可解释的人工智能用于死亡率预测:使用MIMIC-III数据集进行比较研究
Niusha Shafiabady1,2, Dave Akume2, Mohammadreza Haghighat3
1Women in AI for Social Good Lab & Discipline of IT, Australian Catholic University, North Sydney, New South Wales, Australia Niusha.Shafiabady@acu.edu.au.
BMJ health & care informatics
|February 26, 2026
概括
机器学习模型准确地预测了重症监护室 (ICU) 的死亡率,额外树和梯度增强显示了最高的性能. 可解释的人工智能确定了关键的死亡率预测因素,增强了临床决策.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 临床决策支持系统 临床决策支持系统
背景情况:
- 预测重症监护室 (ICU) 患者的死亡率对于治疗优化和资源管理至关重要.
- 机器学习 (ML) 模型显示出在ICU死亡率预测方面表现优于传统评分系统的潜力.
- 机器学习的"黑子"性质阻碍了临床采用,需要可解释的AI (XAI) 方法.
研究的目的:
- 用MIMIC-III数据集评估各种ML算法在预测ICU死亡率方面的准确性.
- 应用XAI技术,特别是SHapley添加式扩展 (SHAP),以确定死亡率的关键预测因素.
- 评估可解释的ML模型在支持临床决策方面的潜力.
主要方法:
- 从MIMIC-III数据库中对600个患者记录进行了回顾性分析.
- 实施和比较八个ML算法:SVM,KNN,DT,GB,RF,NB,LR和ET.
- 模型性能评估使用三重交叉验证,F1评分,灵敏度,特异性和准确性.
- SHAP的应用用于识别显著的死亡预测因素.
主要成果:
- 额外树木 (ET) 和梯度提升 (GB) 获得了最高的准确性 (98.33%和98.23%),F1得分超过96%.
- 支持矢量机 (SVM) 也表现出强的性能 (97.50%的准确性).
- SHAP分析发现高血压,瘤和内分泌/消化系统疾病是主要的死亡预测因素.
结论:
- ML算法,特别是ET和GB,对于预测ICU死亡率非常有效.
- 可解释AI (XAI) 对于建立信任和促进临床环境中ML的采用至关重要.
- 可解释的ML模型可以安全地支持知情的ICU决策,并改善患者的治疗结果.
相关概念视频
01:20Actuarial Approach
336
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
336
01:13Nonconscious Mimicry
5.2K
Nonconscious mimicry occurs when individuals alter their mannerisms to match the behaviors and expressions of those nearby, without intention.
5.2K
01:52Regression Toward the Mean
7.2K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
7.2K
01:03Prediction Intervals
3.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.5K