error
2.0K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
2.0K