在精密瘤学中重新审视AI解释性:为什么预测准确性不能确保稳定的特征重要性
Souichi Oka1, Yoshiyasu Takefuji2
1Science Park Corporation, 3-24-9 Iriya-Nishi, Zama 252-0029, Japan.
Cancers
|February 27, 2026
概括
在瘤学中,机器学习的解释性通常是不可靠的. 这项研究引入了特征排名一致性,以确保稳定,可靠的AI解释精密瘤学,优先考虑稳定性与临床使用的准确性.
科学领域:
- 在瘤学瘤学.
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 人工智能 (AI) 在瘤学中越来越重要,用于风险预测,治疗计划和生物标志物发现.
- 当前的人工智能评估通常将高预测准确度等同于可靠的解释,可能会损害可重现性和临床决策.
- 这项研究解决了针对瘤学的人工智能的强有力的解释性指标的需求.
研究的目的:
- 通过引入特征排名顺序一致性作为一个以稳定性为重点的指标,重新评估在瘤学中的AI解释性.
- 评估AI模型解释如何响应最小的输入扰动.
- 确保人工智能模型提供可靠和临床可行的见解.
主要方法:
- 将监督模型 (线性回归,LASSO,随机森林,XGBoost) 与未监督/统计方法 (PCA,高度可变的基因选择,斯皮尔曼等级相关性) 进行比较,使用癌症基因组图谱 (TCGA) 乳腺癌多组数据.
- 通过测试在删除排名最高的特征 (<0.1%的扰动) 后的一致性来评估特征排名稳定性.
- 使用随机森林分类器评估预测性能,具有10倍的交叉验证.
主要成果:
- 被监督的模型表明,即使在最小的干扰下,特征重要性排名也不稳定,这表明尽管预测准确度高,但解释可能脆弱或误导.
- 无监督的方法,特别是高度可变的基因选择和斯皮尔曼等级相关性,始终产生稳定和生物学连贯的特征集.
- 与监督方法相比,这些稳定方法保持了竞争力的预测性能.
结论:
- 解释性不稳定性是阻碍许多机器学习模型在瘤学中的临床应用的一个重大限制.
- 将基于稳定性的标准,如特征排名一致性,整合到AI评估框架中,对于可重复和可信的结果至关重要.
- 优先考虑可解释性与准确性是人工智能在精密瘤学中的负责任和有效部署的关键.
相关概念视频
01:13Sensitivity, Specificity, and Predicted Value
1.5K
In healthcare diagnostics, laboratory tests play a crucial role in identifying and diagnosing a wide range of medical conditions. However, interpreting test results is not always straightforward. An abnormal test result does not always confirm the presence of a disease, just as a normal result does not guarantee its absence. To assess the reliability of these diagnostic tools, healthcare practitioners rely on two key statistical indicators: sensitivity and specificity.
Sensitivity is the...
Sensitivity is the...
1.5K
01:15Receiver Operating Characteristic Plot
519
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
519
02:07Improving Translational Accuracy
15.3K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
15.3K
02:07Improving Translational Accuracy
3.7K
3.7K
01:52Accuracy and Precision
16.4K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value. Highly accurate...
16.4K
01:20Biostatistics: Overview
945
Biostatistics plays a crucial role in understanding and analyzing data in healthcare and biology. Biostatisticians conduct experiments, gather evidence, and draw meaningful conclusions using statistical methods and techniques. Different variables form the foundation of biostatistical analysis, allowing researchers to understand and interpret data effectively. These variables are classified into different types, each serving a specific purpose in statistical analysis.
Discrete variables are...
Discrete variables are...
945