机器学习模型与用于预测皮肤冠状动脉干预结果的传统统计方法的比较:系统性审查和元分析
Sepehr Nayebirad1, Ali Hassanzadeh2, Amir Mohammad Vahdani3
1Tehran Heart Center, Cardiovascular Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran. nayebisepehr76@gmail.com.
BMC cardiovascular disorders
|April 24, 2025
概括
机器学习 (ML) 模型显示,与物流回归 (LR) 相比,穿皮冠状动脉干预 (PCI) 后的结果的预测略好. 然而,偏差和复杂性的高风险限制了ML的ML.
科学领域:
- 心脏病学 心脏病学
- 医疗信息学 医疗信息学
- 机器学习 机器学习
背景情况:
- 穿皮冠状动脉干预 (PCI) 是冠状动脉疾病 (CAD) 的首要治疗方法.
- 预测建模对于评估PCI后患者结果至关重要.
- 将机器学习 (ML) 和后勤回归 (LR) 模型进行比较对于推进预测准确性至关重要.
研究的目的:
- 系统地比较ML模型与LR模型的预测性能,用于PCI后的各种结果.
- 评估ML在PCI后预测死亡率,主要心脏不良事件 (MACE),出血和急性损伤 (AKI) 的有效性.
- 评估使用ML进行PCI结果预测的研究中的偏差风险.
主要方法:
- 对比ML或深度学习 (DL) 与PCI结果的LR模型的研究进行了全面的文献搜索.
- 包括的研究重点是预测死亡率,MACE,出血和AKI.
- 在聚合数据上进行了元分析,比较了表现最好的ML和LR模型,并使用PROBAST和CHARMS检查清单评估了偏差风险.
主要成果:
- 对59项研究的元分析表明,与LR相比,在所有评估结果中,ML模型的c-统计数据较高,包括长期死亡率 (0.84比0.79),短期死亡率 (0.91比0.85),出血 (0.81比0.77),AKI (0.81比0.75) 和MACE (0.85比0.75).
- 尽管预测值较高,但这些比较的P值并不显著,这表明没有统计学上显著的差异.
- 在包括的大量研究中发现了高偏差风险,特别是在ML模型中,从AKI的69%到长期死亡率的93%不等.
结论:
- 虽然ML模型显示PCI后结果的数值优异预测性能,但与LR模型相比,没有发现统计学上显著的差异.
- 研究中偏差的高患病率,特别是那些使用ML的研究,引起了人们对其有效性和临床适用性的担忧.
- 与复杂的ML模型相关的解释性挑战可能会阻碍它们在临床实践中得到广泛采用.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.6K
07:25Predicting Amputation using Local Circulating Mononuclear Progenitor Cells in Angioplasty-treated Patients with Critical Limb Ischemia
Published on: September 22, 2020
3.3K
相关概念视频
Kaplan-Meier Approach
55
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
55
Comparing the Survival Analysis of Two or More Groups
85
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
85
